Subjects -> ENGINEERING (Total: 2688 journals)
    - CHEMICAL ENGINEERING (229 journals)
    - CIVIL ENGINEERING (237 journals)
    - ELECTRICAL ENGINEERING (176 journals)
    - ENGINEERING (1325 journals)
    - ENGINEERING MECHANICS AND MATERIALS (452 journals)
    - HYDRAULIC ENGINEERING (56 journals)
    - INDUSTRIAL ENGINEERING (98 journals)
    - MECHANICAL ENGINEERING (115 journals)

ENGINEERING (1325 journals)                  1 2 3 4 5 6 7 | Last

Showing 1 - 200 of 1205 Journals sorted by number of followers
Composite Structures     Hybrid Journal   (Followers: 245)
IEEE Spectrum     Full-text available via subscription   (Followers: 219)
Composites Part B : Engineering     Hybrid Journal   (Followers: 219)
ACS Nano     Hybrid Journal   (Followers: 181)
Composites Part A : Applied Science and Manufacturing     Hybrid Journal   (Followers: 173)
Composites Science and Technology     Hybrid Journal   (Followers: 150)
IEEE Geoscience and Remote Sensing Letters     Hybrid Journal   (Followers: 149)
IEEE Instrumentation & Measurement Magazine     Hybrid Journal   (Followers: 148)
IEEE Communications Magazine     Full-text available via subscription   (Followers: 139)
IEEE Engineering Management Review     Full-text available via subscription   (Followers: 117)
IEEE Antennas and Propagation Magazine     Hybrid Journal   (Followers: 112)
IEEE Transactions on Control Systems Technology     Hybrid Journal   (Followers: 111)
IEEE Transactions on Instrumentation and Measurement     Hybrid Journal   (Followers: 106)
IEEE Transactions on Signal Processing     Hybrid Journal   (Followers: 92)
IEEE Antennas and Wireless Propagation Letters     Hybrid Journal   (Followers: 88)
IEEE Industry Applications Magazine     Full-text available via subscription   (Followers: 82)
IEEE Transactions on Antennas and Propagation     Full-text available via subscription   (Followers: 78)
IEEE Transactions on Engineering Management     Hybrid Journal   (Followers: 74)
Engineering Failure Analysis     Hybrid Journal   (Followers: 68)
IEEE Microwave Magazine     Full-text available via subscription   (Followers: 63)
IEEE Signal Processing Letters     Hybrid Journal   (Followers: 60)
IEEE Transactions on Reliability     Hybrid Journal   (Followers: 53)
Experimental Techniques     Hybrid Journal   (Followers: 51)
IET Radar, Sonar & Navigation     Open Access   (Followers: 50)
IEEE Transactions on Microwave Theory and Techniques     Hybrid Journal   (Followers: 49)
Control Engineering Practice     Hybrid Journal   (Followers: 46)
IEEE Journal of Selected Topics in Signal Processing     Hybrid Journal   (Followers: 43)
Biotechnology Progress     Hybrid Journal   (Followers: 42)
IEEE Potentials     Full-text available via subscription   (Followers: 42)
IEEE Journal on Selected Areas in Communications     Hybrid Journal   (Followers: 39)
Heat Transfer Engineering     Hybrid Journal   (Followers: 36)
IET Microwaves, Antennas & Propagation     Open Access   (Followers: 35)
International Journal for Numerical Methods in Engineering     Hybrid Journal   (Followers: 35)
IEEE Microwave and Wireless Components Letters     Hybrid Journal   (Followers: 35)
Digital Signal Processing     Hybrid Journal   (Followers: 34)
IEEE Transactions on Knowledge and Data Engineering     Hybrid Journal   (Followers: 31)
AIChE Journal     Hybrid Journal   (Followers: 31)
Computing in Science & Engineering     Full-text available via subscription   (Followers: 31)
Computers & Geosciences     Hybrid Journal   (Followers: 30)
Flow, Turbulence and Combustion     Hybrid Journal   (Followers: 30)
Coastal Management     Hybrid Journal   (Followers: 29)
Canadian Geotechnical Journal     Hybrid Journal   (Followers: 28)
GPS Solutions     Hybrid Journal   (Followers: 28)
Fluid Dynamics     Hybrid Journal   (Followers: 27)
Bell Labs Technical Journal     Hybrid Journal   (Followers: 27)
Géotechnique     Hybrid Journal   (Followers: 27)
IEEE Transactions on Information Theory     Hybrid Journal   (Followers: 27)
IEEE Transactions on Power Delivery     Hybrid Journal   (Followers: 26)
Applied Energy     Partially Free   (Followers: 26)
Advances in Engineering Software     Hybrid Journal   (Followers: 26)
IEEE Journal of Solid-State Circuits     Full-text available via subscription   (Followers: 24)
Corrosion Science     Hybrid Journal   (Followers: 23)
Engineering & Technology     Hybrid Journal   (Followers: 22)
IET Image Processing     Open Access   (Followers: 22)
Intermetallics     Hybrid Journal   (Followers: 21)
Combustion, Explosion, and Shock Waves     Hybrid Journal   (Followers: 21)
IEEE Transactions on Electronics Packaging Manufacturing     Hybrid Journal   (Followers: 21)
IET Signal Processing     Open Access   (Followers: 21)
IEEE Transactions on Circuits and Systems II: Express Briefs     Hybrid Journal   (Followers: 20)
Advanced Synthesis & Catalysis     Hybrid Journal   (Followers: 20)
Implementation Science     Open Access   (Followers: 20)
International Journal for Numerical Methods in Fluids     Hybrid Journal   (Followers: 19)
Engineering Optimization     Hybrid Journal   (Followers: 19)
International Communications in Heat and Mass Transfer     Hybrid Journal   (Followers: 19)
Electrophoresis     Hybrid Journal   (Followers: 18)
IET Circuits, Devices & Systems     Open Access   (Followers: 18)
IEEE/ACM Transactions on Computational Biology and Bioinformatics     Hybrid Journal   (Followers: 18)
International Journal of Adhesion and Adhesives     Hybrid Journal   (Followers: 18)
IEEE Transactions on Intelligent Transportation Systems     Hybrid Journal   (Followers: 17)
Experiments in Fluids     Hybrid Journal   (Followers: 17)
Computational Geosciences     Hybrid Journal   (Followers: 17)
Integration     Hybrid Journal   (Followers: 16)
IEEE Transactions on Energy Conversion     Hybrid Journal   (Followers: 16)
Engineering Geology     Hybrid Journal   (Followers: 16)
European Journal of Mass Spectrometry     Hybrid Journal   (Followers: 16)
Energy Conversion and Management     Hybrid Journal   (Followers: 15)
Bulletin of Engineering Geology and the Environment     Hybrid Journal   (Followers: 15)
Coastal Engineering     Hybrid Journal   (Followers: 15)
IEEE Transactions on Magnetics     Hybrid Journal   (Followers: 14)
IEEE Journal of Biomedical and Health Informatics     Hybrid Journal   (Followers: 14)
IEEE Transactions on Automation Science and Engineering     Full-text available via subscription   (Followers: 13)
IEEE Transactions on Evolutionary Computation     Hybrid Journal   (Followers: 13)
Electromagnetics     Hybrid Journal   (Followers: 13)
Computers and Geotechnics     Hybrid Journal   (Followers: 12)
IEEE Transactions on Semiconductor Manufacturing     Hybrid Journal   (Followers: 12)
IET Renewable Power Generation     Open Access   (Followers: 12)
Human Factors in Ergonomics & Manufacturing     Hybrid Journal   (Followers: 12)
IEEE Transactions on Professional Communication     Hybrid Journal   (Followers: 11)
Biomedical Engineering     Hybrid Journal   (Followers: 11)
IEEE Transactions on Education     Hybrid Journal   (Followers: 11)
CIRP Annals - Manufacturing Technology     Hybrid Journal   (Followers: 11)
IEEE Journal of Oceanic Engineering     Hybrid Journal   (Followers: 11)
Heat Transfer - Asian Research     Hybrid Journal   (Followers: 10)
International Journal of Antennas and Propagation     Open Access   (Followers: 10)
Proceedings of the Institution of Civil Engineers - Geotechnical Engineering     Hybrid Journal   (Followers: 10)
IEEE Transactions on Nuclear Science     Hybrid Journal   (Followers: 10)
IEEE Transactions on Plasma Science     Hybrid Journal   (Followers: 10)
Computers & Mathematics with Applications     Full-text available via subscription   (Followers: 9)
Fuel Cells Bulletin     Full-text available via subscription   (Followers: 9)
Computational Optimization and Applications     Hybrid Journal   (Followers: 9)
Annals of Science     Hybrid Journal   (Followers: 9)
European Journal of Engineering Education     Hybrid Journal   (Followers: 9)
Applied Catalysis B: Environmental     Hybrid Journal   (Followers: 9)
Biomedical Microdevices     Hybrid Journal   (Followers: 8)
IEEE Technology and Society Magazine     Full-text available via subscription   (Followers: 8)
Fuel Cells     Hybrid Journal   (Followers: 8)
Adaptive Behavior     Hybrid Journal   (Followers: 8)
Proceedings of the Institution of Civil Engineers - Bridge Engineering     Hybrid Journal   (Followers: 8)
Energy Engineering     Full-text available via subscription   (Followers: 8)
IEEE Transactions on Advanced Packaging     Full-text available via subscription   (Followers: 8)
Clay Minerals     Hybrid Journal   (Followers: 8)
Continuum Mechanics and Thermodynamics     Hybrid Journal   (Followers: 8)
Applied Catalysis A: General     Hybrid Journal   (Followers: 7)
International Journal of Applied Ceramic Technology     Hybrid Journal   (Followers: 7)
Basin Research     Hybrid Journal   (Followers: 7)
Discrete Optimization     Full-text available via subscription   (Followers: 7)
Designs, Codes and Cryptography     Hybrid Journal   (Followers: 7)
IEEE Journal of Selected Topics in Quantum Electronics     Hybrid Journal   (Followers: 7)
Environmental and Ecological Statistics     Hybrid Journal   (Followers: 7)
Biomicrofluidics     Open Access   (Followers: 7)
Geothermics     Hybrid Journal   (Followers: 7)
Fuel and Energy Abstracts     Full-text available via subscription   (Followers: 7)
IEEE Vehicular Technology Magazine     Full-text available via subscription   (Followers: 7)
Catalysis Communications     Hybrid Journal   (Followers: 7)
Computers and Electronics in Agriculture     Hybrid Journal   (Followers: 7)
Computer Applications in Engineering Education     Hybrid Journal   (Followers: 6)
Computing and Visualization in Science     Hybrid Journal   (Followers: 6)
Fusion Engineering and Design     Hybrid Journal   (Followers: 6)
Applied Clay Science     Hybrid Journal   (Followers: 6)
Composite Interfaces     Hybrid Journal   (Followers: 6)
Formal Methods in System Design     Hybrid Journal   (Followers: 6)
Acta Geotechnica     Hybrid Journal   (Followers: 6)
Advances in OptoElectronics     Open Access   (Followers: 6)
International Journal of Adaptive Control and Signal Processing     Hybrid Journal   (Followers: 5)
IEEE Transactions on Vehicular Technology     Hybrid Journal   (Followers: 5)
IET Science, Measurement & Technology     Open Access   (Followers: 5)
IEEE Transactions on Applied Superconductivity     Hybrid Journal   (Followers: 5)
International Journal of Architectural Computing     Full-text available via subscription   (Followers: 5)
Finite Fields and Their Applications     Full-text available via subscription   (Followers: 5)
Focus on Powder Coatings     Full-text available via subscription   (Followers: 5)
Engineering With Computers     Hybrid Journal   (Followers: 5)
Proceedings of the Institution of Civil Engineers - Engineering Sustainability     Hybrid Journal   (Followers: 5)
Archives of Computational Methods in Engineering     Hybrid Journal   (Followers: 5)
Active and Passive Electronic Components     Open Access   (Followers: 5)
Proceedings of the Institution of Civil Engineers - Ground Improvement     Hybrid Journal   (Followers: 4)
Frontiers in Energy     Hybrid Journal   (Followers: 4)
Adsorption     Hybrid Journal   (Followers: 4)
Catalysis Today     Hybrid Journal   (Followers: 4)
Applied Numerical Mathematics     Hybrid Journal   (Followers: 4)
Current Applied Physics     Full-text available via subscription   (Followers: 4)
Fluid Phase Equilibria     Hybrid Journal   (Followers: 4)
Graphs and Combinatorics     Hybrid Journal   (Followers: 4)
Filtration & Separation     Full-text available via subscription   (Followers: 4)
Annals of Pure and Applied Logic     Open Access   (Followers: 4)
Grass and Forage Science     Hybrid Journal   (Followers: 4)
Catalysis Surveys from Asia     Hybrid Journal   (Followers: 4)
Informatik-Spektrum     Hybrid Journal   (Followers: 3)
Engineering Computations     Hybrid Journal   (Followers: 3)
European Journal of Combinatorics     Full-text available via subscription   (Followers: 3)
Applicable Algebra in Engineering, Communication and Computing     Hybrid Journal   (Followers: 3)
Chaos : An Interdisciplinary Journal of Nonlinear Science     Hybrid Journal   (Followers: 3)
Concurrent Engineering     Hybrid Journal   (Followers: 3)
Focus on Pigments     Full-text available via subscription   (Followers: 3)
Annals of Combinatorics     Hybrid Journal   (Followers: 3)
Frontiers of Environmental Science & Engineering     Hybrid Journal   (Followers: 3)
Fuzzy Sets and Systems     Hybrid Journal   (Followers: 3)
Catalysis Letters     Hybrid Journal   (Followers: 3)
IET Generation, Transmission & Distribution     Open Access   (Followers: 2)
Historical Records of Australian Science     Hybrid Journal   (Followers: 2)
IET Optoelectronics     Open Access   (Followers: 2)
Assembly Automation     Hybrid Journal   (Followers: 2)
International Journal of Abrasive Technology     Hybrid Journal   (Followers: 2)
Aerobiologia     Hybrid Journal   (Followers: 2)
Cellular and Molecular Neurobiology     Hybrid Journal   (Followers: 2)
Comptes Rendus : Mécanique     Open Access   (Followers: 2)
Chinese Journal of Catalysis     Full-text available via subscription   (Followers: 2)
IEEE Latin America Transactions     Full-text available via subscription   (Followers: 2)
Communications in Numerical Methods in Engineering     Hybrid Journal   (Followers: 2)
ESAIM: Control Optimisation and Calculus of Variations     Open Access   (Followers: 2)
Focus on Surfactants     Full-text available via subscription   (Followers: 2)
Engineering Analysis with Boundary Elements     Hybrid Journal   (Followers: 2)
Chaos, Solitons & Fractals     Hybrid Journal   (Followers: 1)
Foundations of Science     Hybrid Journal   (Followers: 1)
Forschung     Hybrid Journal   (Followers: 1)
European Journal of Lipid Science and Technology     Hybrid Journal   (Followers: 1)
Antarctic Science     Hybrid Journal   (Followers: 1)
Épités - Épitészettudomány     Full-text available via subscription   (Followers: 1)
Dyes and Pigments     Hybrid Journal   (Followers: 1)
Bautechnik     Hybrid Journal   (Followers: 1)
Biointerphases     Open Access   (Followers: 1)
Designed Monomers and Polymers     Open Access   (Followers: 1)
Color Research & Application     Hybrid Journal   (Followers: 1)
Abstract and Applied Analysis     Open Access   (Followers: 1)
Focus on Catalysts     Full-text available via subscription  
ESAIM: Proceedings     Open Access  
Environmetrics     Hybrid Journal  
COMBINATORICA     Hybrid Journal  
Chinese Science Bulletin     Open Access  
Calphad     Hybrid Journal  
Boundary Value Problems     Open Access  

        1 2 3 4 5 6 7 | Last

Similar Journals
Journal Cover
IEEE Transactions on Signal Processing
Journal Prestige (SJR): 1.247
Citation Impact (citeScore): 6
Number of Followers: 92  
 
  Hybrid Journal Hybrid journal (It can contain Open Access articles)
ISSN (Print) 1053-587X
Published by IEEE Homepage  [228 journals]
  • IEEE Signal Processing Society

    • Free pre-print version: Loading...

      Abstract: Presents a listing of the editorial board, board of governors, current staff, committee members, and/or society editors for this issue of the publication.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Target Detection Using Quantized Cloud MIMO Radar Measurements

    • Free pre-print version: Loading...

      Authors: Zhen Wang;Qian He;Rick S. Blum;
      Pages: 1 - 16
      Abstract: Target detection is studied for a cloud multiple-input multiple-output (MIMO) radar using quantized measurements. According to the local sensor quantization strategies and fusion strategies, this paper discusses three methods: quantize local test statistics which are linearly fused (QTLF), quantize local test statistics which are optimally fused (QTOF), and quantize local received signals which are optimally fused (QROF). We first directly analyze the detection performance of each method when the quantizer output is represented as a discrete random variable, where it is difficult to obtain a closed-form expression for the detection probability. Then, an approximate description for the quantization is analyzed for the case of a Gaussian signal and a closed-form expression for the detection probability is obtained. We prove that the QTOF method outperforms the QTLF method in general, and for small SCNR the QROF method has the best detection performance among the three methods, while for large SCNR the QROF method performs the worst. The correctness of theoretical analysis is verified by simulations.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Ensemble Gaussian Processes for Online Learning Over Graphs With
           Adaptivity and Scalability

    • Free pre-print version: Loading...

      Authors: Konstantinos D. Polyzos;Qin Lu;Georgios B. Giannakis;
      Pages: 17 - 30
      Abstract: In the past decade, semi-supervised learning (SSL) over graphs has gained popularity due to its importance in a gamut of network science applications. While most of existing SSL methods provide only point estimates of the targeted variables, the present work capitalizes on Gaussian processes (GPs) to offer a Bayesian SSL approach over graphs with uncertainty quantification, a key attribute especially in safety-critical domains. To accommodate also delay-sensitive scenarios, an incremental learning mode is considered, where prediction of the desired value of a new node per iteration is followed by processing the corresponding nodal observation. Taking the per-node one-hop connectivity vector as the input, the prediction of targeted nodal value is enabled by leveraging an ensemble (E) of GP experts, whose weights are updated in a data-adaptive fashion. In the resultant GRaph-ADpative EGP framework, random feature-based kernel approximation is employed to not only allow learning with scalability, but also preserve privacy by relying on an encrypted version of each node’s connectivity. Besides the one-hop connectivity vector, the novel GradEGP accommodates each node’s egonet features as alternative inputs. On the analytical side, to assess the performance of GradEGP in the adversarial setting where the generative assumptions are violated, regret analysis measures the cumulative online losses relative to their counterparts of a benchmark learner with batch data in hindsight. Tests conducted on real and synthetic datasets demonstrate the effectiveness of the advocated method.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • The Impact of Multipath Information on Time-of-Arrival Estimation

    • Free pre-print version: Loading...

      Authors: Wesley M. Gifford;Davide Dardari;Moe Z. Win;
      Pages: 31 - 46
      Abstract: Time-of-arrival (TOA) based localization plays a central role in current and future localization systems. Such systems, exploiting the fine delay resolution properties of wideband and ultra-wideband (UWB) signals, are particularly attractive for ranging under harsh propagation conditions in which significant multipath may be present. While multipath has been traditionally considered detrimental in the design of TOA estimators, it can be exploited to benefit ranging. This paper investigates the impact of a priori multipath information on TOA estimation. To this end, bounds on the performance of TOA estimation in dense multipath channels are provided and discussed under different operating conditions. The effects of channel dispersion and transmission bandwidth on ranging systems are investigated showing that, contrary to communication systems, diversity behavior is only exhibited in the medium signal-to-noise ratio regime.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Innovative and Additive Outlier Robust Kalman Filtering With a Robust
           Particle Filter

    • Free pre-print version: Loading...

      Authors: Alexander T. M. Fisch;Idris A. Eckley;Paul Fearnhead;
      Pages: 47 - 56
      Abstract: In this paper, we propose CE-BASS, a particle mixture Kalman filter which is robust to both innovative and additive outliers, and able to fully capture multi-modality in the distribution of the hidden state. Furthermore, the particle sampling approach re-samples past states, which enables CE-BASS to handle innovative outliers which are not immediately visible in the observations, such as trend changes. The filter is computationally efficient as we derive new, accurate approximations to the optimal proposal distributions for the particles. The proposed algorithm is shown to compare well with existing approaches and is applied to both machine temperature and server data.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Functional Bayesian Filter

    • Free pre-print version: Loading...

      Authors: Kan Li;José C. Príncipe;
      Pages: 57 - 71
      Abstract: We present a general nonlinear Bayesian filter for high-dimensional state estimation using the theory of reproducing kernel Hilbert space (RKHS). By applying the kernel method and the representer theorem to perform linear quadratic estimation in a functional space, we derive a Bayesian recursive state estimator for a general nonlinear dynamical system in the original input space. Unlike existing nonlinear extensions of the Kalman filter where the system dynamics are assumed known, the state-space representation for the Functional Bayesian Filter (FBF) is completely learned online from measurement data in the form of an infinite impulse response (IIR) filter or recurrent network in the RKHS, with universal approximation property. Using a positive definite kernel function satisfying Mercer’s conditions to compute and evolve information quantities, the FBF exploits both the statistical and time-domain information about the signal, extracts higher-order moments, and preserves the properties of covariances without the ill effects due to conventional arithmetic operations. We apply this novel kernel adaptive filtering (KAF) to recurrent network training, chaotic time-series estimation and cooperative filtering using Gaussian and non-Gaussian noises, and inverse kinematics modeling. Simulation results show FBF outperforms existing Kalman-based algorithms.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Direction-of-Arrival Estimation for Large Antenna Arrays With Hybrid
           Analog and Digital Architectures

    • Free pre-print version: Loading...

      Authors: Ruoyu Zhang;Byonghyo Shim;Wen Wu;
      Pages: 72 - 88
      Abstract: The large antenna arrays with hybrid analog and digital (HAD) architectures can provide a large aperture with low cost and hardware complexity, resulting in enhanced direction-of-arrival (DOA) estimation and reduced power consumption. This paper investigates the trade-off between DOA estimation and power consumption in large antenna arrays with HAD architectures. Particularly, the DOA estimation problem of fully-connected, sub-connected (SC), and switches-based (SE) hybrid architectures is formulated into a unified expression, with the compression matrix in a time-varying form. Based on this model, we derive a dynamic maximum likelihood (D-ML) estimator that is suitable for both HAD and conventional fully digital (FD) structures, and the closed-form expression of Cramér-Rao bound (CRB) to evaluate the performance limit of the D-ML estimator for different HAD structures. The theoretical CRB analysis in the single-source case reveals that, the SC structure has the ability to achieve approximately the same performance as the FD structures at DOAs around zero, but suffers from the inherent angle ambiguity because of the antenna grouping. In addition, we propose a dynamic SC (D-SC) structure that is proved to eliminate the angle ambiguity with time-varying phase shifters, and a switch optimization (SWO) algorithm to minimize the CRB of SE structures. Finally, we introduce a new metric, DOA efficiency, to measure the trade-off between the DOA estimation performance and power consumption of different structures. Simulation results verify our theoretical analysis and the superiority of the proposed D-SC structure and the SWO algorithm.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Identifying Latent Stochastic Differential Equations

    • Free pre-print version: Loading...

      Authors: Ali Hasan;João M. Pereira;Sina Farsiu;Vahid Tarokh;
      Pages: 89 - 104
      Abstract: We present a method for learning latent stochastic differential equations (SDEs) from high dimensional time series data. Given a high-dimensional time series generated from a lower dimensional latent unknown Itô process, the proposed method learns the mapping from ambient to latent space, and the underlying SDE coefficients, through a self-supervised learning approach. Using the framework of variational autoencoders, we consider a conditional generative model for the data based on the Euler-Maruyama approximation of SDE solutions. Furthermore, we use recent results on identifiability of latent variable models to show that the proposed model can recover not only the underlying SDE coefficients, but also the original latent variables, up to an isometry, in the limit of infinite data. We validate the method through several simulated video processing tasks, where the underlying SDE is known, and through real world datasets.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Asynchrony Increases Efficiency: Time Encoding of Videos and Low-Rank
           Signals

    • Free pre-print version: Loading...

      Authors: Karen Adam;Adam Scholefield;Martin Vetterli;
      Pages: 105 - 116
      Abstract: In event-based sensing, many sensors independently and asynchronously emit events when there is a change in their input. Event-based sensing can present significant improvements in power efficiency when compared to traditional sampling, because (1) the output is a stream of events where the important information lies in the timing of the events, and (2) the sensor can easily be controlled to output information only when interesting activity occurs at the input. Moreover, event-based sampling can often provide better resolution than standard uniform sampling. Not only does this occur because individual event-based sensors have higher temporal resolution (Rebecq et al., 2021) it also occurs because the asynchrony of events within a sensor and therefore across sensors allows for less redundant and more informative encoding. We would like to explain how such curious results come about. To do so, we use ideal time encoding machines as a proxy for event-based sensors. We explore time encoding of signals with low rank structure, and apply the resulting theory to video. We then see how the asynchronous firing across time encoding machines can couple spatial sampling density with temporal resolution, leading to better reconstruction, whereas, in frame-based video, temporal resolution depends solely on the frame-rate and spatial resolution solely on the pixel grid used.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Complex Parameter Rao, Wald, Gradient, and Durbin Tests for Multichannel
           Signal Detection

    • Free pre-print version: Loading...

      Authors: Mengru Sun;Weijian Liu;Jun Liu;Chengpeng Hao;
      Pages: 117 - 131
      Abstract: In the problem of multichannel signal detection, when it comes to the detector design criteria apart from the generalized likelihood ratio test, the traditional method is to cascade the real and imaginary parts of the parameters, and then substitute them into the real parameter statistics. This method is not succinct, and sometimes may be cumbersome and difficult to handle. Recently, a complex parameter Rao test was introduced by Kay and Zhu without the need of cascading the real and imaginary parts of the complex parameters when there is no nuisance parameter. Inspired by this work, we move a further step toward the complex parameter statistics of the Rao, Wald, gradient, and Durbin tests both with and without nuisance parameters, and derive the relationships between their real and complex parameter statistics. Moreover, for a special Fisher information matrix which often holds in practice, we derive a series of simple forms of the complex parameter statistics for the above four criteria, and discuss their application conditions in linear multivariate complex circular Gaussian distribution. Finally, several application examples are given to confirm the proposed schemes.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • On the Correlation Concentration of Discrete Prolate Spheroidal Sequences

    • Free pre-print version: Loading...

      Authors: Karim A. Said;A. A. Louis Beex;
      Pages: 132 - 141
      Abstract: For theessential set of discrete prolate spheroidal sequences (DPSS) corresponding to a given discrete-time-bandwidth product, we show that the auto and cross-correlations between the member sequences of the set also exhibit high concentration over a correlation length twice the concentration length of the member sequences. We start by deriving one upper bound and two lower bounds for the energy of the correlation sequence of index-limited DPSSs from which we derive similar bounds for the energy of DPSS correlation sequences. Then, we obtain an upper bound for the tail energy of DPSS correlation sequences. Finally, we obtain a lower bound for the concentration ratio of DPSS correlation sequences. All derived bounds require knowledge of the following parameters for each DPSS sequence in the correlation pair: corresponding eigen-value, Fourier transform evaluated at two special frequency points, derivative of the Fourier transform evaluated at the same two points. Most of the aforementioned parameters can be expressed or bounded by functions in the global parameters: sequence length and discrete-time-bandwidth.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Quantization for Communication-Efficient Change-Point Detection Over
           Networks

    • Free pre-print version: Loading...

      Authors: Yuchen Jiao;Xingyu Xu;Yuantao Gu;
      Pages: 142 - 157
      Abstract: Change-Point Detection (CPD) has been researched for a long time in statistical signal processing, and has been widely used in many applications such as monitoring and anomaly detection. When detecting over networks, existing algorithms require sensors to exchange information via transmitting full-precision variables, which requires large bandwidth and consumes a large amount of energy. To address these problems, we explore the idea of quantizing data with low precision without deteriorating the detection performance. Specifically, considering the strong autocorrelation of the transmitted sequence in time domain and the accumulation of quantization error due to the autocorrelation, we design a scheme that combines the differential quantization technique and the error feedback technique. Based on this scheme, we propose a communication-efficient decentralized CPD algorithm named Quantized CUSUM (Q-CUSUM), which only requires small bandwidth and has low energy consumption. We theoretically analyze two commonly-used detection criteria, namely Average Run Length (ARL) and Expected Detection Delay (EDD), and compute their theoretical bounds. It is proved that the detection performance is robust to the quantization error. The proposed quantization scheme can be easily extended to the partial-communication case, where at each time only a subset of sensor pairs are allowed to exchange information. Experiments are implemented on both synthetic and real-world datasets. The results indicate that the proposed quantization scheme can effectively reduce the communication cost without deteriorating the detection performance.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Data-Driven Representations for Testing Independence: Modeling, Analysis
           and Connection With Mutual Information Estimation

    • Free pre-print version: Loading...

      Authors: Mauricio E. Gonzalez;Jorge F. Silva;Miguel Videla;Marcos E. Orchard;
      Pages: 158 - 173
      Abstract: This work addresses testing the independence of two continuous and finite-dimensional random variables from the design of a data-driven partition. The empirical log-likelihood statistic is adopted to approximate the sufficient statistics of an oracle test against independence (that knows the two hypotheses). It is shown that approximating the sufficient statistics of the oracle test offers a learning criterion for designing a data-driven partition that connects with the problem of mutual information estimation. Applying these ideas in the context of a data-dependent tree-structured partition (TSP), we derive conditions on the TSP’s parameters to achieve a strongly consistent distribution-free test of independence over the family of probabilities equipped with a density. Complementing this result, we present finite-length results that show our TSP scheme’s capacity to detect the scenario of independence structurally with the data-driven partition as well as new sampling complexity bounds for this detection. Finally, some experimental analyses provide evidence regarding our scheme’s advantage for testing independence compared with some strategies that do not use data-driven representations.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Anomaly Search With Multiple Plays Under Delay and Switching Costs

    • Free pre-print version: Loading...

      Authors: Tidhar Lambez;Kobi Cohen;
      Pages: 174 - 189
      Abstract: The problem of searching for $L$ anomalous processes among $M$ processes is considered. At each time, the decision maker can observe a subset of $K$ processes (i.e., multiple plays). The measurement drawn when observing a process follows one of two different distributions, depending on whether the process is normal or abnormal. The goal is to design a policy that minimizes the Bayes risk which balances between the sample complexity, detection errors, and the switching cost associated with switching across processes. We develop a policy, dubbed consecutive controlled sensing (CCS), to achieve this goal. On the one hand, by contrast to existing studies on controlled sensing, the CCS policy senses processes consecutively to reduce the switching cost. On the other hand, the policy controls the sensing operation in a closed-loop manner to switch between processes when necessary to guarantee reliable inference. We prove theoretically that CCS is asymptotically optimal in terms of minimizing the Bayes risk as the detection error approaches zero (i.e., the sample complexity increases). Simulation results demonstrate strong performance of CCS in the finite regime as well. Index Terms - Anomaly detection, controlled sensing, active hypothesis testing, sequential design of experiments.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Local Strong Convexity of Source Localization and Error Bound for Target
           Tracking under Time-of-Arrival Measurements

    • Free pre-print version: Loading...

      Authors: Yuen-Man Pun;Anthony Man-Cho So;
      Pages: 190 - 201
      Abstract: In this paper, we consider a time-varying optimization approach to the problem of tracking a moving target using noisy time-of-arrival (TOA) measurements. Specifically, we formulate the problem as that of sequential TOA-based source localization and apply online gradient descent (OGD) to it to generate the position estimates of the target. To analyze the tracking performance of OGD, we first revisit the classic least-squares formulation of the (static) TOA-based source localization problem and elucidate its estimation and geometric properties. In particular, under standard assumptions on the TOA measurement model, we establish a bound on the distance between an optimal solution to the least-squares formulation and the true target position. Using this bound, we show that the loss function in the formulation, albeit non-convex in general, is locally strongly convex at its global minima. To the best of our knowledge, these results are new and can be of independent interest. By combining them with existing techniques from online strongly convex optimization, we then establish the first non-trivial bound on the cumulative target tracking error of OGD. Our numerical results corroborate the theoretical findings and show that OGD can effectively track the target at different noise levels.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Improving Sum-Rate of Cell-Free Massive MIMO With Expanded
           Compute-and-Forward

    • Free pre-print version: Loading...

      Authors: Jiayi Zhang;Jing Zhang;Derrick Wing Kwan Ng;Shi Jin;Bo Ai;
      Pages: 202 - 215
      Abstract: Cell-free massive multiple-input multiple-output (MIMO) employs a large number of distributed access points (APs) to serve a small number of user equipments (UEs) via the same time/frequency resource. Due to the strong macro diversity gain, cell-free massive MIMO can considerably improve the achievable sum-rate compared to conventional cellular massive MIMO. However, the performance of cell-free massive MIMO is upper limited by inter-user interference (IUI) when employing simple maximum ratio combining (MRC) at receivers. To harness IUI, the expanded compute-and-forward (ECF) framework is adopted. In particular, we propose power control algorithms for the parallel computation and successive computation in the ECF framework, respectively, to exploit the performance gain and then improve the system performance. Furthermore, we propose an AP selection scheme and the application of different decoding orders for the successive computation. Finally, numerical results demonstrate that ECF frameworks outperform the conventional CF and MRC frameworks in terms of achievable sum-rate.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Analysis of Reassignment Operators Used in Synchrosqueezing Transforms:
           With an Application to Instantaneous Frequency Estimation

    • Free pre-print version: Loading...

      Authors: Sylvain Meignen;Neha Singh;
      Pages: 216 - 227
      Abstract: In this paper, our goal is first to investigate the behavior of reassignment operators used in synchrosqueezing transforms applied to multicomponent signals made of the superposition of amplitude and frequency modulated modes. Indeed, while these operators are associated with instantaneous frequency estimators very accurate on specific types of modes, the quality of the former worsens drastically when the modes depart from the ideal case they are designed for. We show in this paper that this particularly true when the modes interfere in the time-frequency plane or when some noise is present. Based on that analysis, we propose a novel instantaneous frequency estimator that only makes use of some specific points located on the ridges of synchrosqueezing transforms, and compare its performance with state-of-the-art techniques based on the same type of time-frequency representations.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Extended Target Tracking With a Lidar Sensor Using Random Matrices and a
           Virtual Measurement Model

    • Free pre-print version: Loading...

      Authors: Patrick Hoher;Stefan Wirtensohn;Tim Baur;Johannes Reuter;Felix Govaers;Wolfgang Koch;
      Pages: 228 - 239
      Abstract: Random matrices are widely used to estimate the extent of an elliptically contoured object. Usually, it is assumed that the measurements follow a normal distribution, with its standard deviation being proportional to the object’s extent. However, the random matrix approach can filter the center of gravity and the covariance matrix of measurements independently of the measurement model. This work considers the whole chain from data acquisition to the linear Kalman Filter with extension estimation as a reference plant. The input is the (unknown) ground truth (position and extent). The output is the filtered center of gravity and the filtered covariance matrix of the measurement distribution. A virtual measurement model emulates the behavior of the reference plant. The input of the virtual measurement model is adapted using the proposed algorithm until the output parameters of the virtual measurement model match the result of the reference plant. After the adaptation, the input to the virtual measurement model is considered an estimation for position and extent. The main contribution of this paper is the reference model concept and an adaptation algorithm to optimize the input of the virtual measurement model.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Cramér-Rao Bound Optimization for Joint Radar-Communication
           Beamforming

    • Free pre-print version: Loading...

      Authors: Fan Liu;Ya-Feng Liu;Ang Li;Christos Masouros;Yonina C. Eldar;
      Pages: 240 - 253
      Abstract: In this paper, we propose multi-input multi-output (MIMO) beamforming designs towards joint radar sensing and multi-user communications. We employ the Cramér-Rao bound (CRB) as a performance metric of target estimation, under both point and extended target scenarios. We then propose minimizing the CRB of radar sensing while guaranteeing a pre-defined level of signal-to-interference-plus-noise ratio (SINR) for each communication user. For the single-user scenario, we derive a closed form for the optimal solution for both cases of point and extended targets. For the multi-user scenario, we show that both problems can be relaxed into semidefinite programming by using the semidefinite relaxation approach, and prove that the global optimum can be generally obtained. Finally, we demonstrate numerically that the globally optimal solutions are reachable via the proposed methods, which provide significant gains in target estimation performance over state-of-the-art benchmarks.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • A General Framework for Constrained Convex Quaternion Optimization

    • Free pre-print version: Loading...

      Authors: Julien Flamant;Sebastian Miron;David Brie;
      Pages: 254 - 267
      Abstract: This paper introduces a general framework for solving constrained convex quaternion optimization problems in the quaternion domain. To soundly derive these new results, the proposed approach leverages the recently developed generalized $mathbb {H}mathbb {R}$-calculus together with the equivalence between the original quaternion optimization problem and its augmented real-domain counterpart. This new framework simultaneously provides rigorous theoretical foundations as well as elegant, compact quaternion-domain formulations for optimization problems in quaternion variables. Our contributions are threefold: (i) we introduce the general form for convex constrained optimization problems in quaternion variables, (ii) we extend fundamental notions of convex optimization to the quaternion case, namely Lagrangian duality and optimality conditions, (iii) we develop the quaternion alternating direction method of multipliers (Q-ADMM) as a general purpose quaternion optimization algorithm. The relevance of the proposed methodology is demonstrated by solving two typical examples of constrained convex quaternion optimization problems arising in signal processing. Our results open new avenues in the design, analysis and efficient implementation of quaternion-domain optimization procedures.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Analysis of Adaptive Detectors Robustness to Mismatches on Noise Mean
           Value

    • Free pre-print version: Loading...

      Authors: Olivier Besson;François Vincent;
      Pages: 268 - 279
      Abstract: We consider the problem of detecting a signal of interest corrupted by Gaussian noise with unknown mean and covariance matrix when the training samples available have a different mean. We evaluate the robustness of well-known adaptive detectors designed under the assumption of a same mean. More precisely, statistical representations of the generalized likelihood ratio test, the adaptive matched filter and the adaptive coherence estimator are derived for both an additive model with an arbitrary mismatch between the means, and a replacement model which is widely used in hyperspectral imaging. The new representations are given in terms of simple $F$ distributions and are shown to depend in a simple way on the norm of the whitened mean difference and its angle with the whitened signal of interest signature, or on the replacement factor. These new representations allow to identify the key parameters that impact most the probability of false alarm and probability of detection. Numerical simulations illustrate the theoretical results.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Structural Sparsity in Multiple Measurements

    • Free pre-print version: Loading...

      Authors: F. Boßmann;S. Krause-Solberg;J. Maly;N. Sissouno;
      Pages: 280 - 291
      Abstract: We propose a novel sparsity model for distributed compressed sensing in the multiple measurement vectors (MMV) setting. Our model extends the concept of row-sparsity to allow more general types of structured sparsity arising in a variety of applications like, e.g., seismic exploration and non-destructive testing. To reconstruct structured data from observed measurements, we derive a non-convex but well-conditioned LASSO-type functional. By exploiting the convex-concave geometry of the functional, we design a projected gradient descent algorithm and show its effectiveness in extensive numerical simulations, both on toy and real data.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Filter Distortions in Ultra High-Throughput Satellites: Models, Parameters
           and Multicarrier Optimization

    • Free pre-print version: Loading...

      Authors: Tony Colin;Thomas Delamotte;Andreas Knopp;
      Pages: 292 - 306
      Abstract: Ultra high-throughput satellite systems are expected to play an essential role in future beyond 5G and 6G networks. These systems must remain as flexible as possible to adapt to heterogeneous traffic demands, while also delivering the highest possible rate for dedicated services. Satellites flexible payloads are increasingly employing wideband output multiplexers. In this context, it is now more important than ever to evaluate frequency-dependent degradations on multicarrier signals. In particular, it is critical to characterize the distortions entailed by the output multiplexers filters. In this paper, models are presented and novel formulas are derived to determine the carrier-to-interference ratio resulting from these distortions. Derivations are oriented towards the applicability of either high-accuracy (e.g., for link budget) or low-complexity calculations (e.g., for real-time carrier allocation). The influence of key parameters such as the optimal decision instant, symbol rate and roll-off factor is thoroughly analyzed. Furthermore, formulas are evaluated in a practical scenario: the dynamic carrier allocation optimization. They are combined with efficient optimization algorithms to obtain the best performance based on user fairness. Relevant metrics such as accuracy, complexity and allocation gain are also investigated. In the end, the application of the proposed formulas and algorithms leads to a significant allocation gain that is increasing with the number of carriers. The feasibility of real-time dynamic carrier allocation to further increase the capacity of the next generation of satellite systems is emphasized.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Escaping Saddle Points for Successive Convex Approximation

    • Free pre-print version: Loading...

      Authors: Amrit Singh Bedi;Ketan Rajawat;Vaneet Aggarwal;Alec Koppel;
      Pages: 307 - 321
      Abstract: Optimizing non-convex functions is of primary importance in modern pattern recognition because it underlies the training of deep networks and nonlinear dimensionality reduction. First-order algorithms under suitable randomized perturbations or step-size rules have been shown to be effective for such settings as their limit points can be guaranteed to be local extrema rather than saddle points. However, it is well-known that the practical convergence of first-order methods is slower than those which exploit additional structure. In particular, empirically, successive convex approximation (SCA) converges faster than first-order methods. However, to date, SCA in general non-convex settings converges to first-order stationary points, which could either be local extrema or saddle points whose performance is typically inferior. To mitigate this issue, we propose calibrated randomized perturbations of SCA, which exhibit the improved convergence rate as compared to the gradient descent counter part. In particular, our main technical contributions are to establish the non-asymptotic performance of SCA algorithm and its perturbed variant converges to an approximate second-order stationary point. Experiments on multi-dimensional scaling, a machine learning problem whose training objective is non-convex, substantiate the performance gains associated with employing random perturbations.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Fusion of Sensor Measurements and Target-Provided Information in
           Multitarget Tracking

    • Free pre-print version: Loading...

      Authors: Domenico Gaglione;Paolo Braca;Giovanni Soldi;Florian Meyer;Franz Hlawatsch;Moe Z. Win;
      Pages: 322 - 336
      Abstract: Tracking multiple time-varying states based on heterogeneous observations is a key problem in many applications. Here, we develop a statistical model and algorithm for tracking an unknown number of targets based on the probabilistic fusion of observations from two classes of data sources. The first class, referred to as target-independent perception systems (TIPSs), consists of sensors that periodically produce noisy measurements of targets without requiring target cooperation. The second class, referred to as target-dependent reporting systems (TDRSs), relies on cooperative targets that report noisy measurements of their state and their identity. We present a joint TIPS–TDRS observation model that accounts for observation-origin uncertainty, missed detections, false alarms, and asynchronicity. We then establish a factor graph that represents this observation model along with a state evolution model including target identities. Finally, by executing the sum-product algorithm on that factor graph, we obtain a scalable multitarget tracking algorithm with inherent TIPS–TDRS fusion. The performance of the proposed algorithm is evaluated using simulated data as well as real data from a maritime surveillance experiment.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Joint ML/MAP Estimation of the Frequency and Phase of a Single Sinusoid
           With Wiener Carrier Phase Noise

    • Free pre-print version: Loading...

      Authors: Qian Wang;Zhi Quan;Suzhi Bi;Pooi-Yuen Kam;
      Pages: 337 - 350
      Abstract: We address here the issue of jointly estimating the angle parameters of a single sinusoid with Wiener carrier phase noise and observed in additive, white, Gaussian noise (AWGN). We develop the theoretical foundation for time-domain, phase-based, joint maximum likelihood (ML) estimation of the unknown carrier frequency and the initial carrier phase, with simultaneous maximum a posteriori probability (MAP) estimation of the time-varying carrier phase noise. The derivation is based on the amplitude and phase-form of the noisy received signal model together with the use of the best, linearized, additive observation phase noise model due to AWGN. Our newly derived estimators are closed-form expressions, consisting of both the phase and the magnitude of all the received signal samples. More importantly, they all have a low-complexity, sample-by-sample iterative processing structure, which can be implemented iteratively in real-time. As a basis for comparison, the Cramer-Rao lower bound (CRLB) for the ML estimators and the Bayesian CRLB (BCRLB) for the MAP estimator are derived in the presence of carrier phase noise, and the results simply depend on the signal-to-noise ratio (SNR), the observation length and the phase noise variance. It is theoretically shown that the estimates obtained are unbiased, and the mean-square error (MSE) of the estimators attain the CRLB/BCRLB at high SNR. The MSE performance as a function of the SNR, the observation length and the phase noise variance is verified using Monte Carlo simulation, which shows a remarkable improvement in estimation accuracy in large phase noise.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Composite Hypothesis Tests for Detection of Modeling Misspecification

    • Free pre-print version: Loading...

      Authors: Ofir Krauz;Joseph Tabrikian;
      Pages: 351 - 365
      Abstract: The performance of model-based signal processing inference methods may significantly degrade due to model errors. Thus, detection of model misspecification (MM) is essential in many applications. One of the most prominent MM detection approaches is based on comparison between the empirical characteristic function (CF) and the CF of the assumed model. However, there is no concrete or optimal method to extract the relevant information for MM detection. Another popular approach for MM detection is the information matrix test (IMT), which is based on the Cramér-Rao bound (CRB) regularity condition. This method is insensitive in some basic problems and it requires a twice continuously-differentiable probability density function of the observation under the null hypothesis. In order to address these issues, three new methods for MM detection are proposed in this paper. In the first method, it is proposed to address the CF frequency selection question via an optimization procedure, yielding the optimized characteristic function test (OCFT). In addition, a local version of the OCFT, called the optimized local characteristic function test (OLCFT), which combines information obtained from the CF and information matrix equality, is proposed. This test stems from the generalization of both the CF and the CRB regularity condition. In order to address the differentiabilty limitation, the IMT for MM detection is extended by a finite-difference form, named, discrete IMT (DIMT). Thus, it is applicable for discrete-valued parameters or classification problems. The performances of the proposed methods are studied via several signal processing examples.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Learned Factor Graphs for Inference From Stationary Time Sequences

    • Free pre-print version: Loading...

      Authors: Nir Shlezinger;Nariman Farsad;Yonina C. Eldar;Andrea J. Goldsmith;
      Pages: 366 - 380
      Abstract: The design of methods for inference from time sequences has traditionally relied on statistical models that describe the relation between a latent desired sequence and the observed one. A broad family of model-based algorithms have been derived to carry out inference at controllable complexity using recursive computations over the factor graph representing the underlying distribution. An alternative model-agnostic approach utilizes machine learning (ML) methods. Here we propose a framework that combines model-based algorithms and data-driven ML tools for stationary time sequences. In the proposed approach, neural networks are developed to separately learn specific components of a factor graph describing the distribution of the time sequence, rather than the complete inference task. By exploiting stationary properties of this distribution, the resulting approach can be applied to sequences of varying temporal duration. Learned factor graphs can be realized using compact neural networks that are trainable using small training sets, or alternatively, be used to improve upon existing deep inference systems. We present an inference algorithm based on learned stationary factor graphs, which learns to implement the sum-product scheme from labeled data, and can be applied to sequences of different lengths. Our experimental results demonstrate the ability of the proposed learned factor graphs to learn from small training sets to carry out accurate inference for sleep stage detection using the Sleep-EDF dataset, as well as for symbol detection in digital communications with unknown channels.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Adaptive Graph-Constrained Group Testing

    • Free pre-print version: Loading...

      Authors: Saurabh Sihag;Ali Tajer;Urbashi Mitra;
      Pages: 381 - 396
      Abstract: This paper considers the problem of adaptive group testing for isolating up to $k$ defective items from a population of size $n$. There exist restrictions or preferences which determine how the items can be pooled for testing. A graphical model formalizes the pooling restrictions and preferences. Such graph-constrained group testing is investigated in three settings: populations with defectives, populations facing the potential presence of inhibitors, and populations with community structures. Adaptive group testing frameworks are provided for each setting. In populations without inhibitors, existing non adaptive frameworks can isolate the defective items perfectly with $Theta(k log n/k)$ number of tests, where is the$beta$-mixing time of a random walk over the underlying graph. This paper provides a two-stage framework that can perfectly isolate up to $k$ defective items for a regular graph using $Theta(k2 log n k + k)$ number of tests, thus achieving an approximate gain of a factor of $k$ over the non-adaptive frameworks. This twostage framework's principles are extended to community-structured graphs and graphs with up to $r$ inhibitor items. In particular, when inhibitors are present in the graph, a four-stage group testing framework is proposed. The results show that in the regime $r= O(k)$ for a fully connected graph, $Theta ((k+r)log n/(k+r) + rlog n)$ tests are sufficient for isolating the defective items. This matches the corresponding necessary condition on tests which scales $(k+r)log n$. The adaptive graphconstrained group testing framework is also empirically evaluated.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • On Non-Linear Trajectory Tracking via Variety-Based Background Subtraction
           Models

    • Free pre-print version: Loading...

      Authors: Amr Elnakeeb;Urbashi Mitra;
      Pages: 397 - 409
      Abstract: Trajectory tracking wherein the trajectories can be described by polynomials in the spatial coordinate space is considered. A background subtraction model is extended to include an algebraic variety-based low rank constraint that captures the trajectory. The optimization is solved via the Iteratively Reweighted Least Squares method, adapted to the new signal model. The convergence of the Variety-based Background Subtraction Iterative Reweighted Least Squares (VBSI) algorithm is investigated, where a boundedness analysis is conducted. It is proved that the sequence of estimates generated by VBSI is bounded; furthermore, any limit point of that sequence is a stationary point of the optimization problem. An aggregated error function is shown to converge to zero. A bound on the estimation error is derived that characterizes the relationship between performance and system parameters. Simulation results show that the proposed algorithm achieves excellent recovery of the key matrices in both noisy and noiseless scenarios, and typically converges in 20 iterations. Furthermore, a performance improvement of 2.4 dB with regards to the Mean Square Error is observed over prior methods. Finally, the proposed technique is applied to real video data and shown to be effective in estimating non-linear trajectories.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Tensor Wiener Filter

    • Free pre-print version: Loading...

      Authors: Shih Yu Chang;Hsiao-Chun Wu;
      Pages: 410 - 422
      Abstract: In signal processing and data analytics, Wiener filter is a classical powerful tool to transform an input signal to match a desired or target signal by a linear time-invariant (LTI) filter. The input signal of a Wiener filter is one-dimensional while its associated least-squares solution, namely Wiener-Hopf equation, involves a two-dimensional data-array, or correlation matrix. However, the actual match should often be carried out between a multi-dimensional filtered signal-sequence, which is the output of a multi-channel filter characterized as a linear-time-invariant MIMO (multi-input and multi-output) system, and a multi-dimensional desired signal-sequence simultaneously. In the presence of such a multi-channel filter, the solution to the corresponding Wiener filter, which we call MIMO Wiener-Hopf equation now, involves a correlation tensor. Therefore, we call this optimal multi-channel filter Tensor Wiener Filter (TWF). Due to lack of the pertinent mathematical framework of needed tensor operations, TWF has never been investigated so far. Now we would like to make the first-ever attempt to establish a new mathematical framework for TWF, which relies on the inverse of the correlation tensor. We propose the new parallel block-Jacobi tensor-inversion algorithm for this tensor inversion. A typical application of the new TWF approach is illustrated as a multi-channel linear predictor (MCLP) built upon a multi-channel autoregressive (MCAR) filter with multi-dimensional input data. Numerical experiments pertaining to seismic data, optical images, and macroeconomic time-series are conducted in comparison with other existing methods. The memory- and computational-complexities corresponding to our proposed parallel block-Jacobi tensor-inversion algorithm are also studied in this paper.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • A Variational Bayesian Inference-Inspired Unrolled Deep Network for MIMO
           Detection

    • Free pre-print version: Loading...

      Authors: Qian Wan;Jun Fang;Yinsen Huang;Huiping Duan;Hongbin Li;
      Pages: 423 - 437
      Abstract: The great success of deep learning (DL) has inspired researchers to develop more accurate and efficient symbol detectors for multi-input multi-output (MIMO) systems. Existing DL-based MIMO detectors, however, suffer several drawbacks. To address these issues, in this paper, we develop a model-driven DL detector based on variational Bayesian inference. Specifically, the proposed unrolled DL architecture is inspired by an inverse-free variational Bayesian learning framework which circumvents matrix inversion via maximizing a relaxed evidence lower bound. Two networks are respectively developed for independent and identically distributed (i.i.d.) Gaussian channels and arbitrarily correlated channels. The proposed networks, referred to as VBINet, have only a few learnable parameters and thus can be efficiently trained with a moderate amount of training samples. The proposed VBINet-based detectors can work in both offline and online training modes. An important advantage of our proposed networks over state-of-the-art MIMO detection networks such as OAMPNet and MMNet is that the VBINet can automatically learn the noise variance from data, thus yielding a significant performance improvement over the OAMPNet and MMNet in the presence of noise variance uncertainty. Simulation results show that the proposed VBINet-based detectors achieve competitive performance for both i.i.d. Gaussian and realistic 3GPP MIMO channels.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Sampling and Reconstruction of Sparse Signals in Shift-Invariant Spaces:
           Generalized Shannon’s Theorem Meets Compressive Sensing

    • Free pre-print version: Loading...

      Authors: Tin Vlašić;Damir Seršić;
      Pages: 438 - 451
      Abstract: This paper introduces a novel framework and corresponding methods for sampling and reconstruction of sparse signals in shift-invariant (SI) spaces. We reinterpret the random demodulator, a system that acquires sparse bandlimited signals, as a system for the acquisition of linear combinations of the samples in the SI setting with the box function as the sampling kernel. The sparsity assumption is exploited by the compressive sensing (CS) paradigm for a recovery of the SI samples from a reduced set of measurements. The SI samples are subsequently filtered by a discrete-time correction filter to reconstruct expansion coefficients of the observed signal. Furthermore, we offer a generalization of the proposed framework to other compactly supported sampling kernels that span a wider class of SI spaces. The generalized method embeds the correction filter in the CS optimization problem which directly reconstructs expansion coefficients of the signal. Both approaches recast an inherently continuous-domain inverse problem in a set of finite-dimensional CS problems in an exact way. Finally, we conduct numerical experiments on signals in polynomial B-spline spaces whose expansion coefficients are assumed to be sparse in a certain transform domain. The coefficients can be regarded as parametric models of an underlying continuous-time signal, obtained from a reduced set of measurements. Such continuous signal representations are particularly suitable for signal processing without converting them into samples.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Distributionally Robust State Estimation for Linear Systems Subject to
           Uncertainty and Outlier

    • Free pre-print version: Loading...

      Authors: Shixiong Wang;Zhi-Sheng Ye;
      Pages: 452 - 467
      Abstract: Parameter uncertainties and measurement outliers unavoidably exist in a real linear system. Such uncertainties and outliers make the true joint state-measurement distributions (induced by the true system model) deviate from the nominal ones (induced by the nominal system model) so that the performance of the optimal state estimator designed for the nominal model becomes unsatisfactory or even unacceptable in practice. The challenges are to quantitatively describe the uncertainties in the model and the outliers in the measurements, and then robustify the estimator in a right way. This article studies a distributionally robust state estimation framework for linear systems subject to parameter uncertainties and measurement outliers. It utilizes a family of distributions near the nominal one to implicitly describe the uncertainties and outliers, and the robust state estimation in the worst case is made over the least-favorable distribution. The advantages of the presented framework include: 1) it only uses a few scalars to parameterize the method and does not require the structural information of uncertainties; 2) it generalizes several classical filters (e.g., the fading Kalman filter, risk-sensitive Kalman filter, relative-entropy Kalman filter, outlier-insensitive Kalman filters) into a unified framework. We show that the distributionally robust state estimation problem can be reformulated into a linear semi-definite program and in some special cases it can be analytically solved. Comprehensive comparisons with existing state estimation frameworks that are insensitive to parameter uncertainties and measurement outliers are also conducted.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • “Self-Wiener” Filtering: Data-Driven Deconvolution of
           Deterministic Signals

    • Free pre-print version: Loading...

      Authors: Amir Weiss;Boaz Nadler;
      Pages: 468 - 481
      Abstract: We consider the problem of robust deconvolution, and particularly the recovery of an unknown deterministic signal convolved with a known filter and corrupted by additive noise. We present a novel, non-iterative data-driven approach. Specifically, our algorithm works in the frequency-domain, where it tries to mimic the optimal unrealizable non-linear Wiener-like filter as if the unknown deterministic signal were known. This leads to a threshold-type regularized estimator, where the threshold at each frequency is determined in a data-driven manner. We perform a theoretical analysis of our proposed estimator, and derive approximate formulas for its Mean Squared Error (MSE) at both low and high Signal-to-Noise Ratio (SNR) regimes. We show that in the low SNR regime our method provides enhanced noise suppression, and in the high SNR regime it approaches the optimal unrealizable solution. Further, as we demonstrate in simulations, our solution is highly suitable for (approximately) bandlimited or frequency-domain sparse signals, and provides a significant gain of several dBs relative to other methods in the resulting MSE.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Over-Parametrized Matrix Factorization in the Presence of Spurious
           Stationary Points

    • Free pre-print version: Loading...

      Authors: Armin Eftekhari;
      Pages: 482 - 496
      Abstract: Motivated by the emerging role of interpolating machines in signal processing and machine learning, this work considers the computational aspects of over-parametrized matrix factorization. In this context, the optimization landscape may contain spurious stationary points (SSPs), which are proved to be full-rank matrices. The presence of these SSPs means that it is impossible to hope for any global guarantees in over-parametrized matrix factorization. For example, when initialized at an SSP, the gradient flow will be trapped there forever. Nevertheless, despite these SSPs, we establish in this work that the gradient flow of the corresponding merit function converges to a global minimizer, provided that its initialization is rank-deficient and sufficiently close to the feasible set of the optimization problem. We numerically observe that a heuristic discretization of the proposed gradient flow, inspired by primal-dual algorithms, is successful when initialized randomly. Our result is in sharp contrast with the local refinement methods which require an initialization close to the optimal set of the optimization problem. More specifically, we successfully avoid the traps set by the SSPs because the gradient flow remains rank-deficient at all times, and not because there are no SSPs nearby. The latter is the case for the local refinement methods. Moreover, the widely-used restricted isometry property plays no role in our main result.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Online Particle Smoothing With Application to Map-Matching

    • Free pre-print version: Loading...

      Authors: Samuel Duffield;Sumeetpal S. Singh;
      Pages: 497 - 508
      Abstract: We introduce a novel method for online smoothing in state-space models that utilises a fixed-lag approximation to overcome the well known issue of path degeneracy. Unlike classical fixed-lag techniques that only approximate certain marginals, we introduce an online resampling algorithm, called particle stitching, that converts these marginal samples into a full posterior approximation. We demonstrate the utility of our method in the context of map-matching, the task of inferring a vehicle’s trajectory given a road network and noisy GPS observations. We develop a new state-space model for the difficult task of map-matching on dense, urban road networks.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Joint Parameter Estimation From Binary Observations Over Decentralized
           Channels

    • Free pre-print version: Loading...

      Authors: Wenzhe Fan;Yili Xia;Chunguo Li;Yongming Huang;Björn Ottersten;
      Pages: 509 - 522
      Abstract: In wireless sensor networks, due to the bandwidth constraint, the distributed nodes (DNs) might only provide binary representatives of the source signal, and then transmit them to the central node (CN). In this paper, we consider the joint estimation of signal amplitude and background noise variance from binary observations over decentralized channels. We first analyze the Cramér–Rao lower bounds (CRLBs) of the parameters of interest and develop a quasilinear estimator (QLE), in which the desirable estimates can be obtained from several intermediate parameters linearly. Next, we consider a more realistic situation where the decentralized channel is noisy during the data transmission. Based on the error propagation model, the asymptotic analysis shows that the performance of the proposed QLE is mainly dominated by the thresholds of the quantizers, which encourages us to adopt a correlated quantization (CQ) scheme by exploiting the spatial correlation among background noises/channel noises. To ease the implementation of QLE in practice, an adaptive quantization (AQ) scheme is also proposed so as to obtain reasonable selections of the required thresholds. Finally, numerical simulations are provided to validate our theoretical findings.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Distributed Primal-Dual Method for Convex Optimization With Coupled
           Constraints

    • Free pre-print version: Loading...

      Authors: Yanxu Su;Qingling Wang;Changyin Sun;
      Pages: 523 - 535
      Abstract: Distributed primal-dual methods have been widely used for solving large-scale constrained optimization problems. The majority of existing results focus on the problems with decoupled constraints. Some recent works have studied the problems subject to separable globally coupled constraints. This paper considers the distributed optimization problems with globally coupled constraints over networks without requiring the separability of the globally coupled constraints. This is made possible by the local estimates of the constraint violations. For solving such a problem, we propose a primal-dual algorithm in the augmented Lagrangian framework, combining the average consensus technique. We first establish a non-ergodic convergence rate of $mathcal {O}(1/k)$ in terms of the objective residual for solving a distributed constrained convex optimization problem, where $k$ is the iteration counter. Specifically, the global objective function is the aggregate of the local convex and possibly non-smooth costs, and the coupled constraint is the sum of the local linear equality constraints. The numerical results illustrate the performance of the proposed method.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Total Least Squares Phase Retrieval

    • Free pre-print version: Loading...

      Authors: Sidharth Gupta;Ivan Dokmanić;
      Pages: 536 - 549
      Abstract: We address the phase retrieval problem with errors in the sensing vectors. A number of recent methods for phase retrieval are based on least squares (LS) formulations which assume errors in the quadratic measurements. We extend this approach to handle errors in the sensing vectors by adopting the total least squares (TLS) framework that is used in linear inverse problems with operator errors. We show how gradient descent and the specific geometry of the phase retrieval problem can be used to obtain a simple and efficient TLS solution. Additionally, we derive the gradients of the TLS and LS solutions with respect to the sensing vectors and measurements which enables us to calculate the solution errors. By analyzing these error expressions we determine conditions under which each method should outperform the other. We run simulations to demonstrate that our method can lead to more accurate solutions. We further demonstrate the effectiveness of our approach by performing phase retrieval experiments on real optical hardware which naturally contains both sensing vector and measurement errors.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • A Novel Wireless Communication Paradigm for Intelligent Reflecting Surface
           Based Symbiotic Radio Systems

    • Free pre-print version: Loading...

      Authors: Meng Hua;Qingqing Wu;Luxi Yang;Robert Schober;H. Vincent Poor;
      Pages: 550 - 565
      Abstract: This paper investigates a novel intelligent reflecting surface (IRS)-based symbiotic radio (SR) system architecture consisting of a transmitter, an IRS, and an information receiver (IR). The primary transmitter communicates with the IR and at the same time assists the IRS in forwarding information to the IR. Based on the IRS’s symbol period, we distinguish two scenarios, namely, commensal SR (CSR) and parasitic SR (PSR), where two different techniques for decoding the IRS signals at the IR are employed. We formulate bit error rate (BER) minimization problems for both scenarios by jointly optimizing the active beamformer at the base station and the phase shifts at the IRS, subject to a minimum primary rate requirement. Specifically, for the CSR scenario, a penalty-based algorithm is proposed to obtain a high-quality solution, where semi-closed-form solutions for the active beamformer and the IRS phase shifts are derived based on Lagrange duality and Majorization-Minimization methods, respectively. For the PSR scenario, we apply a bisection search-based method, successive convex approximation, and difference of convex programming to develop a computationally efficient algorithm, which converges to a locally optimal solution. Simulation results demonstrate the effectiveness of the proposed algorithms and show that the proposed SR techniques are able to achieve a lower BER than benchmark schemes.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Asymptotic Spectral Representation of Linear Convolutional Layers

    • Free pre-print version: Loading...

      Authors: Xinping Yi;
      Pages: 566 - 581
      Abstract: By stacking a number of convolutional layers, convolutional neural networks (CNNs) have made remarkable performance boosts in many artificial intelligence applications. While the convolution operation is well-understood, it is still a mystery why repeated convolutions yield so good expressive power and generalization performance. Noting that the linear convolution operation can be represented as a matrix-vector product with the matrix being of a Toeplitz structure, we propose to inspect the individual convolutional layer through its asymptotic spectral representation - the spectral density matrix - by leveraging Toeplitz matrix theory. Thanks to such spectral representation, we are able to develop a simple singular value approximation method with improved accuracy, and spectral norm upper bounds with reduced computational complexity, compared with the state-of-the-art methods. Both the improved approximation and upper bounds can be employed as regularization techniques to further enhance the generalization performance of CNNs. By extensive experiments on well-deployed CNN models (e.g., ResNets), we also demonstrate that the approximation approach achieves higher accuracy and the upper bounds are effective spectral regularizers for generalization.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Probabilistic Simplex Component Analysis

    • Free pre-print version: Loading...

      Authors: Ruiyuan Wu;Wing-Kin Ma;Yuening Li;Anthony Man-Cho So;Nicholas D. Sidiropoulos;
      Pages: 582 - 599
      Abstract: This study presents PRISM, a probabilistic simplex component analysis approach to identifying the vertices of a data-circumscribing simplex from data. The problem has a rich variety of applications, the most notable being hyperspectral unmixing in remote sensing and non-negative matrix factorization in machine learning. PRISM uses a simple probabilistic model, namely, uniform simplex data distribution and additive Gaussian noise, and it carries out inference by maximum likelihood. The inference model is sound in the sense that the vertices are provably identifiable under some assumptions, and it suggests that PRISM can be effective in combating noise when the number of data points is large. PRISM has strong, but hidden, relationships with simplex volume minimization, a powerful geometric approach for the same problem. We study these fundamental aspects, and we also consider algorithmic schemes based on importance sampling and variational inference. In particular, the variational inference scheme is shown to resemble a matrix factorization problem with a special regularizer, which draws an interesting connection to the matrix factorization approach. Numerical results are provided to demonstrate the potential of PRISM.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Quantized Corrupted Sensing With Random Dithering

    • Free pre-print version: Loading...

      Authors: Zhongxing Sun;Wei Cui;Yulong Liu;
      Pages: 600 - 615
      Abstract: Corrupted sensing concerns the problem of recovering a high-dimensional structured signal from a collection of measurements that are contaminated by unknown structured corruption and unstructured noise. In the case of linear measurements, the recovery performance of different convex programming procedures (e.g., generalized Lasso and its variants) is well established in the literature. However, in practical applications of digital signal processing, the quantization process is inevitable, which often leads to non-linear measurements. This paper is devoted to studying corrupted sensing under quantized measurements. Specifically, we demonstrate that, with the aid of uniform dithering, both constrained and unconstrained Lassos can stably recover signal and corruption from the quantized samples when the measurement matrix is sub-Gaussian. Our theoretical results reveal the role of quantization resolution in the recovery performance of Lassos. Numerical experiments are provided to confirm our theoretical results.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • The Surprising Benefits of Hysteresis in Unlimited Sampling: Theory,
           Algorithms and Experiments

    • Free pre-print version: Loading...

      Authors: Dorian Florescu;Felix Krahmer;Ayush Bhandari;
      Pages: 616 - 630
      Abstract: The Unlimited Sensing Framework (USF) was recently introduced to overcome the sensor saturation bottleneck in conventional digital acquisition systems. At its core, the USF converts a continuous-time high-dynamic-range (HDR) signal into folded, low-dynamic-range, modulo samples and allows the recovery of the HDR signal via algorithmic unfolding. In hardware, however, implementing ideal modulo folding requires careful calibration, analog design and high precision. At the interface of theory and practice, this paper explores a computational sampling strategy that relaxes strict hardware requirements via a novel, mathematically guaranteed reconstruction. We start with a generalized model for USF with two new parameters modeling hysteresis and folding transients in addition to the modulo threshold. Hysteresis accounts for mismatches between the reset threshold and the amplitude displacement at the folding time and the folding transient is a continuous transition period in the implementation of a reset. Both these effects are motivated by our hardware experiments and also occur in previous, domain-specific applications. We show that hysteresis is beneficial for USF and leverage it to derive the first recovery guarantees in the context of our generalized USF model for a certain sampling rate regime. Additionally, we show how the sampling rate requirement can be greatly reduced via a direct generalization of the proposed recovery. Our theoretical work is corroborated by hardware experiments with a hysteresis enabled, modulo ADC testbed comprising off-the-shelf electronic components. Thus, by capitalizing on a collaboration between hardware and algorithms, our paper enables an end-to-end pipeline for HDR sampling allowing more flexible hardware implementations.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • The Level Set Kalman Filter for State Estimation of Continuous-Discrete
           Systems

    • Free pre-print version: Loading...

      Authors: Ningyuan Wang;Daniel B. Forger;
      Pages: 631 - 642
      Abstract: We propose a new extension of Kalman filtering for continuous-discrete systems with nonlinear state-space models that we name as the level set Kalman filter (LSKF). The LSKF assumes the probability distribution can be approximated as a Gaussian and updates the Gaussian distribution through a time-update step and a measurement-update step. The LSKF improves the time-update step compared to existing methods, such as the continuous-discrete cubature Kalman filter (CD-CKF), by reformulating the underlying Fokker-Planck equation as an ordinary differential equation for the Gaussian, thereby avoiding the need for the explicit expression of the higher derivatives. Together with a carefully picked measurement-update method, numerical experiments show that the LSKF has a consistent performance improvement over the CD-CKF for a range of parameters. Meanwhile, the LSKF simplifies implementation, as no user-defined timestep subdivisions between measurements are required, and the spatial derivatives of the drift function are not explicitly needed.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Quantization Analysis and Robust Design for Distributed Graph Filters

    • Free pre-print version: Loading...

      Authors: L. Ben Saad;B. Beferull-Lozano;Elvin Isufi;
      Pages: 643 - 658
      Abstract: Distributed graph filters have recently found applications in wireless sensor networks (WSNs) to solve distributed tasks such as reaching consensus, signal denoising, and reconstruction. However, when implemented over WSNs, the graph filters should deal with network limited energy constraints as well as processing and communication capabilities. Quantization plays a fundamental role to improve the latter but its effects on distributed graph filtering are little understood. WSNs are also prone to random link losses due to noise and interference. In this instance, the filter output is affected by both the quantization error and the topological randomness error, which, if it is not properly accounted in the filter design phase, may lead to an accumulated error through the filtering iterations and significantly degrade the performance. In this paper, we analyze how quantization affects distributed graph filtering over both time-invariant and time-varying graphs. We bring insights on the quantization effects for the two most common graph filters: the finite impulse response (FIR) and autoregressive moving average (ARMA) graph filter. Besides providing a comprehensive analysis, we devise theoretical performance guarantees on the filter performance when the quantization stepsize is fixed or changes dynamically over the filtering iterations. For FIR filters, we show that a dynamic quantization stepsize leads to more reduction of the quantization noise than in the fixed-stepsize quantization. For ARMA graph filters, we show that decreasing the quantization stepsize over the iterations reduces the quantization noise to zero at the steady-state. In addition, we propose robust filter design strategies that minimize the quantization noise for both time-invariant and time-varying networks. Numerical experiments on synthetic and two real data sets corroborate our findings and show the different trade-offs between quantization bits, filter order, and robustness to topological rand-mness.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Linear Pooling of Sample Covariance Matrices

    • Free pre-print version: Loading...

      Authors: Elias Raninen;David E. Tyler;Esa Ollila;
      Pages: 659 - 672
      Abstract: We consider the problem of estimating high-dimensional covariance matrices of $K$-populations or classes in the setting where the sample sizes are comparable to the data dimension. We propose estimating each class covariance matrix as a distinct linear combination of all class sample covariance matrices. This approach is shown to reduce the estimation error when the sample sizes are limited, and the true class covariance matrices share a somewhat similar structure. We develop an effective method for estimating the coefficients in the linear combination that minimize the mean squared error under the general assumption that the samples are drawn from (unspecified) elliptically symmetric distributions possessing finite fourth-order moments. To this end, we utilize the spatial sign covariance matrix, which we show (under rather general conditions) to be an asymptotically unbiased estimator of the normalized covariance matrix as the dimension grows to infinity. We also show how the proposed method can be used in choosing the regularization parameters for multiple target matrices in a single class covariance matrix estimation problem. We assess the proposed method via numerical simulation studies including an application in global minimum variance portfolio optimization using real stock data.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Parameter Training Methods for Convolutional Neural Networks With Adaptive
           Adjustment Method Based on Borges Difference

    • Free pre-print version: Loading...

      Authors: Jing Jian;Zhe Gao;Tao Kan;
      Pages: 673 - 685
      Abstract: This paper proposes a momentum algorithm based on Borges difference and an adaptive momentum (Adam) algorithm based on Borges difference to update parameters, which can adjust the momentum information more flexibly. The Borges difference is proposed from the definition of Borges derivative to be combined with the gradient algorithm in convolutional neural networks. The proposed momentum algorithm based on Borges difference and Adam algorithm based on Borges difference can be adjusted more flexibly in order to speed up the convergence. The parameter optimization algorithm with the Borges difference presents a better performance compared with the integer-order momentum algorithm and integer-order Adam algorithm, with the proposed nonlinear adjustment method for the parameter tuning of convolutional neural networks. By analyzing experimental results of Fashion-MNIST dataset and CIFAR-10 dataset, the optimization algorithms based on Borges difference proposed in this paper gain better effects on the optimization model compared with the corresponding ones based on the integer-order difference, and can speed up the convergence speed and recognition accuracy of the image recognition.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Projection Filtering With Observed State Increments With Applications in
           Continuous-Time Circular Filtering

    • Free pre-print version: Loading...

      Authors: Anna Kutschireiter;Luke Rast;Jan Drugowitsch;
      Pages: 686 - 700
      Abstract: Angular path integration is the ability of a system to estimate its own heading direction from potentially noisy angular velocity (or increment) observations. Non-probabilistic algorithms for angular path integration, which rely on a summation of these noisy increments, do not appropriately take into account the reliability of such observations, which is essential for appropriately weighing one’s current heading direction estimate against incoming information. In a probabilistic setting, angular path integration can be formulated as a continuous-time nonlinear filtering problem (circular filtering) with observed state increments. The circular symmetry of heading direction makes this inference task inherently nonlinear, thereby precluding the use of popular inference algorithms such as Kalman filters, rendering the problem analytically inaccessible. Here, we derive an approximate solution to circular continuous-time filtering, which integrates state increment observations while maintaining a fixed representation through both state propagation and observational updates. Specifically, we extend the established projection-filtering method to account for observed state increments and apply this framework to the circular filtering problem. We further propose a generative model for continuous-time angular-valued direct observations of the hidden state, which we integrate seamlessly into the projection filter. Applying the resulting scheme to a model of probabilistic angular path integration, we derive an algorithm for circular filtering, which we term the circular Kalman filter. Importantly, this algorithm is analytically accessible, interpretable, and outperforms an alternative filter based on a Gaussian approximation.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Hyperspectral Image Classification Using Adaptive Weighted Quaternion
           Zernike Moments

    • Free pre-print version: Loading...

      Authors: Huizhen Li;Hua Huang;Zhijing Ye;Hongfeng Li;
      Pages: 701 - 713
      Abstract: Hyperspectral image classification (HSI) has been widely used in many fields. However, image noise, atmospheric conditions, material distribution and other factors seriously degrade the classification accuracy of HSIs. To alleviate these issues, a new approach, namely adaptive weighted quaternion Zernike moments (AWQZM), is proposed, which extracts effective spatial-spectral features for pixels in HSI classification. The main contributions and novelties of the method are as follows: 1) the AWQZM can adaptively set weights for each pixel in the neighborhood, which not only can flexibly search for homogeneous regions of HSIs, but also can strengthen the similarity of pixels from the same class and the distinctiveness of pixels from different classes; 2) the AWQZM can be constructed in a small subset of bands through a grouping strategy, thereby reducing the computational complexity; and 3) the introduction of quaternions can preserve the spatial correlation among bands and reduce the loss of data information, and the use of quaternion phase information makes the extracted features more informative and discriminative. Moreover, the spectral features and spatial features are combined to achieve better HSI classification results. Experimental results on three benchmark data sets demonstrate that the proposed approach achieves better classification performance than other related approaches.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Outlier-Resistant Filtering With Dead-Zone-Like Censoring Under
           Try-Once-Discard Protocol

    • Free pre-print version: Loading...

      Authors: Hang Geng;Zidong Wang;Alireza Mousavi;Fuad E. Alsaadi;Yuhua Cheng;
      Pages: 714 - 728
      Abstract: In this paper, a novel outlier-resistant filtering problem is concerned for a class of networked systems with dead-zone-like censoring under the weighted try-once-discard protocol (WTODP). To describe the phenomenon of dead-zone-like censoring, the sensor output is characterized by the Tobit model in which the censored region is restrained by specified left- and right-censoring thresholds. The WTODP is employed to decide the transmission sequence of sensors so as to alleviate undesirable data collisions. In the case of the measurement outliers, a saturation function is employed in the Tobit Kalman filter structure to constrain the innovations contaminated by the measurement outliers, thereby maintaining satisfactory filtering performance. By resorting to the approach of the matrix inequality, an upper bound is first obtained on the filtering error covariance where the gain matrix of the Tobit Kalman filter is carefully designed to minimize the obtained upper bound. Moreover, the exponential boundedness of the filtering error is analyzed in the mean square sense. Finally, the effectiveness of the proposed outlier-resistant filtering algorithm is verified by three practical examples.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Joint Radar and Communications for Frequency-Hopped MIMO Systems

    • Free pre-print version: Loading...

      Authors: William Baxter;Elias Aboutanios;Aboulnasr Hassanien;
      Pages: 729 - 742
      Abstract: Contention in the frequency spectrum has seen the emergence of Dual-Function Radar Communications (DFRC) systems, enabling frequency-hopped (FH) multiple-input-multiple-output (MIMO) waveforms to carry communication symbols. While a variety of novel signaling strategies have been developed to facilitate the communication function, their implementation in slow-time results in the achievable data rate being limited by the radar pulse repetition interval. We develop a generalized framework for performing information embedding in DFRC systems by exploiting the fast-time structure of the transmitted radar waveform. By defining a unified formulation, we show that a variety of existing signaling strategies can be accommodated, including FH index modulation, FH permutation, quadrature amplitude modulation (QAM), M-arry PSK (MPSK) modulation and/or frequency carrier index modulation. In addition, we use this framework to propose hybrid modulation strategies constructed using combinations of the aforementioned schemes to produce significant improvements in the achievable data rate over the individual signaling schemes. Simulation results demonstrate that the hybrid schemes can deliver significantly higher bit rates with only small increases in the required $E_b/N_0$. They also show that, in terms of the impact on the radar operation, the frequency hopping code selection has the highest range sidelobes whereas the PSK schemes suffer from significant spectral leakage. Finally, we also give a discussion of the issues and open problems that remain unaddressed.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Efficient DOA Estimation Method for Reconfigurable Intelligent Surfaces
           Aided UAV Swarm

    • Free pre-print version: Loading...

      Authors: Peng Chen;Zhimin Chen;Beixiong Zheng;Xianbin Wang;
      Pages: 743 - 755
      Abstract: The conventional direction of arrival (DOA) estimation methods are performed with multiple receiving channels. In this paper, a changeling DOA estimation problem is addressed in a different scenario with only one full-functional receiving channel. A new unmanned aerial vehicle (UAV) swarm system using multiple lifted reconfigurable intelligent surface (RIS) is proposed for the DOA estimation. The UAV movement degrades the DOA estimation performance significantly, and the existing atomic norm minimization (ANM) methods cannot be used in the scenario with array perturbation. Specifically, considering the position perturbation of UAVs, a new atomic norm-based DOA estimation method is proposed, where an atomic norm is defined with the parameter of the position perturbation. Then, a customized semi-definite programming (SDP) method is derived to solve the atomic norm-based method, where different from the traditional SDP method, an additional transforming matrix is formulated. Moreover, a gradient descent method is applied to refine the estimated DOA and the position perturbation further. Simulation results show that the proposed method achieves much better DOA estimation performance in the RIS-aided UAV swarm system with only one receiving channel than various benchmark schemes.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Efficient Algorithms for Constant-Modulus Analog Beamforming

    • Free pre-print version: Loading...

      Authors: Aakash Arora;Christos G. Tsinos;M. R. Bhavani Shankar;Symeon Chatzinotas;Björn Ottersten;
      Pages: 756 - 771
      Abstract: The use of a large-scale antenna array (LSAA) has become an important characteristic of multi-antenna communication systems to achieve beamforming gains such as in designing millimeter-wave (mmWave) systems to combat severe propagation losses. In such applications, each antenna element has to be driven by a radio frequency (RF) chain for the implementation of fully-digital beamformers, significantly increasing the hardware cost, complexity, and power consumption. Therefore, constant-modulus analog beamforming (CMAB) becomes a viable solution. In this paper, we consider the scaled analog beamforming (SAB) or constant-modulus analog beamforming (CMAB) architecture and design the system parameters by solving two variants of beampattern matching problem. In the first case, both the magnitude and phase of the beampattern are matched to the given desired beampattern whereas in the second case, only the magnitude of the beampattern is matched. Both the beampattern matching problems are cast as a variant of the constant-modulus least-squares (CLS) problem. We provide efficient algorithms based on the alternating majorization-minimization (AMM) framework that combines the alternating minimization and the MM frameworks and the conventional-cyclic coordinate descent (C-CCD) algorithms to solve the problem in each case. We also propose algorithms based on a new modified-CCD (M-CCD) based approach. For all the developed algorithms we prove convergence to a Karush-Kuhn-Tucker (KKT) point (or a stationary point). Numerical results demonstrate that the proposed algorithms converge faster than the state-of-the-art solutions. Among all the algorithms, the M-CCD-based algorithms have faster convergence when evaluated in terms of the number of iterations and the AMM-based algorithms offer lower complexity.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • JOT: A Variational Signal Decomposition Into Jump, Oscillation and Trend

    • Free pre-print version: Loading...

      Authors: Antonio Cicone;Martin Huska;Sung-Ha Kang;Serena Morigi;
      Pages: 772 - 784
      Abstract: We propose a two stages signal decomposition method which efficiently separates a given signal into Jump, Oscillation and Trend. While there have been numerous advances in signal processing in past few decades, they mainly aim to analyze the signal in terms of oscillating (underlying frequencies) or non-oscillating (underlying trend) features. Both traditional Time-Frequency analysis methods, like Short Time Fourier Transform, wavelet, and advanced ones, like Synchrosqueezing wavelet, Hilbert Huang Transform or IMFogram, can fail when abrupt changes and jump discontinuities appear in the signal. We present a variational framework separating piece-wise constant jump features as well as smooth trends and oscillating features of a given signal. In the first stage, a three component signal decomposition is applied, using sparsity promoting regularization, and Sobolev spaces of negative differentiability to model oscillations. In the second stage, components are refined using residuals of other components. The proposed method finds big and small jumps, is stable against high level of noise, is independent from the choice of basis functions, and does not have different level of decompositions which can be affected by large discontinuities. This variational framework is free from training in network-based approaches, and can be used for generating training data. The optimization problem is efficiently solved by an alternating minimization strategy. Applied as pre-processing for time-frequency analysis and Synchrosqueezing, it allows for improvements in results showing much clearer separation without artifacts. The proposed method is tested against synthetic data, where the ground truth is known, and real world data.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Tensor Convolutional Dictionary Learning With CP Low-Rank Activations

    • Free pre-print version: Loading...

      Authors: Pierre Humbert;Laurent Oudre;Nicolas Vayatis;Julien Audiffren;
      Pages: 785 - 796
      Abstract: In this paper, we propose to extend the standard Convolutional Dictionary Learning problem to a tensor representation where the activations are constrained to be “low-rank” through a Canonical Polyadic decomposition. We show that this additional constraint increases the robustness of the CDL with respect to noise and improve the interpretability of the final results. In addition, we discuss in detail the advantages of this representation and introduce two algorithms, based on ADMM or FISTA, that efficiently solve this problem. We show that by exploiting the low rank property of activations, they achieve lower complexity than the main CDL algorithms. Finally, we evaluate our approach on a wide range of experiments, highlighting the modularity and the advantages of this tensorial low-rank formulation.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Fast and Robust Sparsity Learning Over Networks: A Decentralized Surrogate
           Median Regression Approach

    • Free pre-print version: Loading...

      Authors: Weidong Liu;Xiaojun Mao;Xin Zhang;
      Pages: 797 - 809
      Abstract: Decentralized sparsity learning has attracted a significant amount of attention recently due to its rapidly growing applications. To obtain the robust and sparse estimators, a natural idea is to adopt the non-smooth median loss combined with a $ell _1$ sparsity regularizer. However, most of the existing methods suffer from slow convergence performance caused by the double non-smooth objective. To accelerate the computation, in this paper, we proposed a decentralized surrogate median regression (deSMR) method for efficiently solving the decentralized sparsity learning problem. We show that our proposed algorithm enjoys a linear convergence rate with a simple implementation. We also investigate the statistical guarantee, and it shows that our proposed estimator achieves a near-oracle convergence rate without any restriction on the number of network nodes. Moreover, we establish the theoretical results for sparse support recovery. Thorough numerical experiments and real data study are provided to demonstrate the effectiveness of our method.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Parameter Estimation in PMCW MIMO Radar Systems With Few-Bit Quantized
           Observations

    • Free pre-print version: Loading...

      Authors: Chao-Yi Wu;Tianyi Zhang;Jian Li;Tan F. Wong;
      Pages: 810 - 821
      Abstract: We consider the problem of target parameter estimation in phase modulated continuous wave (PMCW) multiple-input multiple-output (MIMO) radar systems with quantized observations. We derive the Cramér-Rao bound (CRB) for jointly estimating targets’ amplitudes, time delays, Doppler shifts, and directions. The derived bound provides an efficient method to analyze the estimation performance achieved by different quantization schemes. We also devise the maximum likelihood (ML) estimator for the considered parameters, and a direct grid-based method (DGM) is introduced to obtain the ML estimates. To obtain the ML estimates more efficiently, a two-stage scheme is proposed. In the proposed scheme, we first formulate the estimation problem as a sparse signal recovery problem and modify the sparse learning via iterative minimization (SLIM) approach to solve it. Next, a RELAX-based iterative algorithm is proposed to refine the estimates. Simulation results show that the proposed scheme can approach the CRB. Simulation results also show that using quantized observations does not affect the estimation performance significantly when the targets’ amplitudes are similar.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Interference Mitigation for FMCW Radar With Sparse and Low-Rank Hankel
           Matrix Decomposition

    • Free pre-print version: Loading...

      Authors: Jianping Wang;Min Ding;Alexander Yarovoy;
      Pages: 822 - 834
      Abstract: In this paper, the interference mitigation for Frequency Modulated Continuous Wave (FMCW) radar system with a dechirping receiver is investigated. After dechirping operation, the scattered signals from targets result in beat signals, i.e., the sum of complex exponentials while the interferences lead to chirp-like short pulses. Taking advantage of these different time and frequency features between the useful signals and the interferences, the interference mitigation is formulated as an optimization problem: a sparse and low-rank decomposition of a Hankel matrix constructed by lifting the measurements. Then, an iterative optimization algorithm is proposed to tackle it by exploiting the Alternating Direction of Multipliers (ADMM) scheme. Compared to the existing methods, the proposed approach does not need to detect the interference and also improves the estimation accuracy of the separated useful signals. Both numerical simulations with point-like targets and experiment results with distributed targets (i.e., raindrops) are presented to demonstrate and verify its performance. The results show that the proposed approach is generally applicable for interference mitigation in both stationary and moving target scenarios.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Two-Dimensional Multi-Target Detection: An Autocorrelation Analysis
           Approach

    • Free pre-print version: Loading...

      Authors: Shay Kreymer;Tamir Bendory;
      Pages: 835 - 849
      Abstract: We consider thetwo-dimensional multi-target detection problem of recovering a target image from a noisy measurement that contains multiple copies of the image, each randomly rotated and translated. Motivated by the structure reconstruction problem in single-particle cryo-electron microscopy, we focus on the high noise regime, where the noise hampers accurate detection of the image occurrences. We develop an autocorrelation analysis framework to estimate the image directly from a measurement with an arbitrary spacing distribution of image occurrences, bypassing the estimation of individual locations and rotations. We conduct extensive numerical experiments, and demonstrate image recovery in highly noisy environments.1
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Reinforcement Learning for Motion Policies in Mobile Relaying Networks

    • Free pre-print version: Loading...

      Authors: Spilios Evmorfos;Konstantinos I. Diamantaras;Athina P. Petropulu;
      Pages: 850 - 861
      Abstract: We consider joint beamforming and relay motion control in mobile relay beamforming networks, operating in a spatio-temporally varying channel environment. A time slotted approach is adopted, where in each slot, the relays implement optimal beamforming and estimate their optimal positions for the next slot. We place the problem of relay motion control in a sequential decision-making framework. We employ Reinforcement Learning (RL) to guide the relay motion, with the goal of maximizing the cumulative Signal-to-Interference+Noise Ratio (SINR) at the destination. First, we present a model based RL approach, which predictively estimates the SINR and accordingly determines the relay motion, based on partial knowledge of the channel model along with channel measurements at the current relay positions. Second, we propose a model-free deep Q-learning approach, which does not rely on channel models. For the deep Q-learning approach, we propose two modified Multilayer Perceptron Neural Networks (MLPs) for approximating the value function Q. The first modification applies a Fourier feature mapping of the state before passing it through the MLP. The second modification constitutes a different neural network architecture that uses sinusoids as activations between layers. Both modifications enable the MLP to better learn the high frequency value function and have a profound effect on convergence speed and SINR performance. Finally, we conduct a comparative analysis of all the presented approaches and provide insights on advantages and drawbacks.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Exponential Mixture Density Based Approximation to Posterior Cramér-Rao
           Lower Bound for Distributed Target Tracking

    • Free pre-print version: Loading...

      Authors: Ye Yuan;Wei Yi;Pramod K. Varshney;
      Pages: 862 - 877
      Abstract: The posterior Cramr-Rao lower bound (PCRLB) and a number of its extensions including the unconditional PCRLB (U-PCRLB) and the conditional PCRLB (C-PCRLB) have been widely studied in multi-sensor target tracking (MSTT). Previous MSTT works assume that the measurements are conditionally independent, which is often not the case in practice. When the correlations of the measurements are unknown, the standard Bayes update and PCRLB computations cannot be performed. Inspired by geometric average (GA) fusion that implements data fusion with unknown data correlations by employing exponential mixture density (EMD) to compute the global posterior, EMD-based approximations to U-PCRLB and C-PCRLB are derived in this paper for two classic distributed fusion architectures, namely the hierarchical and consensus architectures. The PCRLB can be decomposed into two parts, one coming from the prior information and the other from the information contained in the data. The data information part of PCRLB is approximated via EMD-based posterior, leading to the approximation of the PCRLB. We present a sequential Monte Carlo solution to recursively compute the proposed approximation to the PCRLB for nonlinear non-Gaussian estimation problems. Numerical simulations are provided to show that the proposed approximation to the bound on the estimation mean square error (MSE) is tighter compared to the existing bounds based on likelihood fusion obtained under the measurement independence assumption.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • High-Throughput Adaptive List Decoding Architecture for Polar Codes on GPU

    • Free pre-print version: Loading...

      Authors: Zhanxian Liu;Rongke Liu;Haijun Zhang;
      Pages: 878 - 889
      Abstract: Polar codes have been adopted in the 5th generation communication standard (5G). Successive-cancellation list (SCL) decoding, a promising solution to decode polar codes, provides good tradeoff between error-correction performance and implementation complexity. To meet high flexibility and scalability requirements of Cloud or Open random access networks (RANs) for the 5G or future communication standards, this paper presents software list decoding architectures on graphics processing units (GPUs) and considers special nodes to reduce the decoding complexity. In order to improve the throughput and latency performance, a GPU-based adaptive mapping strategy taking advantage of the GPU architecture is proposed. Without considering the data transfer procedure between host and device, the proposed adaptive list decoder on NVIDIA RTX3090 for the code (1024, 512) with list sizes $L=8$ and $L=32$ can achieve above 30 Gbps coded throughput at the frame error rates of $10^{-6}$ and $10^{-7}$, respectively. Compared to the state-of-the-art software works, the proposed decoder achieves about $times 1.78$ to $times 9.07$ throughput speedups.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • An Enhanced Lattice Algorithm for Range Estimation Using Noisy Measurement
           With Phase Ambiguity

    • Free pre-print version: Loading...

      Authors: Wenchao Li;Xuezhi Wang;Bill Moran;
      Pages: 890 - 902
      Abstract: The problem of range estimation based on noisy measurements with phase ambiguity can be solved using signals across multiple frequencies by existing algorithms based on either the Chinese Remainder Theorem or lattice theory. The performances of these algorithms are constrained by the trade-off between SNR of measurements and required estimation accuracy. In this paper, we firstly propose an algorithm to find a set of wavelengths satisfying the conditions to apply the closed-form lattice algorithm from a given interval. Then we propose an enhanced lattice algorithm for range estimation based on existing lattice approaches. In the conventional lattice algorithm, the selection of an integer vector by the estimator often fails to be the ground truth because of noise. As a result, the true value can be a neighbouring lattice point of the estimated point where neighbours are defined in terms of a distance depending on the noise characteristics. In this paper, all neighbouring lattice points of the estimated point obtained by a conventional lattice algorithm are regarded as candidates for the new estimate. Then an efficient estimator is presented to choose one of those candidates to be the new estimate. The performance of the proposed algorithm, i.e. the successful probability of reconstruction, is derived mathematically. Additionally, a computation-reduced algorithm is presented to reduce the overhead of computation. The calculated probability and simulation results demonstrate the efficiency of the proposed algorithm.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Adaptive Fourier Decomposition for Multi-Channel Signal Analysis

    • Free pre-print version: Loading...

      Authors: Ze Wang;Chi Man Wong;Agostinho Rosa;Tao Qian;Feng Wan;
      Pages: 903 - 918
      Abstract: Evolved from the conventional Fourier decomposition based on a pre-defined basis, Adaptive Fourier decomposition (AFD) uses adaptive basis to achieve the fast energy convergence. This paper extends the AFD to the multi-channel case, which finds common adaptive basis across all channels. The proposed multi-channel AFD (MAFD) scheme includes the multi-channel core AFD for general signals and the multi-channel unwinding AFD for specific signals that have common inner functions. Owing to the merits of the original AFD, the MAFD can provide sparse joint time-frequency distribution by computing the transient time frequency distribution (TTFD) across channels. Simulations on synthetic and real-world signals demonstrate that the proposed scheme can find and apply the common adaptive basis with desired properties maintained by the AFD, showing high potentials in real-world applications.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Robust Spectral Analysis of Multi-Channel Sinusoidal Signals in Impulsive
           Noise Environments

    • Free pre-print version: Loading...

      Authors: Zhenhua Zhou;Lei Huang;Mads Græsbøll Christensen;Shengli Zhang;
      Pages: 919 - 935
      Abstract: Robust spectral analysis of the sinusoidal signals corrupted by impulsive noise poses a big challenge in the signal processing community. In this paper, we address the issue of robust spectral analysis for multi-channel sinusoidal signals, including order detection and parameter estimation. The successive robust low-rank decomposition is firstly designed to extract the common signal subspace from the multi-channel data matrix. Subsequently, the number of sinusoidal poles is determined with a model order selection criterion, based on the so-obtained subspace. With the signal order information, the sinusoidal parameters and outliers are jointly estimated according to the maximum a posteriori criterion. To find a robust initial guess of the sinusoidal parameters, an estimator based on robust weighted linear prediction is developed. Additionally, the performance analysis is provided, which includes computational complexity, convergence verification of the sinusoidal parameter estimation, and asymptotic consistency of the signal order detection. Simulation results demonstrate the advantages of the proposed robust spectral analysis framework compared to state-of-the-art schemes.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Kernel Regression Over Graphs Using Random Fourier Features

    • Free pre-print version: Loading...

      Authors: Vitor Rosa Meireles Elias;Vinay Chakravarthi Gogineni;Wallace A. Martins;Stefan Werner;
      Pages: 936 - 949
      Abstract: This paper proposes efficient batch-based and online strategies for kernel regression over graphs (KRG). The proposed algorithms do not require the input signal to be a graph signal, whereas the target signal is defined over the graph. We first use random Fourier features (RFF) to tackle the complexity issues associated with kernel methods employed in the conventional KRG. For batch-based approaches, we also propose an implementation that reduces complexity by avoiding the inversion of large matrices. Then, we derive two distinct online strategies using RFF, namely, the mini-batch gradient KRG (MGKRG) and the recursive least squares KRG (RLSKRG). The stochastic-gradient KRG (SGKRG) is introduced as a particular case of the MGKRG. The MGKRG and the SGKRG are low-complexity algorithms that employ stochastic gradient approximations in the regression-parameter update. The RLSKRG is a recursive implementation of the RFF-based batch KRG. A detailed stability analysis is provided for the proposed online algorithms, including convergence conditions in both mean and mean-squared senses. A discussion on complexity is also provided. Numerical simulations include a synthesized-data experiment and real-data experiments on temperature prediction, brain activity estimation, and image reconstruction. Results show that the RFF-based batch implementation offers competitive performance with a reduced computational burden when compared to the conventional KRG. The MGKRG offers a convenient trade-off between performance and complexity by varying the number of mini-batch samples. The RLSKRG has a faster convergence than the MGKRG and matches the performance of the batch implementation.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Finite-Time Error Bounds of Biased Stochastic Approximation With
           Application to TD-Learning

    • Free pre-print version: Loading...

      Authors: Gang Wang;
      Pages: 950 - 962
      Abstract: Motivated by the recent success of reinforcement learning algorithms, this paper studies a class of biased stochastic approximation (SA) procedures under a mild “ergodicity-like” assumption on the random noise sequence. Building on a multistep Lyapunov function that looks ahead to several future updates to accommodate the stochastic perturbations (thus gaining control over the bias), we prove a general result on the convergence of the SA iterates, and use it to derive non-asymptotic bounds on the mean-square error in the case of constant stepsizes. This novel viewpoint renders finite-time analysis of biased SA algorithms under a family of stochastic perturbations possible. For direct comparison with prior work, we demonstrate these bounds by applying them to TD-learning with linear function approximation, under the Markov chain observation model. The resultant finite-time error bound for TD-learning is the first of its kind, in the sense that it holds i) for the unmodified versions (i.e., without any modification to the updates) using even nonlinear approximators; as well as for Markov chains ii) under sublinear mixing conditions and iii) starting from any initial distribution, at least one of which has to be violated for existing results to be applicable.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Dual Optimization for Kolmogorov Model Learning Using Enhanced Gradient
           Descent

    • Free pre-print version: Loading...

      Authors: Qiyou Duan;Hadi Ghauch;Taejoon Kim;
      Pages: 963 - 977
      Abstract: Data representation techniques have made a substantial contribution to advancing data processing and machine learning (ML). Improving predictive power was the focus of previous representation techniques, which unfortunately perform rather poorly on the interpretability in terms of extracting underlying insights of the data. Recently, the Kolmogorov model (KM) was studied, which is an interpretable and predictable representation approach to learning the underlying probabilistic structure of a set of random variables. The existing KM learning algorithms using semi-definite relaxation with randomization (SDRwR) or discrete monotonic optimization (DMO) have, however, limited utility to big data applications because they do not scale well computationally.In this paper, we propose a computationally scalable KM learning algorithm, based on the regularized dual optimization combined with enhanced gradient descent (GD) method. To make our method more scalable to large-dimensional problems, we propose two acceleration schemes, namely, the eigenvalue decomposition (EVD) elimination strategy and an approximate EVD algorithm. Furthermore, a thresholding technique by exploiting the error bound analysis and leveraging the normalized Minkowski $ell _1$-norm, is provided for the selection of the number of iterations of the approximate EVD algorithm. When applied to big data applications, it is demonstrated that the proposed method can achieve compatible training/prediction performance with significantly reduced computational complexity; roughly two orders of magnitude improvement in terms of the time overhead, compared to the existing KM learning algorithms. Furthermore, it is shown that the accuracy of logical relation mining for interpretability by using the proposed KM learning algorithm exceeds 80%.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Adaptive Radar Detection in Gaussian Interference Using Clutter-Free
           Training Data

    • Free pre-print version: Loading...

      Authors: Yao Rong;Augusto Aubry;Antonio De Maio;Mengjiao Tang;
      Pages: 978 - 993
      Abstract: This paper addresses adaptive detection of range spread targets in the presence of thermal noise, jammer, and clutter. After motivating the study, a set of clutter-free training (CFT) data is considered to assist radar detection in absence of conventional secondary data sharing the same spectral properties as the interference of the cells under test. To this end, a maximum likelihood (ML) estimate of the unknown parameters is derived under the alternative hypothesis by leveraging the primary data and the CFT data simultaneously. Subsequently, the ML estimate is used to design decision rules based on generalized likelihood ratio, complex parameter Wald, and complex parameter Gradient test criteria. Furthermore, conditions guaranteeing the constant false alarm rate (CFAR) property of the proposed detectors are discussed. At the analysis stage, numerical examples are presented to evaluate the effectiveness of the proposed detectors in comparison with other detection schemes available in the literature.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • An Outlier-Robust Kalman Filter With Adaptive Selection of Elliptically
           Contoured Distributions

    • Free pre-print version: Loading...

      Authors: Chao Xue;Yulong Huang;Fengchi Zhu;Yonggang Zhang;Jonathon A. Chambers;
      Pages: 994 - 1009
      Abstract: In this paper, elliptically contoured (EC) distributions are used to model outlier-contaminated measurement noises. Exploiting a heuristic approach to introduce an unknown parameter, we present an analytical update form of the joint posterior probability density function of the state vector and auxiliary random variable, from which a novel robust EC distributions-based Kalman filtering framework is first derived. To illustrate the effectiveness of the proposed framework, the convergence, robustness, optimality and computational complexity analyses of the proposed method are then given. In addition, to cope with complex noise environments, the interaction multiple model is employed to achieve the adaptive selection of EC distributions such that well-behaved estimation performance can be obtained for different noise cases. Simulation results demonstrate the validity and superiority of the proposed algorithm.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Multi-Sensor Joint Adaptive Birth Sampler for Labeled Random Finite Set
           Tracking

    • Free pre-print version: Loading...

      Authors: Anthony Trezza;Donald J. Bucci;Pramod K. Varshney;
      Pages: 1010 - 1025
      Abstract: This paper provides a scalable, multi-sensor measurement adaptive track initiation technique for labeled random finite set filters. A naive construction of the multi-sensor measurement adaptive birth set distribution leads to an exponential number of newborn components in the number of sensors. A truncation criterion is established for a labeled multi-Bernoulli random finite set birth density. The proposed truncation criterion is shown to have a bounded L1 error in the generalized labeled multi-Bernoulli posterior density. This criterion is used to construct a Gibbs sampler that produces a truncated measurement-generated labeled multi-Bernoulli birth distribution with quadratic complexity in the number of sensors. A closed-form solution of the conditional sampling distribution assuming linear Gaussian likelihoods is provided, alongside an approximate solution using Monte Carlo importance sampling. Multiple simulation results are provided to verify the efficacy of the truncation criterion, as well as the reduction in complexity.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Phase Calibration for Intelligent Reflecting Surfaces Assisted Millimeter
           Wave Communications

    • Free pre-print version: Loading...

      Authors: Jiezhi Zhang;Xiaoling Hu;Caijun Zhong;
      Pages: 1026 - 1040
      Abstract: In this paper, wepropose a novel two-stage transmission framework for an intelligent reflecting surface (IRS) assisted millimeter wave (mmWave) system in the presence of phase error caused by hardware impairments. Specifically, in Stage I, we introduce a pilot-based phase calibration task and reformulate it as an alternating optimization program. Building on this formulation, an efficient iterative algorithm is developed to jointly estimate the phase error, which needs to be calibrated, and the channels corresponding to the first user. Stage II consists of two blocks, channel estimation and data transmission. During the channel estimation block, by leveraging on the sparsity of mmWave channels, we propose a fast Fourier transform based scheme to estimate the IRS-BS channel and user-IRS channels. During the data transmission block, based on the estimated channel state information, base station precoders and IRS phase shifts are jointly optimized to maximize the sum signal-to-leakage-plus-noise ratio of all users. To handle this non-convex problem, we further develop a low-complexity joint beamforming algorithm by exploiting fractional programming techniques. Moreover, to examine the performance of the proposed phase calibration scheme, we derive the Cramer-Rao lower bound for the intended phase error estimation. Simulation results validate the effectiveness of our proposed transmission framework and the necessity of IRS phase calibration.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Quickest Change Detection in Anonymous Heterogeneous Sensor Networks

    • Free pre-print version: Loading...

      Authors: Zhongchang Sun;Shaofeng Zou;Ruizhi Zhang;Qunwei Li;
      Pages: 1041 - 1055
      Abstract: The problem of quickest change detection (QCD) in anonymous heterogeneous sensor networks is studied. There are $n$ heterogeneous sensors and a fusion center. The sensors are clustered into $K$ groups, and different groups follow different data-generating distributions. At some unknown time, an event occurs in the network and changes the data-generating distribution of the sensors. The goal is to detect the change as quickly as possible, subject to false alarm constraints. The anonymous setting is studied, where at each time step, the fusion center receives $n$ unordered samples, and the fusion center does not know which sensor each sample comes from, and thus does not know its exact distribution. A simple optimality proof is first derived for the mixture likelihood ratio test, which was constructed and proved to be optimal for the non-sequential anonymous setting in (Chen et al., 2019). For the QCD problem, a mixture CuSum algorithm is further constructed, and is further shown to be optimal under Lorden’s criterion. For large networks, a computationally efficient test is proposed and a novel theoretical characterization of its false alarm rate is developed. Numerical results are provided to validate the theoretical results.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Block-Sparse Signal Recovery via General Total Variation Regularized
           Sparse Bayesian Learning

    • Free pre-print version: Loading...

      Authors: Aditya Sant;Markus Leinonen;Bhaskar D. Rao;
      Pages: 1056 - 1071
      Abstract: One of the main challenges in block-sparse signal recovery, as encountered in, e.g., multi-antenna mmWave channel models, is block-patterned estimation without knowledge of block sizes and boundaries. We propose a novel Sparse Bayesian Learning (SBL) method for block-sparse signal recovery under unknown block patterns. Contrary to conventional approaches that impose block-promoting regularization on the signal components, we apply two classes of hyperparameter regularizers for the SBL cost function, inspired by total variation (TV) denoising. The first class relies on a conventional TV difference unit and allows performing the SBL inference iteratively through a set of convex optimization problems, enabling a flexible choice of numerical solvers. The second class incorporates a region-aware TV penalty to penalize the signal and zero blocks in a dissimilar manner, enhancing the performance. We derive an alternating optimization algorithm based on expectation-maximization to perform the SBL inference through computationally efficient parallel updates for both the regularizer classes. The numerical results show that the proposed TV-regularized SBL algorithm is robust to the nature of the block structure and is capable of recovering signals with both block-patterned and isolated components, proving effective for various signal recovery systems.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Tight Regret Bounds for Noisy Optimization of a Brownian Motion

    • Free pre-print version: Loading...

      Authors: Zexin Wang;Vincent Y. F. Tan;Jonathan Scarlett;
      Pages: 1072 - 1087
      Abstract: We consider the problem of Bayesian optimization of a one-dimensional Brownian motion in which the $T$ adaptively chosen observations are corrupted by Gaussian noise. We show that the smallest possible expected cumulative regret and the smallest possible expected simple regret scale as $Omega (sigma sqrt {T / log (T)}) cap mathcal {O}(sigma sqrt {T} cdot log T)$ and $Omega (sigma / sqrt {T log (T)}) cap mathcal {O}(sigma log T / sqrt {T})$ respectively, where $sigma ^2$ is the noise variance. Thus, our upper and lower bounds are tight up to a factor of $mathcal {O} ((log T)^{1.5})$. The upper bound uses an algorithm based on confidence bounds and the Markov property of Brownian motion (among other useful properties), and the lower bound is based on a reduction to binary hypothesis testing.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Total Secrecy From Anti-Eavesdropping Channel Estimation

    • Free pre-print version: Loading...

      Authors: Shuo Wu;Yingbo Hua;
      Pages: 1088 - 1103
      Abstract: Anti-eavesdropping channel estimation (ANECE) is useful for a network of cooperative full-duplex radio devices/users. Using ANECE, a secret key can be generated by each pair of users, and additional secret information can be transmitted between a pair of users. This paper analyzes the capacity of the secret key based on ANECE, and compares it with the conventional method for channel training. The paper also analyzes the secrecy capacity of information transmission using an one-way scheme, and compares it with a two-way scheme. It is shown that the total amount of secrecy generated from ANECE can be substantially larger than that based on the conventional method especially when an eavesdropper may have an unlimited number of antennas. The paper also formulates a total secure degree of freedom (TSDoF) of the ANECE based scheme, and compares it with a prior scheme of secret information transmission from a multi-antenna node to another against a multi-antenna eavesdropper where channel state information is unknown everywhere initially. The comparison shows that there is a substantial gain of TSDoF by exploiting full-duplex radios and reciprocal channels via ANECE. Most of the key insights are highlighted in twelve proven properties.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Signal Analysis via the Stochastic Geometry of Spectrogram Level Sets

    • Free pre-print version: Loading...

      Authors: Subhroshekhar Ghosh;Meixia Lin;Dongfang Sun;
      Pages: 1104 - 1117
      Abstract: Spectrograms are fundamental tools in time-frequency analysis, being the squared magnitude of the so-called short time Fourier transform (STFT). Signal analysis via spectrograms has traditionally explored their peaks, i.e. their maxima. This is complemented by a recent interest in their zeros or minima, following seminal work by Flandrin and others, which exploits connections with Gaussian analytic functions (GAFs). However, the zero sets (or extrema) of GAFs have a complicated stochastic structure, complicating any direct theoretical analysis. Standard techniques largely rely on statistical observables from the analysis of spatial data, whose distributional properties for spectrograms are mostly understood only at an empirical level. In this work, we investigate spectrogram analysis via an examination of the stochastic geometric properties of their level sets. We obtain rigorous theorems demonstrating the efficacy of a spectrogram level sets based approach to the detection and estimation of signals, framed in a concrete inferential set-up. Exploiting these ideas as theoretical underpinnings, we propose a level sets based algorithm for signal analysis that is intrinsic to given spectrogram data, and substantiate its effectiveness via extensive empirical studies. Our results also have theoretical implications for spectrogram zero based approaches to signal analysis. To our knowledge, these results are arguably among the first to provide a rigorous statistical understanding of signal detection and reconstruction in this set up, complemented with provable guarantees on detection thresholds and rates of convergence.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Deep Learning-Aided Coherent Direction-of-Arrival Estimation With the FTMR
           Algorithm

    • Free pre-print version: Loading...

      Authors: Dai Trong Hoang;Kyungchun Lee;
      Pages: 1118 - 1130
      Abstract: In this work, we apply deep learning to estimate the direction-of-arrival (DoA) of multiple narrowband signals with a uniform linear array in a coherent environment. First, the logarithmic eigenvalue-based classification network (LogECNet) is introduced to enhance signal number detection accuracy in challenging scenarios, such as the low signal-to-noise (SNR) regime and limited snapshots. Next, a multi-label classification model called the root-spectrum network (RSNet) is devised to estimate the DoAs using the signal number inferred by LogECNet. In the proposed architecture, the full-row Toeplitz matrices reconstruction (FTMR), which exploits all rows of the signal covariance matrix (SCM), is combined with LogECNet and RSNet to inversely map the SCM to the numerical DoAs in the coherent scenario. It is shown that the eigenvalues factorized from the FTMR output matrix become more robust sources for signal enumeration than those of the forward/backward spatial smoothing (FBSS) algorithm. Furthermore, the logarithmic scaling of the eigenvalues of the FTMR results in LogECNet outperforming other detectors. The simulation results show our proposed method not only improves the signal number detection and angular estimation performance, but also achieves the complexity reduction with respect to the prior schemes.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Unlimited Sampling From Theory to Practice: Fourier-Prony Recovery and
           Prototype ADC

    • Free pre-print version: Loading...

      Authors: Ayush Bhandari;Felix Krahmer;Thomas Poskitt;
      Pages: 1131 - 1141
      Abstract: Following the Unlimited Sampling strategy to alleviate the omnipresent dynamic range barrier, we study the problem of recovering a bandlimited signal from point-wise modulo samples, aiming to connect theoretical guarantees with hardware implementation considerations. Our starting point is a class of non-idealities that we observe in prototyping an unlimited sampling based analog-to-digital converter. To address these non-idealities, we provide a new Fourier domain recovery algorithm. Our approach is validated both in theory and via extensive experiments on our prototype analog-to-digital converter, providing the first demonstration of unlimited sampling for data arising from real hardware, both for the current and previous approaches. Advantages of our algorithm include that it is agnostic to the modulo threshold and it can handle arbitrary folding times. We expect that the end-to-end realization studied in this paper will pave the path for exploring the unlimited sampling methodology in a number of real world applications.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Robust Aggregation for Federated Learning

    • Free pre-print version: Loading...

      Authors: Krishna Pillutla;Sham M. Kakade;Zaid Harchaoui;
      Pages: 1142 - 1154
      Abstract: We present a novel approach to federated learning that endows its aggregation process with greater robustness to potential poisoning of local data or model parameters of participating devices. The proposed approach, Robust Federated Aggregation (RFA), relies on the aggregation of updates using the geometric median, which can be computed efficiently using a Weiszfeld-type algorithm. RFA is agnostic to the level of corruption and aggregates model updates without revealing each device’s individual contribution. We establish the convergence of the robust federated learning algorithm for the stochastic learning of additive models with least squares. We also offer two variants of RFA: a faster one with one-step robust aggregation, and another one with on-device personalization. We present experimental results with additive models and deep networks for three tasks in computer vision and natural language processing. The experiments show that RFA is competitive with the classical aggregation when the level of corruption is low, while demonstrating greater robustness under high corruption.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Efficient Caching by Linear Compression for Parameter Estimation in
           Wireless Sensor Networks

    • Free pre-print version: Loading...

      Authors: Pradeep Chennakesavula;Y.-W. Peter Hong;Anna Scaglione;
      Pages: 1155 - 1169
      Abstract: This work proposes a cross-layered caching strategy for parameter estimation in wireless sensor networks (WSNs). Here, sensors first gather information about common parameters of interest and then forward the information to an edge server for final inference. The collaborative nature of this application enables the caching of linearly compressed information across sensors rather than individual observations. By assuming that the parameters are correlated over time, the estimation quality at the edge server can be improved by combining both present and past information, where the latter can be obtained from cached data. The data caching and accessing strategies are jointly designed to minimize the expected mean-squared-error (MSE) of the requested parameter estimates. We first consider a single-cache single-server scenario under ideal accessing assumptions and propose a greedy one-step-ahead (OSA) caching strategy that determines the optimal linear combination of observations to cache by minimizing the expected MSE of the requested parameter estimate in the next time slot. We adopt an alternating optimization approach where the combining coefficients at the cache and the linear estimator at the server are optimized in turn until convergence. Then, the proposed OSA caching strategy is extended to the multi-cache multi-server scenario with constraints on the accessing costs at both the caches and the edge servers. The alternating optimization subproblems in this case are non-convex due to the additional access constraints and, thus, are solved by adopting a successive convex approximation (SCA) procedure. Numerical simulations are provided to demonstrate the effectiveness of the proposed caching strategies.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Deep Spectrum Cartography: Completing Radio Map Tensors Using Learned
           Neural Models

    • Free pre-print version: Loading...

      Authors: Sagar Shrestha;Xiao Fu;Mingyi Hong;
      Pages: 1170 - 1184
      Abstract: The spectrum cartography (SC) technique constructs multi-domain (e.g., frequency, space, and time) radio frequency (RF) maps from limited measurements, which can be viewed as an ill-posed tensor completion problem. Model-based cartography techniques often rely on handcrafted priors (e.g., sparsity, smoothness and low-rank structures) for the completion task. Such priors may be inadequate to capture the essence of complex wireless environments—especially when severe shadowing happens. To circumvent such challenges, offline-trained deep neural models of radio maps were considered for SC, as deep neural networks (DNNs) are able to “learn” intricate underlying structures from data. However, such deep learning (DL)-based SC approaches encounter serious challenges in both off-line model learning (training) and completion (generalization), possibly because the latent state space for generating the radio maps is prohibitively large. In this work, an emitter radio map disaggregation-based approach is proposed, under which only individual emitters’ radio maps are modeled by DNNs. This way, the learning and generalization challenges can both be substantially alleviated. Using the learned DNNs, a fast nonnegative matrix factorization-based two-stage SC method and a performance-enhanced iterative optimization algorithm are proposed. Theoretical aspects—such as recoverability of the radio tensor, sample complexity, and noise robustness—under the proposed framework are characterized, and such theoretical properties have been elusive in the context of DL-based radio tensor completion. Experiments using synthetic and real-data from indoor and heavily shadowed environments are employed to showcase the effectiveness of the proposed methods.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Consensus-Based Labeled Multi-Bernoulli Filter With Event-Triggered
           Communication

    • Free pre-print version: Loading...

      Authors: Kai Shen;Chengxi Zhang;Peng Dong;Zhongliang Jing;Henry Leung;
      Pages: 1185 - 1196
      Abstract: This paper introduces a novel consensus-based labeled multi-Bernoulli (LMB) filter to tackle multi-target tracking (MTT) in a communication resource-sensitive distributed sensor network (DSN). Although consensus-based approaches provide effective tools for distributed fusion and MTT, the requirement of iterative communication makes it impractical in resource limited situations. To deal with this issue, two event-triggered strategies are proposed and incorporated into the consensus-based LMB. Focusing on the information discrepancy between the local multi-target probability density function (PDF) and the time prediction of the latest broadcast one, the integral-triggering strategy (ITS) is introduced. Furthermore, by proving that the information discrepancy (Kullback-Leibler divergence) between two LMB densities with the same label space can be decomposed into the sum of the information discrepancy of each LMB component pair (LMB components with the same label), the separated-triggering strategy (STS) is proposed. The performance of the proposed algorithms is demonstrated in a distributed multi-target tracking scenario via numerical simulations.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • A Hybrid Approach to Optimal TOA-Sensor Placement With Fixed Shared
           Sensors for Simultaneous Multi-Target Localization

    • Free pre-print version: Loading...

      Authors: Sheng Xu;Linlong Wu;Kutluyıl Doğançay;Mohammad Alaee-Kerahroodi;
      Pages: 1197 - 1212
      Abstract: This paper focuses on optimal time-of-arrival (TOA) sensor placement for multiple target localization simultaneously. In previous work, different solutions only using non-shared sensors to localize multiple targets have been developed. Those methods localize different targets one-by-one or use a large number of mobile sensors with many limitations, such as low effectiveness and high network complexity. In this paper, firstly, a novel optimization model for multi-target localization incorporating shared sensors is formulated. Secondly, the systematic theoretical results of the optimal sensor placement are derived and concluded using the A-optimality criterion, i.e., minimizing the trace of the inverse Fisher information matrix (FIM), based on rigorous geometrical derivations. The reachable optimal trace of Cramér-Rao lower bound (CRLB) is also derived. It can provide optimal conditions for many cases and even closed form solutions for some special cases. Thirdly, a novel numerical optimization algorithm to quickly find and calculate the (sub-)optimal placement and achievable lower bound is explored, when the model becomes complicated with more practical constraints. Then, a hybrid method for solving the most general situation, integrating both the analytical and numerical solutions, is proposed. Finally, the correctness and effectiveness of the proposed theoretical and mathematical methods are demonstrated by several simulation examples.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Non-Smooth Regularization: Improvement to Learning Framework Through
           Extrapolation

    • Free pre-print version: Loading...

      Authors: Sajjad Amini;Mohammad Soltanian;Mostafa Sadeghi;Shahrokh Ghaemmaghami;
      Pages: 1213 - 1223
      Abstract: Deep learning architectures employ various regularization terms to handle different types of priors. Non-smooth regularization terms have shown promising performance in the deep learning architectures and a learning framework has recently been proposed to train autoencoders with such regularization terms. While this framework efficiently manages the non-smooth term during training through proximal operators, it is limited to autoencoders and suffers from low convergence speed due to several optimization sub-problems that must be solved in a row. In this paper, we address these issues by extending the framework to general feed-forward neural networks and introducing variable extrapolation which can dramatically increase the convergence speed in each sub-problem. We show that the proposed update rules converge to a critical point of the objective function under mild conditions. To compare the resulting framework with the previously proposed one, we consider the problem of training sparse autoencoders and robustifying deep neural architectures against both targeted and untargeted attacks. Simulations show superior performance in both convergence speed and final objective function value.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Efficient Super-Resolution Two-Dimensional Harmonic Retrieval With
           Multiple Measurement Vectors

    • Free pre-print version: Loading...

      Authors: Yu Zhang;Yue Wang;Zhi Tian;Geert Leus;Gong Zhang;
      Pages: 1224 - 1240
      Abstract: This paper develops an efficient solution for super-resolution two-dimensional (2D) harmonic retrieval from multiple measurement vectors (MMV). Given the sample covariance matrix constructed from the MMV, a gridless compressed sensing approach is proposed based on the atomic norm minimization (ANM). In the approach, our key step is to perform a redundancy reduction (RR) transformation that effectively reduces the large problem size at hand, without loss of useful frequency information. For uncorrelated sources, the transformed 2D covariance matrices in the RR domain retain a salient structure, which permits a sparse representation over a matrix-form atom set with decoupled 1D frequency components. Accordingly, the decoupled ANM (D-ANM) framework can be applied for super-resolution 2D frequency estimation. Moreover, the resulting RR-enabled D-ANM technique, termed RR-D-ANM, further allows an efficient relaxation under certain conditions, which leads to low computational complexity of the same order as the 1D case. Simulation results verify the advantages of our solutions over benchmark methods, in terms of higher computational efficiency and detectability for 2D harmonic retrieval.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • PDMM: A Novel Primal-Dual Majorization-Minimization Algorithm for Poisson
           Phase-Retrieval Problem

    • Free pre-print version: Loading...

      Authors: Ghania Fatima;Zongyu Li;Aakash Arora;Prabhu Babu;
      Pages: 1241 - 1255
      Abstract: In this paper, we introduce a novel iterative algorithm for the problem of phase-retrieval where the measurements consist of only the magnitude of linear function of the unknown signal, and the noise in the measurements follow Poisson distribution. The proposed algorithm is based on the principle of majorization-minimization (MM); however, the application of MM here is very novel and distinct from the way MM has been usually used to solve optimization problems in the literature. More precisely, we reformulate the original minimization problem into a saddle point problem by invoking Fenchel dual representation of the $log (cdot)$ term in the Poisson likelihood function. We then propose tighter surrogate functions over both primal and dual variables resulting in a double-loop MM algorithm, which we have named as Primal-Dual Majorization-Minimization (PDMM) algorithm. The iterative steps of the resulting algorithm are simple to implement and involve only computing matrix vector products. We also extend our algorithm to handle various $ell _{1}$ regularized Poisson phase-retrieval problems (which exploit sparsity). The proposed algorithm is compared with previously proposed algorithms such as wirtinger flow (WF), MM (conventional), and alternating direction methods of multipliers (ADMM) for the Poisson data model. The simulation results under different experimental settings show that PDMM is faster than the competing methods, and its performance in recovering the original signal is at par with the state-of-the-art algorithms.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Bayesian Sparse Blind Deconvolution Using MCMC Methods Based on
           Normal-Inverse-Gamma Prior

    • Free pre-print version: Loading...

      Authors: Burak C. Civek;Emre Ertin;
      Pages: 1256 - 1269
      Abstract: Bayesian estimation methods for sparse blind deconvolution problems conventionally employ Bernoulli-Gaussian (BG) prior for modeling sparse sequences and utilize Markov Chain Monte Carlo (MCMC) methods for the estimation of unknowns. However, the discrete nature of the BG model creates computational bottlenecks, preventing efficient exploration of the probability space even with the recently proposed enhanced sampler schemes. To address this issue, we propose an alternative MCMC method by modeling the sparse sequences using the Normal-Inverse-Gamma (NIG) prior. We derive effective Gibbs samplers for this prior and illustrate that the computational burden associated with the BG model can be eliminated by transferring the problem into a completely continuous-valued framework. In addition to sparsity, we also incorporate time and frequency domain constraints on the convolving sequences. We demonstrate the effectiveness of the proposed methods via extensive simulations and characterize computational gains relative to the existing methods that utilize BG modeling.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Detection of the Number of Signals in Uniform Arrays by
           Invariant-Signal-Subspace Matching

    • Free pre-print version: Loading...

      Authors: Mati Wax;Amir Adler;
      Pages: 1270 - 1281
      Abstract: We present a novel and computationally simple solution to the problem of detecting the number of signals in the case of uniform linear arrays (ULA) and uniform rectangular arrays (URA), which is applicable to white and colored noise, and to a very small number of samples. The solution is based on novel and non-asymptotic goodness-of-fit metric, referred invariant signal subspace matching (ISSM), which is aimed at matching the signal subspaces of two subarrays which are translation invariant. We form a pair of projection matrices on the signal subspaces – one for each subarray – which are parameterized by the number of signals $k$ and constructed from the $k$ leading eigenvectors of the sample-covariance matrices of the subarrays. The value of $k$ which minimizes this metric is selected as the number of signals. We prove the consistency of the ISSM criterion for the high signal-to-noise-ratio (SNR) limit, and also for the large-sample limit, conditioned on the noise being white. The evaluation of the ISSM criterion involves only the computation of eigenvectors of the sample-covariance matrix of the the array. Simulation results, demonstrating the improved performance of the ISSM criterion over existing criteria, especially for colored noise, are included.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Enhanced Target Localization With Deployable Multiplatform Radar Nodes
           Based on Non-Convex Constrained Least Squares Optimization

    • Free pre-print version: Loading...

      Authors: Augusto Aubry;Paolo Braca;Antonio De Maio;Angela Marino;
      Pages: 1282 - 1294
      Abstract: A new algorithm for 3D localization in multiplatform radar networks, comprising one transmitter and multiple receivers, is proposed. To take advantage of the monostatic sensor radiation pattern features, ad-hoc constraints are imposed in the target localization process. Therefore, the localization problem is formulated as a non-convex constrained Least Squares (LS) optimization problem which is globally solved in a quasi-closed-form leveraging Karush-Kuhn-Tucker (KKT) conditions. The performance of the new algorithm is assessed in terms of Root Mean Square Error (RMSE) in comparison with the benchmark Root Cramer Rao Lower Bound (RCRLB) and some competitors from the open literature. The results corroborate the effectiveness of the new strategy which is capable of ensuring a lower RMSE than the counterpart methodologies especially in the low Signal to Noise Ratio (SNR) regime.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • $Z$ +Transforms&rft.title=IEEE+Transactions+on+Signal+Processing&rft.issn=1053-587X&rft.date=2022&rft.volume=70&rft.spage=1295&rft.epage=1309&rft.aulast=Joshi;&rft.aufirst=Pushpendra&rft.au=Pushpendra+Singh;Anubha+Gupta;Shiv+Dutt+Joshi;">General Parameterized Fourier Transform: A Unified Framework for the
           Fourier, Laplace, Mellin and $Z$ Transforms

    • Free pre-print version: Loading...

      Authors: Pushpendra Singh;Anubha Gupta;Shiv Dutt Joshi;
      Pages: 1295 - 1309
      Abstract: This paper introduces the general parameterized Fourier transform (GP-FT) that is an extension of the Fourier transform (FT). This study makes a significant scholarly contribution. Firstly, GP-FT is applicable to a much larger class of signals, some of which cannot be analyzed with FT and Laplace transform (LT). For example, we have shown the applicability of GP-FT on the polynomially decaying functions and super-exponential functions. Interestingly, GP-FT provides a valid representation of signals that do not satisfy Dirichlet conditions such as $tan (t)$ and $cos (1/t)$. Unilateral Laplace transform is the special case of the proposed GP-FT. Secondly, we demonstrate the efficacy of GP-FT in solving the initial value problems (IVPs). Thirdly, the generalization presented for FT is extended for other integral transforms, with examples shown for wavelet transform and cosine transform. Likewise, the general Gamma function is also presented. One interesting application of GP-FT is the computation of general parameterized moments, for the otherwise non-finite moments, of any random variable such as the Cauchy random variable. Fourthly, the exponential isomorphic mapping in GP-FT leads to a general parameterized version of Mellin transform, designated as Fourier scale transform (FST). Lastly, we propose General Parameterized Discrete-Time Fourier transform (GP-DTFT). DTFT and unilateral $z$-transform are shown to be the special cases of the proposed GP-DTFT. We have also discussed the properties of GP-FT and GP-DTFT.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Self-Regularity of Non-Negative Output Weights for Overparameterized
           Two-Layer Neural Networks

    • Free pre-print version: Loading...

      Authors: David Gamarnik;Eren C. Kızıldağ;Ilias Zadik;
      Pages: 1310 - 1319
      Abstract: We consider the problem of finding a two-layer neural network with sigmoid, rectified linear unit (ReLU), or binary step activation functions that “fits” a training data set as accurately as possible as quantified by the training error; and study the following question: does a low training error guarantee that the norm of the output layer (outer norm) itself is small' We answer affirmatively this question for the case of non-negative output weights. Using a simple covering number argument, we establish that under quite mild distributional assumptions on the input/label pairs; any such network achieving a small training error on polynomially many data necessarily has a well-controlled outer norm. Notably, our results (a) have a polynomial (in $d$) sample complexity, (b) are independent of the number of hidden units (which can potentially be very high), (c) are oblivious to the training algorithm; and (d) require quite mild assumptions on the data (in particular the input vector $Xin mathbb {R}^{d}$ need not have independent coordinates). We then leverage our bounds to establish generalization guarantees for such networks through fat-shattering dimension, a scale-sensitive measure of the complexity class that the network architectures we investigate belong to. Notably, our generalization bounds also have good sample complexity (polynomials in $d$ with a low degree), and are in fact near-linear for some important cases of interest.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Multi-Spectrally Constrained Transceiver Design Against Signal-Dependent
           Interference

    • Free pre-print version: Loading...

      Authors: Jing Yang;Augusto Aubry;Antonio De Maio;Xianxiang Yu;Guolong Cui;
      Pages: 1320 - 1332
      Abstract: This paper focuses on the joint synthesis of constant envelope transmit signal and receive filter aimed at optimizing radar performance in signal-dependent interference and spectrally contested-congested environments. To ensure the desired Quality of Service (QoS) at each communication system, a precise control of the interference energy injected by the radar in each licensed/shared bandwidth is imposed. Besides, along with an upper bound to the maximum transmitted energy, constant envelope (with either arbitrary or discrete phases) and similarity constraints are forced to ensure compatibility with amplifiers operating in saturation regime and bestow relevant waveform features, respectively. To handle the resulting NP-hard design problems, new iterative procedures (with ensured convergence properties) are devised to account for continuous and discrete phase constraints, capitalizing on the Coordinate Descent (CD) framework. Two heuristic procedures are also proposed to perform valuable initializations. Numerical results are provided to assess the effectiveness of the conceived algorithms in comparison with the existing methods.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Linear Canonical Stockwell Transform: Theory and Applications

    • Free pre-print version: Loading...

      Authors: Deyun Wei;Yijie Zhang;Yuan-Min Li;
      Pages: 1333 - 1347
      Abstract: The Stockwell transform (ST), which is a reversible method of time-frequency spectral representation, is an extension of the ideas of the wavelet transform (WT) and short-time Fourier transform (STFT). And yet, it represents the signal just in the time-frequency plane, which is unfavorable for nonstationary signals. In this paper, a new linear canonical Stockwell transform (LCST) is proposed based on the specific convolution structure in linear canonical transform (LCT) domain, which is a combination of the merits of ST and LCT to address this problem. It not only characterizes the signal in the time-linear canonical frequency plane, but more importantly, inherits the advantages of ST with a clear physical meaning. First, the theories about the continuous LCST are described at length, including its definition, basic properties and the time-LCT domain-frequency analysis. Next, the convolution theorem and cross-correlation theorem constructed in LCST domain are considered. Further, the discretization algorithm of the LCST is explored in order to realize it in the physical system. Finally, based on the proposed LCST, we study and discuss several applications of it, including time-frequency analysis and filtering of chirp signals. The rationality and validity of the work is verified out by simulations.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Asymmetric Compressive Learning Guarantees With Applications to Quantized
           Sketches

    • Free pre-print version: Loading...

      Authors: Vincent Schellekens;Laurent Jacques;
      Pages: 1348 - 1360
      Abstract: The compressive learning framework reduces the computational cost of training on large-scale datasets. In a sketching phase, the data is first compressed to a lightweight sketch vector, obtained by mapping the data samples through a well-chosen feature map, and averaging those contributions. In a learning phase, the desired model parameters are then extracted from this sketch by solving an optimization problem, which also involves a feature map. When the feature map is identical during the sketching and learning phases, formal statistical guarantees (excess risk bounds) have been proven. However, the desirable properties of the feature map are different during sketching and learning (e.g., quantized outputs, and differentiability, respectively). We thus study the relaxation where this map is allowed to be different for each phase. First, we prove that the existing guarantees carry over to this asymmetric scheme, up to a controlled error term, provided some Limited Projected Distortion (LPD) property holds. We then instantiate this framework to the setting of quantized sketches, by proving that the LPD indeed holds for binary sketch contributions. Finally, we further validate the approach with numerical simulations, including a large-scale application in audio event classification.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Fast Iterative Soft-Output List Decoding of Polar Codes

    • Free pre-print version: Loading...

      Authors: Yifei Shen;Wenyue Zhou;Yongming Huang;Zaichen Zhang;Xiaohu You;Chuan Zhang;
      Pages: 1361 - 1376
      Abstract: Iterative detection and decoding (IDD) enjoys a higher capacity than separate detection and decoding (SDD). However, IDD requires both the detector and the decoder to support soft input and soft output. Considering the standard channel codes in 5G communication systems, the preferred decoder for polar codes, the successive cancellation list (SCL) decoder, outputs only hard decisions on the side of codeword. Yet, current soft-output polar decoders, such as belief propagation (BP) and soft cancellation (SCAN), are much inferior to the SCL decoders in terms of error correction performance. To this end, we propose a soft-output list (SOL) decoder in this paper, which considers both hypotheses of 0 and 1 for unreliable bits and keeps the a-priori likelihoods for reliable bits, so that it can provide soft output and satisfactory error-rate performance at the same time. Exploiting the property of special nodes, the resulting FastSOL decoder can directly return soft messages from these nodes, thus speeding up the decoding. The error-rate performance of the FastSOL decoder enhances as the number of iterations increases in the non-IDD setup. The proposed FastSOL decoder can also be applied in the IDD system. Concatenated with a maximum a-posteriori detector in ten IDD loops, our decoder with a list size of eight exhibits over 1 dB gain compared to using the SCAN decoder for polar codes with length 256 and half rate, which also outperforms the state-of-the-art soft list decoder by 0.12 dB in the same settings with a higher computational complexity, but comparable decoding latency.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • The Generalized Method of Moments for Multi-Reference Alignment

    • Free pre-print version: Loading...

      Authors: Asaf Abas;Tamir Bendory;Nir Sharon;
      Pages: 1377 - 1388
      Abstract: This paper studies the application of the generalized method of moments (GMM) to multi-reference alignment (MRA): the problem of estimating a signal from its circularly-translated and noisy copies. We begin by proving that the GMM estimator maintains its asymptotic optimality for statistical models with group symmetry, including MRA. Then, we conduct a comprehensive numerical study and show that the GMM substantially outperforms the classical method of moments, whose application to MRA has been studied thoroughly in the literature. We also formulate the GMM to estimate a three-dimensional molecular structure using cryo-electron microscopy and present numerical results on simulated data.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Signaling Design for MIMO-NOMA With Different Security Requirements

    • Free pre-print version: Loading...

      Authors: Yue Qi;Mojtaba Vaezi;
      Pages: 1389 - 1401
      Abstract: Signaling design for secure transmission in two-user multiple-input multiple-output (MIMO) non-orthogonal multiple access (NOMA) networks with different security requirements is investigated. A base station broadcasts multicast data to all users and unicast data and confidential data targeted to certain users. We categorize the above channel into three communication scenarios depending on the security requirements. The associated problem in each scenario is nonconvex. We propose a unified approach, called the power splitting scheme, for optimizing the rate equations corresponding to each scenario. The proposed method converts the optimization of the secure MIMO-NOMA channel into a set of simpler problems, namely multicast, point-to-point, and wiretap MIMO problems, corresponding to the three basic messages: multicast, private/unicast, and confidential messages. We then leverage existing solutions to design signaling (covariance matrix) for the above problems such that the messages are transmitted with high security and reliability. Numerical results illustrate the efficacy of the proposed covariance matrix (linear precoding and power allocation) design. In the case of no multicast messages, we also reformulate the nonconvex problem into weighted sum rate (WSR) maximization problems by applying the block successive maximization method and generalizing the zero duality gap. The two methods have their advantages and limitations. Power splitting is a general tool that can be applied to the MIMO-NOMA with any combination of the three messages (multicast, private, and confidential) whereas the WSR maximization shows greater potential for secure MIMO-NOMA communication without multicasting. In such cases, the WSR maximization provides a slightly better rate than the power splitting method.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Fairness-Oriented Multiple RIS-Aided mmWave Transmission: Stochastic
           Optimization Methods

    • Free pre-print version: Loading...

      Authors: Gui Zhou;Cunhua Pan;Hong Ren;Kezhi Wang;Marco Di Renzo;
      Pages: 1402 - 1417
      Abstract: In millimeter wave (mmWave) systems, it is challenging to ensure reliable communication links due to the high sensitivity to the presence of blockages. In order to improve the robustness of mmWave systems in the presence of random blockages, we consider the deployment of multiple reconfigurable intelligent surfaces (RISs) to enhance the spatial diversity gain, and the design of robust beamforming schemes based on stochastic optimization methods that minimize the maximum outage probability among multiple users so as to ensure fairness. Under the stochastic optimization framework, we adopt the stochastic majorization–minimization (SMM) method and the stochastic successive convex approximation (SSCA) method to construct deterministic surrogate problems at each iteration, and to obtain closed-form solutions of the precoding matrix at the base station (BS) and the beamforming vectors at the RISs. Both stochastic optimization methods are proved to converge to the set of stationary points of the original stochastic problems. Simulation results show that the proposed robust beamforming for RIS-aided systems can effectively compensate for the performance loss caused by the presence of random blockages, especially when the blockage probability is high.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Two Strategies in Transient Change Detection

    • Free pre-print version: Loading...

      Authors: Daniel Egea-Roca;Blaise Kévin Guépié;José A. López-Salcedo;Gonzalo Seco-Granados;Igor V. Nikiforov;
      Pages: 1418 - 1433
      Abstract: The paper addresses the transient change detection (TCD) problem, assuming that the duration of change is finite. The TCD criterion minimizes the worst-case probability of missed detection among all tests with a prescribed worst-case probability of false alarm. We study the fixed sample size (FSS) test as a solution to the TCD problem. First, the operating characteristics of the FSS test have been established for arbitrary pre- and post-change distributions. Next, a numerical method of the sample (block) size optimization has been considered for three particular log-likelihood ratio distributions, i.e., Gaussian, $chi ^{2}$ and exponential. Moreover, simple asymptotic equations for the optimal operating characteristics and block size have been proposed in the Gaussian case. Numerical results are provided to confirm the theoretical findings for the above-mentioned distributions. The accuracy and sharpness of the asymptotic analytical equation is analyzed in the Gaussian case. Finally, the FSS test is compared to the finite moving average (FMA) test obtained by optimizing the CUSUM-type test with respect to the TCD optimality criterion for the above-mentioned distributions. The application of the FSS and FMA tests to the radio-navigation integrity monitoring is also considered.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Joint Power Allocation for Remote State Estimation With SWIPT

    • Free pre-print version: Loading...

      Authors: Huiwen Yang;Mengyu Huang;Yuzhe Li;Subhrakanti Dey;Ling Shi;
      Pages: 1434 - 1447
      Abstract: In this paper, we consider remote state estimation with simultaneous wireless information and power transfer (SWIPT). A remote estimator receives the state estimate transmitted by a sensor and sends an acknowledgment (ACK) signal to the sensor via a feedback wireless channel. The sensor has no other energy supply except that it can harvest wireless energy from the received ACK signal, which carries information and energy simultaneously. Since the symbol error rate of the state estimate transmitted by the sensor depends on the sensor’s transmission power allocation, there exists a tradeoff between the accuracy of the state estimate received by the remote estimator and the transmission power consumption of the sensor. Moreover, the sensor’s transmission power is restricted by the remaining energy level in its battery, which is decided by the amount of the harvested wireless energy. Therefore, we jointly optimize the transmission power allocation of the remote estimator and the sensor and formulate the optimization problem into an infinite time-horizon average cost Markov decision process (MDP). We first prove the existence of the optimal stationary power allocation policy, and then present the monotonic structures of the optimal policy. Simulation results are provided to verify and illustrate the main results.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • High Resolution MIMO Radar Sensing With Compressive Illuminations

    • Free pre-print version: Loading...

      Authors: Nithin Sugavanam;Siddharth Baskar;Emre Ertin;
      Pages: 1448 - 1463
      Abstract: We present a compressive radar design that combines multitone linear frequency modulated (LFM) waveforms in the transmitter with a classical stretch processor and sub-Nyquist sampling in the receiver. The proposed compressive illumination scheme has fewer random elements resulting in reduced storage and complexity for implementation and calibration than previously proposed compressive radar designs based on stochastic waveforms. We analyze this illumination scheme for the task of a joint range-angle of arrival estimation in the multi-input and multi-output (MIMO) radar system. We present recovery guarantees for the proposed illumination technique. We show that for a sufficiently large number of modulating tones, the system achieves high-resolution in range and successfully recovers the range and angle-of-arrival of targets in a sparse scene. Furthermore, we demonstrate the stability of recovery of targets in range and angle of arrival domain in the continuum. Finally, we present simulation results to illustrate the recovery performance as a function of system parameters.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Radix-Partition-Based Over-the-Air Aggregation and Low-Complexity State
           Estimation for IoT Systems Over Wireless Fading Channels

    • Free pre-print version: Loading...

      Authors: Minjie Tang;Songfu Cai;Vincent K. N. Lau;
      Pages: 1464 - 1477
      Abstract: We consider remote state estimation for an internet-of-things (IoT) system, where a number of distributed IoT sensors monitor a dynamic plant and deliver the state measurements to a remote state estimator over an unreliable wireless network. We propose novel radix-partition-based over-the-air aggregation to coordinate the transmissions of the IoT sensors, which strongly enhances the spectral efficiency of radio resources and enables a smaller state estimation mean square error (MSE) at the remote state estimator, taking into consideration the quantization effect and radio resource allocation for the IoT sensors. We consider a fixed-filtering design at the remote state estimator, which significantly reduces the signal processing overhead at the remote state estimator compared to using the conventional Kalman-filtering-based state estimation approach. We show that the proposed low-complexity state estimation scheme enables state estimation stability via the linear matrix inequality (LMI) technique for on-off fading channels and via Lyapunov stability analysis for random fading channels. Based on this, we further propose efficient algorithms for the offline design of the filtering gain, connection topology and radix representation for IoT systems. Numerical results show that the proposed scheme has superior scalability performance and can achieve a smaller state estimation MSE compared to various state-of-the-art baselines.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Channel Estimation for RIS-Aided Multiuser Millimeter-Wave Systems

    • Free pre-print version: Loading...

      Authors: Gui Zhou;Cunhua Pan;Hong Ren;Petar Popovski;A. Lee Swindlehurst;
      Pages: 1478 - 1492
      Abstract: Reconfigurable intelligent surface (RIS) is a promising device that can reconfigure the electromagnetic propagation environment through adjustment of the phase shifts of its reflecting elements. However, channel estimation in RIS-aided multiuser multiple-input single-output (MU-MISO) wireless communication systems is challenging due to the passive nature of the RIS and the large number of reflecting elements that can lead to high channel estimation overhead. To address this issue, we propose a novel cascaded channel estimation strategy with low pilot overhead by exploiting the sparsity and the correlation of multiuser cascaded channels in millimeter-wave MISO systems. Based on the fact that the physical positions of the BS, the RIS and users do not appreciably change over multiple consecutive channel coherence blocks, we first estimate the full channel state information (CSI) including all the angle and gain information in the first coherence block, and then only re-estimate the channel gains in the remaining coherence blocks with much lower pilot overhead. In the first coherence block, we propose a two-phase channel estimation method, in which the cascaded channel of one typical user is estimated in Phase I based on the linear correlation among cascaded paths, while the cascaded channels of other users are estimated in Phase II by utilizing the reparameterized CSI of the common base station (BS)-RIS channel obtained in Phase I. The minimum pilot overhead is much less than the existing works. Simulation results show that the performance of the proposed method outperforms the existing methods in terms of the estimation accuracy when using the same amount of pilot overhead.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Nonlinear Dimension Reduction by PDF Estimation

    • Free pre-print version: Loading...

      Authors: Paul M. Baggenstoss;Steven Kay;
      Pages: 1493 - 1505
      Abstract: A new information criterion is proposed for nonlinear dimension reduction (NLDR) based on probability density function (PDF) estimation. As the PDF is estimated, the transformation to the latent space is learned and information transfer is maximized. The method (a) maximizes information at the output, (b) makes no assumptions about the data structure, (b) is invariant to invertible transformations, (c) can produce any desired output distribution (such as independent uniform or Gaussian latent variables) and (d) is completely general. In addition to performing dimension reduction, the approach results in a complete statistical model of the data including tractable likelihood function and ability to generate synthetic data. The method specializes to principal component analysis (PCA) for the linear/Gaussian case. When the transformation has limited approximation power, the trade-off between information transfer and approximating the desired output distribution can be controlled using a constant $beta$, which is analogous to $beta$-VAE. For efficiency, the method can be implemented with a neural network architecture using a variation of PDF projection, called projected belief network (PBN). In experiments with high-dimensional non-Gaussian input data, the superiority of PBN is shown relative to PCA, restricted Boltzmann machine (RBM), and a $beta$-variational auto-encoder ($beta$-VAE).
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Block-Sparse Recovery With Optimal Block Partition

    • Free pre-print version: Loading...

      Authors: Hiroki Kuroda;Daichi Kitahara;
      Pages: 1506 - 1520
      Abstract: This paper presents a convex recovery method for block-sparse signals whose block partitions are unknown a priori. We first introduce a nonconvex penalty function, where the block partition is adapted for the signal of interest by minimizing the mixed $ell _{2}/ell _{1}$ norm over all possible block partitions. Then, by exploiting a variational representation of the $ell _{2}$ norm, we derive the proposed penalty function as a suitable convex relaxation of the nonconvex one. For a block-sparse recovery model designed with the proposed penalty, we develop an iterative algorithm which is guaranteed to converge to a globally optimal solution. Numerical experiments demonstrate the effectiveness of the proposed method.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Multivariate Fast Iterative Filtering for the Decomposition of
           Nonstationary Signals

    • Free pre-print version: Loading...

      Authors: Antonio Cicone;Enza Pellegrino;
      Pages: 1521 - 1531
      Abstract: In this work, we present a new technique for the decomposition of multivariate data, which we call Multivariate Fast Iterative Filtering (MvFIF) algorithm. We study its properties, proving rigorously that it converges in finite time when applied to the decomposition of any kind of multivariate signal. We test MvFIF performance using a wide variety of artificial and real multivariate signals, showing its ability to: separate multivariate modulated oscillations; align frequencies along different channels; produce a quasi–dyadic filterbank when decomposing white Gaussian noise; decompose the signal in a quasi–orthogonal set of components; being robust to noise perturbation, even when the number of channels is increased considerably. Finally, we compare it and its performance with the main methods developed so far in the literature, proving that MvFIF produces, without any a priori assumption on the signal under investigation and in a fast and reliable manner, a uniquely defined decomposition of any multivariate signal.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • KalmanNet: Neural Network Aided Kalman Filtering for Partially Known
           Dynamics

    • Free pre-print version: Loading...

      Authors: Guy Revach;Nir Shlezinger;Xiaoyong Ni;Adrià López Escoriza;Ruud J. G. van Sloun;Yonina C. Eldar;
      Pages: 1532 - 1547
      Abstract: State estimation of dynamical systems in real-time is a fundamental task in signal processing. For systems that are well-represented by a fully known linear Gaussian state space (SS) model, the celebrated Kalman filter (KF) is a low complexity optimal solution. However, both linearity of the underlying SS model and accurate knowledge of it are often not encountered in practice. Here, we present KalmanNet, a real-time state estimator that learns from data to carry out Kalman filtering under non-linear dynamics with partial information. By incorporating the structural SS model with a dedicated recurrent neural network module in the flow of the KF, we retain data efficiency and interpretability of the classic algorithm while implicitly learning complex dynamics from data. We demonstrate numerically that KalmanNet overcomes non-linearities and model mismatch, outperforming classic filtering methods operating with both mismatched and accurate domain knowledge.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Distributed Estimation for Multi-Subsystem With Coupled Constraints

    • Free pre-print version: Loading...

      Authors: Xiaohui Hao;Yan Liang;Tiancheng Li;
      Pages: 1548 - 1559
      Abstract: The problem of distributed constraint-coupled estimation for multi-subsystem is addressed, in which there exist coupled linear equality constraints generated by cooperating neighbor subsystems (nodes). Our goal is to design a distributed estimator such that the state estimates obtained by each node can satisfy the all/global constraints based on the fact that each node only knows the local coupling constraints with its neighbors. To this end, the global constrained weighted least squares (GCWLS) optimization, as a centralized processing scheme, is presented firstly with its recursive implementation. Then, the distributed estimator of each node is constructed based on the structure of the above recursive centralized estimator and the basic idea of consensus iterative. Moreover, the sufficient conditions are established to guarantee that the iterative solution of the designed distributed estimator is able to converge to the centralized GCWLS estimates, which demonstrates that the local estimates obtained by the distributed estimator satisfy the all/global constraints. Finally, an example of collaborative navigation for formation airplanes is provided to demonstrate the effectiveness of the proposed estimator.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Multi-Agent Fusion With Different Limited Fields-of-View

    • Free pre-print version: Loading...

      Authors: Bailu Wang;Suqi Li;Giorgio Battistelli;Luigi Chisci;Wei Yi;
      Pages: 1560 - 1575
      Abstract: A key objective of multi-agent surveillance systems is to monitor a much larger region than the limited field-of-view (FoV) of any individual agent by successfully exploiting cooperation among multiple agents. Whenever either a centralized or a distributed approach is pursued, this goal cannot be achieved unless an appropriately designed fusion strategy is adopted. This paper presents a novel information fusion approach by considering for each agent a known limited, and possibly different, FoV. The proposed method, named Bayesian-operation InvaRiance on Difference-sets (BIRD) fusion, relies on Generalized Covariance Intersection (GCI) and exploits a general and exact decomposition of each multi-object posterior by partitioning the global FoV, i.e. the union of the FoVs of the fusing agents, into common and exclusive FoVs. It is shown how BIRD fusion can be used to perform multi-object estimation based on random finite sets on both a centralized and a distributed peer-to-peer sensor network. Simulation experiments on realistic multi-object tracking scenarios demonstrate the effectiveness of BIRD fusion.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Computing One-Bit Compressive Sensing via Double-Sparsity Constrained
           Optimization

    • Free pre-print version: Loading...

      Authors: Shenglong Zhou;Ziyan Luo;Naihua Xiu;Geoffrey Ye Li;
      Pages: 1593 - 1608
      Abstract: One-bit compressive sensing gains its popularity in signal processing and communications due to its low storage costs and low hardware complexity. However, it has been a challenging task to recover the signal only by exploiting the one-bit (the sign) information. In this paper, we appropriately formulate the one-bit compressive sensing into a double-sparsity constrained optimization problem. The first-order optimality conditions for this nonconvex and discontinuous problem are established via the newly introduced $tau$-stationarity, based on which, a gradient projection subspace pursuit (GPSP) algorithm is developed. It is proven that GPSP can converge globally and terminate within finite steps. Numerical experiments have demonstrated its excellent performance in terms of a high order of accuracy with a high computational speed.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Successive Convex Approximation Based Off-Policy Optimization for
           Constrained Reinforcement Learning

    • Free pre-print version: Loading...

      Authors: Chang Tian;An Liu;Guan Huang;Wu Luo;
      Pages: 1609 - 1624
      Abstract: Constrained reinforcement learning (CRL), also termed as safe reinforcement learning, is a promising technique enabling the deployment of RL agent in real-world systems. In this paper, we propose a successive convex approximation based off-policy optimization (SCAOPO) algorithm to solve the general CRL problem, which is formulated as a constrained Markov decision process (CMDP) in context of the average cost. The SCAOPO is based on solving a sequence of convex objective/feasibility optimization problems obtained by replacing the objective and constraint functions in the original problem with convex surrogate functions. The proposed SCAOPO enables reuse of experiences from previous updates, thereby significantly reducing implementation cost when deployed in real-world engineering systems that need to online learn the environment. In spite of the time-varying state distribution and the stochastic bias incurred by off-policy learning, the SCAOPO with a feasible initial point can still provably converge to a Karush-Kuhn-Tucker (KKT) point of the original problem almost surely.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Federated Matrix Factorization: Algorithm Design and Application to Data
           Clustering

    • Free pre-print version: Loading...

      Authors: Shuai Wang;Tsung-Hui Chang;
      Pages: 1625 - 1640
      Abstract: Recent demands on data privacy have called for federated learning (FL) as a new distributed learning paradigm in massive and heterogeneous networks. Although many FL algorithms have been proposed, few of them have considered the matrix factorization (MF) model, which is known to have a vast number of signal processing and machine learning applications. Since the MF problem involves two blocks of variables and the variables are usually subject to constraints related to specific solution structure, it requires new FL algorithm designs to achieve communication-efficient MF in heterogeneous data networks. In this paper, we address the challenge by proposing two new federated MF (FedMF) algorithms, namely, FedMAvg and FedMGS, based on the model averaging and gradient sharing principles, respectively. Both FedMAvg and FedMGS adopt multiple steps of local updates per communication round to speed up convergence, and allow only a randomly sampled subset of clients to communicate with the server for reducing the communication cost. Convergence properties for the two algorithms are thoroughly analyzed, which delineate the impacts of heterogeneous data distribution, local update number, and partial client communication on the algorithm performance, and guide the design of proposed algorithms. By focusing on a data clustering task, extensive experiment results are presented to examine the practical performance of proposed algorithms, as well as demonstrating their efficacy over the existing distributed clustering algorithms.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • DCT and DST Filtering With Sparse Graph Operators

    • Free pre-print version: Loading...

      Authors: Keng-Shih Lu;Antonio Ortega;Debargha Mukherjee;Yue Chen;
      Pages: 1641 - 1656
      Abstract: Graph filtering is a fundamental tool in graph signal processing. Polynomial graph filters (PGFs), defined as polynomials of a fundamental graph operator, can be implemented in the vertex domain, and usually have a lower complexity than frequency domain filter implementations. In this paper, we focus on the design of filters for graphs with graph Fourier transform (GFT) corresponding to a discrete trigonometric transform (DTT), i.e., one of 8 types of discrete cosine transforms (DCT) and 8 discrete sine transforms (DST). In this case, we show that multiple sparse graph operators can be identified, which allows us to propose a generalization of PGF design: multivariate polynomial graph filter (MPGF). First, for the widely used DCT-II (type-2 DCT), we characterize a set of sparse graph operators that share the DCT-II matrix as their common eigenvector matrix. This set contains the well-known connected line graph. These sparse operators can be viewed as graph filters operating in the DCT domain, which allows us to approximate any DCT graph filter by a MPGF, leading to a design with more degrees of freedom than the conventional PGF approach. Then, we extend those results to all of the 16 DTTs as well as their 2D versions, and show how their associated sets of multiple graph operators can be determined. We demonstrate experimentally that ideal low-pass and exponential DCT/DST filters can be approximated with higher accuracy with similar runtime complexity. Finally, we apply our method to transform-type selection in a video codec, AV1, where we demonstrate significant encoding time savings, with a negligible compression loss.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • DOA Estimation for Heterogeneous Wideband Sources Based on Adaptive
           Space-Frequency Joint Processing

    • Free pre-print version: Loading...

      Authors: Jun Zhang;Ming Bao;Xiao-Ping Zhang;Zhifei Chen;Jianhua Yang;
      Pages: 1657 - 1672
      Abstract: For direction-of-arrival (DOA) estimation of heterogeneous wideband sources, we propose a new adaptive space-frequency joint processing algorithm. The algorithm is implemented in the sparse Bayesian learning (SBL) DOA framework, which is named as ASF-SBL algorithm in this paper. The traditional SBL-based DOA methods suffer from the problem of erroneous DOA estimation due to the structural mismatch between the invariant prior and the sparse coefficients. To solve this problem, the ASF-SBL algorithm employs a new space-frequency correlation prior model that can be adaptively changed to fit heterogeneous DOA scenarios. Specifically, nine alternative space-frequency structural patterns are constructed to represent the joint space-frequency characteristics of spatial sparse signals. By evaluating the space-frequency correlation of the sparse coefficients updated in each iteration under SBL framework, a suitable pattern is selected from the nine choices to determine the adaptive prior of each coefficient. This adaptive method leads to accurate DOA estimation in different wideband sources scenarios. In addition, we introduce a distributed processing method to extend the ASF-SBL algorithm to two-dimensional DOA estimation. This extension is achieved by decoupling the DOA estimation into two one-dimensional estimations. The decoupling avoids the problems of a huge redundant dictionary and excessive computational complexity caused by the combination of azimuth and elevation angles. Numerical simulations show that the ASF-SBL algorithm is superior to existing algorithms in DOA estimation of heterogeneous sources.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Hardware-Aware Design of Multiplierless Second-Order IIR Filters With
           Minimum Adders

    • Free pre-print version: Loading...

      Authors: Rémi Garcia;Anastasia Volkova;Martin Kumm;Alexandre Goldsztejn;Jonas Kühle;
      Pages: 1673 - 1686
      Abstract: In this work we optimally solve the problem of multiplierless design of second-order Infinite Impulse Response filters with minimum number of adders. Given a frequency specification, we design a stable direct form filter with hardware-aware fixed-point coefficients where all multiplications are replaced by bit shifts and additions. The coefficient design, quantization and implementation, typically conducted independently, are now gathered into one global optimization problem, modeled through integer linear programming and efficiently solved using generic solvers. The optimal filters are implemented within the FloPoCo IP core generator and synthesized for field programmable gate arrays (FPGAs) and application specific integrated circuits (ASICs). With respect to state-of-the-art three-step filter design methods, our one-step design approach achieves, on average, 48% reduction in number of lookup tables, 27% delay reduction and 57% reduction in power on FPGAs. ASICs experiment illustrate similar 48% reduction in circuit area, 27% delay reduction and 65% power reduction for a 14 nm ASIC.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Symbol-Level Precoding Through the Lens of Zero Forcing and Vector
           Perturbation

    • Free pre-print version: Loading...

      Authors: Yatao Liu;Mingjie Shao;Wing-Kin Ma;Qiang Li;
      Pages: 1687 - 1703
      Abstract: Symbol-level precoding (SLP) has recently emerged as a new paradigm for physical-layer transmit precoding in multiuser multi-input-multi-output (MIMO) channels. It exploits the underlying symbol constellation structure, which the conventional paradigm of linear precoding does not, to enhance symbol-level performance such as symbol error probability (SEP). This paper aims to better understand the relationships between SLP and linear precoding, subsequent design implications, and further connections beyond the existing SLP scope. Focused on the quadrature amplitude modulation (QAM) constellations, our study is built on a basic signal observation, namely, that SLP can be equivalently represented by a zero-forcing (ZF) linear precoding scheme augmented with some appropriately chosen symbol-dependent perturbation terms, and that some extended form of SLP is equivalent to a vector perturbation (VP) nonlinear precoding scheme augmented with the above-noted perturbation terms. We examine how insights arising from this perturbed ZF and VP interpretations can be leveraged to i) substantially simplify the optimization of certain SLP design criteria, namely, total or peak power minimization subject to SEP quality guarantees; and ii) draw connections with some existing SLP designs. We also touch on the analysis side by showing that, under total power minimization, the basic ZF scheme is a near-optimal SLP scheme when the QAM order is very high—which gives a vital implication that SLP is more useful for lower-order QAM cases. Numerical results further indicate the merits and limitations of the different SLP designs derived from the perturbed ZF and VP interpretations.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Block-Term Tensor Decomposition Model Selection and Computation: The
           Bayesian Way

    • Free pre-print version: Loading...

      Authors: Paris V. Giampouras;Athanasios A. Rontogiannis;Eleftherios Kofidis;
      Pages: 1704 - 1717
      Abstract: The so-called block-term decomposition (BTD) tensor model, especially in its rank-$(L_{r},L_{r},1)$ version, has been recently receiving increasing attention due to its enhanced ability of representing systems and signals that are composed of blocks of rank higher than one, a scenario encountered in numerous and diverse applications. Uniqueness conditions and fitting methods have thus been thoroughly studied. Nevertheless, the challenging problem of estimating the BTD model structure, namely the number of block terms, $R$, and their individual ranks, $L_{r}$, has only recently started to attract significant attention, mainly through regularization-based approaches which entail the need to tune the regularization parameter(s). In this work, we build on ideas of sparse Bayesian learning (SBL) and put forward a fully automated Bayesian approach. Through a suitably crafted multi-level hierarchical probabilistic model, which gives rise to heavy-tailed prior distributions for the BTD factors, structured sparsity is jointly imposed. Ranks are then estimated from the numbers of blocks ($R$) and columns ($L_{r}$) of non-negligible energy. Approximate posterior inference is implemented, within the variational inference framework. The resulting iterative algorithm completely avoids hyperparameter tuning, which is a significant defect of regularization-based methods. Alternative probabilistic models are also explored and the connections with their regularization-based counterparts are brought to light with the aid of the associated maximum a-posteriori (MAP) estimators. We repor- simulation results with both synthetic and real-word data, which demonstrate the merits of the proposed method in terms of both rank estimation and model fitting as compared to state-of-the-art relevant methods.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Region-Restricted Sensor Placement Based on Gaussian Process for Sound
           Field Estimation

    • Free pre-print version: Loading...

      Authors: Tomoya Nishida;Natsuki Ueno;Shoichi Koyama;Hiroshi Saruwatari;
      Pages: 1718 - 1733
      Abstract: Sensor placement methods for field estimation based on Gaussian processes are proposed. Generally, sensor placement methods determine the appropriate placement positions by selecting them from predefined candidate positions. Many criteria for the selection have been proposed, with which the quality of the placements is evaluated with regard to the field at the candidate positions. This means that these sensor placement methods seek to find the positions that can estimate the field at the candidate positions accurately. In practical situations, however, the candidate sensor placement region can be different from the target region for field estimation. In this paper, to make sensor placement methods applicable to this situation, we propose two sensor placement methods based on the mean squared error and on conditional entropy that can be applied to cases in which the sensor placement region is arbitrarily restricted. After formulating the sensor placement problems, two approximate algorithms are derived: the greedy algorithm and the convex-relaxation-based algorithm. The application of the proposed methods to sound field estimation is also illustrated, and their effectiveness was confirmed through numerical experiments.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • A Riemannian Geometric Approach to Blind Signal Recovery for Grant-Free
           Radio Network Access

    • Free pre-print version: Loading...

      Authors: Carlos Feres;Zhi Ding;
      Pages: 1734 - 1748
      Abstract: We propose a new nonconvex framework for blind multiple signal demixing and recovery. The proposed Riemannian geometric approach extends the well known constant modulus algorithm to facilitate grant-free wireless access for simultaneous demixing and recovery of multiple signal demixing and recovery. We formulate the problem as non-convex problem optimization problem integrated with the signal orthogonality constraint in the form of Riemannian Orthogonal CMA (ROCMA). Unlike traditional stochastic gradient solutions that require large data samples, parameter tuning, and careful initialization, we leverage Riemannian geometry and transform the orthogonality requirement of recovered signals into a Riemannian manifold optimization. Our solution demonstrates full recovery of multiple access signals without large data sample size or special initialization with high probability of success.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Foundations of MIMO Radar Detection Aided by Reconfigurable Intelligent
           Surfaces

    • Free pre-print version: Loading...

      Authors: Stefano Buzzi;Emanuele Grossi;Marco Lops;Luca Venturino;
      Pages: 1749 - 1763
      Abstract: A reconfigurable intelligent surface (RIS) is a nearly-passive flat layer made of inexpensive elements that can add a tunable phase shift to the impinging electromagnetic wave and are controlled by a low-power electronic circuit. This paper considers the fundamental problem of target detection in a RIS-aided multiple-input multiple-output (MIMO) radar. At first, a general signal model is introduced, which includes the possibility of using up to two RISs (one close to the radar transmitter and one close to the radar receiver) and subsumes both a monostatic and a bistatic radar configuration with or without a line-of-sight view of the prospective target. Upon resorting to a generalized likelihood ratio test (GLRT), the design of the phase shifts introduced by the RIS elements is formulated as the maximization of the probability of detection in the location under inspection for a fixed probability of false alarm, and suitable optimization algorithms are proposed. The performance analysis shows the benefits granted by the presence of the RISs and shed light on the interplay among the key system parameters, such as the radar-RIS distance, the RIS size, and the location of the prospective target. A major finding is that the RISs should be better deployed in the near-field of the radar arrays at both the transmit and the receive side. The paper is concluded by discussing some open problems and foreseen applications.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Adaptive Classification Using Incremental Linearized Kernel Embedding

    • Free pre-print version: Loading...

      Authors: John Joseph Hall;Christopher Robbiano;Mahmood R. Azimi-Sadjadi;
      Pages: 1764 - 1774
      Abstract: This paper considers the problem of adaptive classification for performing pattern discrimination in varying conditions when new data arrives. A new efficient method is presented to incrementally update features in a Nyström-approximated linearized kernel embedding (LKE). Our method leverages a fast eigendecomposition algorithm for symmetric Arrowhead matrices. The proposed method can also be applied to kernel principal component analysis (KPCA) or similar problems. A mechanism is proposed which allows the incremental linearized kernel embedding to be used for updating of dictionaries in a sparse representation-based classification algorithm. The method is based on transporting the dictionaries into the embedding expanded with new data points and avoids the need to learn new dictionary matrices every time new data becomes available. The effectiveness of the developed methods is illustrated on two handwritten digit image data sets namely MNIST and USPS. Classification performance before and after sequential embedding updates is evaluated and compared. Comparisons are also made between our incremental LKE algorithm and the conventional approach to updating the empirical kernel map in terms of their computational requirements and numerical stability.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Compressed Gradient Tracking for Decentralized Optimization Over General
           Directed Networks

    • Free pre-print version: Loading...

      Authors: Zhuoqing Song;Lei Shi;Shi Pu;Ming Yan;
      Pages: 1775 - 1787
      Abstract: In this paper, we propose two communication-efficient decentralized optimization algorithms over a general directed multi-agent network. The first algorithm, termed Compressed Push-Pull (CPP), combines the gradient tracking Push-Pull method with communication compression. We show that CPP is applicable to a general class of unbiased compression operators and achieves linear convergence rate for strongly convex and smooth objective functions. The second algorithm is a broadcast-like version of CPP (B-CPP), and it also achieves linear convergence rate under the same conditions on the objective functions. B-CPP can be applied in an asynchronous broadcast setting and further reduce communication costs compared to CPP. Numerical experiments complement the theoretical analysis and confirm the effectiveness of the proposed methods.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Harmonic Radar With Adaptively Phase-Coherent Auxiliary Transmitters

    • Free pre-print version: Loading...

      Authors: Anastasia Lavrenko;James K. Cavers;Graeme K. Woodward;
      Pages: 1788 - 1802
      Abstract: In harmonic radar (HR), the transmitter illuminates a nonlinear target (the tag), causing the return signal to consist of harmonics at multiples of the transmitted carrier frequency. Of them, the second harmonic is usually the strongest and the one to which the receiver is tuned. This frequency difference distinguishes the tag reflection from environmental clutter, which remains at the illuminating frequency. However, the passive nature of HR tags severely limits the reflected power, and therefore the operational range of a HR system. We propose to increase the range and/or signal to noise ratio (SNR) by novel restructuring at the physical and signal levels. For this, we accompany the original transmitter with auxiliary transmitters able to send simple tones that are synchronized to arrive at the tag in phase, and we design the receiver to detect an intermodulation component. The resulting range and SNR are much greater than those of the original, conventional HR system, even if the original system were to transmit with power equal to the aggregate power of the proposed system. Achieving mutually coherent, (in phase), arrival of the tones at the tag is the focus of the present paper. We provide a system framework that models the tag, then present the adaptive phase coherence algorithm and analyze the probabilistic growth of the output signal power. We also account for the effects of frequency shifts due to transmitter mobility and the frequency offset errors in the transmitter local oscillators.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Stochastic Mirror Descent for Low-Rank Tensor Decomposition Under
           Non-Euclidean Losses

    • Free pre-print version: Loading...

      Authors: Wenqiang Pu;Shahana Ibrahim;Xiao Fu;Mingyi Hong;
      Pages: 1803 - 1818
      Abstract: This work considers low-rank canonical polyadic decomposition (CPD) under a class of non-Euclidean loss functions that frequently arise in statistical machine learning and signal processing. These loss functions are often used for certain types of tensor data, e.g., count and binary tensors, where the least squares loss is considered unnatural. Compared to the least squares loss, the non-Euclidean losses are generally more challenging to handle. Non-Euclidean CPD has attracted considerable interests and a number of prior works exist. However, pressing computational and theoretical challenges, such as scalability and convergence issues, still remain. This work offers a unified stochastic algorithmic framework for large-scale CPD decomposition under a variety of non-Euclidean loss functions. Our key contribution lies in a tensor fiber sampling strategy-based flexible stochastic mirror descent framework. Leveraging the sampling scheme and the multilinear algebraic structure of low-rank tensors, the proposed lightweight algorithm ensures global convergence to a stationary point under reasonable conditions. Numerical results show that our framework attains promising non-Euclidean CPD performance. The proposed framework also exhibits substantial computational savings compared to state-of-the-art methods.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • VR-PRUNE: Decidable Variable-Rate Dataflow for Signal Processing Systems

    • Free pre-print version: Loading...

      Authors: Jani Boutellier;Yujunrong Ma;Jiahao Wu;Mir Khan;Shuvra S. Bhattacharyya;
      Pages: 1819 - 1833
      Abstract: The dataflow concept has been successfully used for modeling and synthesizing signal processing applications since decades, and recently, dataflow has also been discovered to match the computation model of machine learning applications, leading to extremely successful dataflow based application design frameworks. One of the most attractive features of dataflow, especially for signal processing, is related to its formal nature: when properly defined, a dataflow-based application model can be analytically verified for correctness at the stage of application design. This paper proposes VR-PRUNE, a novel dataflow model of computation that is aimed for design of high-performance signal processing software, together with runtime support that allows efficient application deployment to heterogeneous GPU-equipped platforms. Compared to prior work, VR-PRUNE features variable token rate processing, which enables designing adaptive signal processing applications, and implementing solutions that, e.g., allow trading-off between power consumption and filtering bandwidth at runtime. The paper presents the formal concepts of VR-PRUNE, as well as four application examples from domains related to signal processing, accompanied with quantitative results, which show that using VR-PRUNE enables, for example, application power-performance scaling, and on the other hand describing adaptive application behavior with 59% fewer dataflow graph components compared to previous work.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Towards Flexible Sparsity-Aware Modeling: Automatic Tensor Rank Learning
           Using the Generalized Hyperbolic Prior

    • Free pre-print version: Loading...

      Authors: Lei Cheng;Zhongtao Chen;Qingjiang Shi;Yik-Chung Wu;Sergios Theodoridis;
      Pages: 1834 - 1849
      Abstract: Tensor rank learning for canonical polyadic decomposition (CPD) has long been deemed as an essential yet challenging problem. In particular, since thetensor rank controls the complexity of the CPD model, its inaccurate learning would cause overfitting to noise or underfitting to the signal sources, and even destroy the interpretability of model parameters. However, the optimal determination of a tensor rank is known to be a non-deterministic polynomial-time hard (NP-hard) task. Rather than exhaustively searching for the best tensor rank via trial-and-error experiments, Bayesian inference under the Gaussian-gamma prior was introduced in the context of probabilistic CPD modeling, and it was shown to be an effective strategy for automatic tensor rank determination. This triggered flourishing research on other structured tensor CPDs with automatic tensor rank learning. On the other side of the coin, these research works also reveal that the Gaussian-gamma model does not perform well for high-rank tensors and/or low signal-to-noise ratios (SNRs). To overcome these drawbacks, in this paper, we introduce a more advanced generalized hyperbolic (GH) prior to the probabilistic CPD model, which not only includes the Gaussian-gamma model as a special case, but also is more flexible to adapt to different levels of sparsity. Based on this novel probabilistic model, an algorithm is developed under the framework of variational inference, where each update is obtained in a closed-form. Extensive numerical results, using synthetic data and real-world datasets, demonstrate the significantly improved performance of the proposed method in learning both low as well as high tensor ranks even for low SNR cases.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Learning Decentralized Wireless Resource Allocations With Graph Neural
           Networks

    • Free pre-print version: Loading...

      Authors: Zhiyang Wang;Mark Eisen;Alejandro Ribeiro;
      Pages: 1850 - 1863
      Abstract: We consider the broad class of decentralized optimal resource allocation problems in wireless networks, which can be formulated as a constrained statistical learning problems with a localized information structure. We develop the use of Aggregation Graph Neural Networks (Agg-GNNs), which process a sequence of delayed and potentially asynchronous graph aggregated state information obtained locally at each transmitter from multi-hop neighbors. We further utilize model-free primal-dual learning methods to optimize performance subject to constraints in the presence of delay and asynchrony inherent to decentralized networks. We demonstrate a permutation equivariance property of the resulting resource allocation policy that can be shown to facilitate transference to dynamic network configurations. The proposed framework is validated with numerical simulations that exhibit superior performance to baseline strategies.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Three Dimensional Source Localization Using Arrival Angles from Linear
           Arrays: Analytical Investigation and Optimal Solution

    • Free pre-print version: Loading...

      Authors: Yimao Sun;K. C. Ho;Lin Gao;Jifeng Zou;Yanbing Yang;Liangyin Chen;
      Pages: 1864 - 1879
      Abstract: Angle-based localization of a source at unique coordinates in the three-dimensional (3-D) space utilizes traditionally the two-dimensional (2-D) angle of arrival (AOA) measurements from planar arrays. This paper investigates the positioning performance and develops an optimal solution for the 3-D localization using one-dimensional (1-D) space angle (SA) measurements that has the appeal of involving linear arrays only. The localization performance by SA is less understood and the positioning algorithms from the literature are suboptimal and have restrictions on the altitudes and orientations of the linear array receivers. This paper establishes the basic concept of using SA for localization, and conducts analytical comparison of SA and AOA positionings by cross arrays, where the contrasts in the angle observation accuracy, the geometric dilution effect and overall localization performance are elaborated. A solution that can reach the Cramér-Rao Lower Bound performance under Gaussian noise is also proposed that does not have restriction on the placement of the linear array receivers. It consists of an initial solution by semidefinite relaxation and a refined solution by an algebraic estimator. Simulations validate the theoretical investigation and the algorithm performance.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Design and Testbed Implementation of Multiuser CFOs Estimation for MIMO
           SC-FDMA System

    • Free pre-print version: Loading...

      Authors: Sushant Kumar;Sudhan Majhi;
      Pages: 1880 - 1889
      Abstract: In this paper, we propose and implement blind multiuser carrier frequency offsets (CFOs) estimation for multi-input multi-output (MIMO) single carrier frequency division multiple access (SC-FDMA) uplink system using orthogonal propagator method (OPM) over a noisy frequency-selective channel. The performance of typical OPM is limited at low signal-to-noise ratio (SNR) due to its noise-free signal model. The additive white Gaussian noise mainly impacts the diagonal elements of the data covariance matrix (DCM) of the received signal. First, the proposed fractional CFOs estimator minimizes the noise effect by reconstructing the denoised diagonal elements of the DCM for the received signal through cubic Hermite interpolation. Therefore, we use modified OPM to estimate multiple CFOs for MIMO SC-FDMA systems. Second, we have used an iterative method based on the first-order Taylor series approximation of the CFO vector to avoid peak ambiguity and reduce the number of iterations required in the grid search. The mean square error of the proposed CFO estimator considerably improves compared with the existing methods at a low SNR regime. The bit error rate performance of the proposed method for MIMO SC-FDMA is also compared with the existing methods. Finally, the proposed estimator is validated by implementing it on radio frequency hardware testbed over an indoor propagation environment.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Low-Complexity LMMSE-Based Iterative Soft Interference Cancellation for
           MIMO Systems

    • Free pre-print version: Loading...

      Authors: Sangjoon Park;
      Pages: 1890 - 1899
      Abstract: This paper presents a low-complexity linear minimum mean-squared-error-based iterative soft interference cancellation (LMMSE-ISIC) scheme for multiple-input multiple-output (MIMO) systems. To avoid direct matrix inversion in the conventional LMMSE-ISIC scheme, expressions are derived to obtain the filtering vector and estimate of the conventional scheme; the direct inverse operation is then replaced by the vector-based operations in the proposed scheme. Thus, for the worst-case scenario in the proposed scheme, the complexity of estimating each transmit symbol is approximately proportional to the square of the number of receive antennas; in the conventional scheme, it is approximately proportional to the cube of the number of receive antennas. In addition, because there are no approximations for deriving the filtering vector and estimate, the proposed LMMSE-ISIC scheme achieves near-optimum performance identical to that of the conventional scheme, which is close to the matched filter bound of the channel. Further, the extension of the proposed scheme for iterative detection and decoding is developed for coded systems. The simulated results confirm that the conventional and proposed schemes outperform the approximated matrix inversion based schemes and achieve the identical error performance in both uncoded and coded systems, while the complexity order of the proposed scheme is similar to or even lower than those of the approximation schemes. Therefore, the proposed scheme can be considered an effective near-optimum LMMSE-based iterative detection approach for MIMO systems, especially for massive MIMO systems with a high load factor.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Learning to Continuously Optimize Wireless Resource in a Dynamic
           Environment: A Bilevel Optimization Perspective

    • Free pre-print version: Loading...

      Authors: Haoran Sun;Wenqiang Pu;Xiao Fu;Tsung-Hui Chang;Mingyi Hong;
      Pages: 1900 - 1917
      Abstract: There has been a growing interest in developing data-driven, and in particular deep neural network (DNN) based methods for modern communication tasks. These methods achieve state-of-the-art performance for a few popular wireless resource allocation problems, while requiring less computational efforts, less resources for acquiring channel state information (CSI), etc. However, it is often challenging for these approaches to learn in a dynamic environment. This work develops a new approach that enables data-driven methods to continuously learn and optimize wireless resource allocation in a dynamic environment. Specifically, we consider an “episodically dynamic” setting where the environment statistics change in “episodes,” and in each episode the environment is stationary. We propose to build the notion of continual learning (CL) into wireless system design, so that the learning model can incrementally adapt to the new episodes, without forgetting knowledge learned from the previous episodes. We demonstrate the effectiveness of the CL approach by integrating it with three popular DNN based models for power control, beamforming and multi-user MIMO, respectively, and testing using both synthetic and ray-tracing based data sets. These numerical results show that the proposed CL approach is not only able to adapt to the new scenarios quickly and seamlessly, but importantly, it also maintains high performance over the previously encountered scenarios as well.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Delayed Combination of Adaptive Filters in Colored Noise

    • Free pre-print version: Loading...

      Authors: Sheng Zhang;Haiquan Zhao;Hing Cheung So;
      Pages: 1918 - 1931
      Abstract: In this work, we study the combination of adaptive filters in colored noise environments. First, a combination framework using delayed weights is introduced to tackle the colored noise. Based on this, delayed convex and affine combinations of two LMS filters are developed, resulting in the so-called Dcvx-LMS and Daff-LMS algorithms. Then, the convergence behaviors of the two algorithms are investigated using standard mean-square deviation analysis. In addition, to speed up the convergence and reduce the computational complexity, we propose delayed combination with periodic feedback, delayed combined-step-size and block implementation methods. Finally, simulation results demonstrate the superiority of our algorithms over previously reported techniques in the presence of colored noise.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Synthesizing Decentralized Controllers With Graph Neural Networks and
           Imitation Learning

    • Free pre-print version: Loading...

      Authors: Fernando Gama;Qingbiao Li;Ekaterina Tolstaya;Amanda Prorok;Alejandro Ribeiro;
      Pages: 1932 - 1946
      Abstract: Dynamical systems consisting of a set of autonomous agents face the challenge of having to accomplish a global task, relying only on local information. While centralized controllers are readily available, they face limitations in terms of scalability and implementation, as they do not respect the distributed information structure imposed by the network system of agents. Given the difficulties in finding optimal decentralized controllers, we propose a novel framework using graph neural networks (GNNs) to learn these controllers. GNNs are well-suited for the task since they are naturally distributed architectures and exhibit good scalability and transferability properties. We show that GNNs learn appropriate decentralized controllers by means of imitation learning, leverage their permutation invariance properties to successfully scale to larger teams and transfer to unseen scenarios at deployment time. The problems of flocking and multi-agent path planning are explored to illustrate the potential of GNNs in learning decentralized controllers.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Disagreement-Based Active Learning in Online Settings

    • Free pre-print version: Loading...

      Authors: Boshuang Huang;Sudeep Salgia;Qing Zhao;
      Pages: 1947 - 1958
      Abstract: We study online active learning for classifying streaming instances within the framework of statistical learning theory. At each time, the learner either queries the label of the current instance or predicts the label based on past seen examples. The objective is to minimize the number of queries while constraining the number of prediction errors over a horizon of length $T$. We develop a disagreement-based online learning algorithm for a general hypothesis space and under the Tsybakov noise and establish its label complexity under a constraint of bounded regret in terms of classification errors. We further establish a matching (up to a poly-logarithmic factor) lower bound, demonstrating the order optimality of the proposed algorithm. We address the tradeoff between label complexity and regret and show that the algorithm can be modified to operate at a different point on the tradeoff curve.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • The Statistics of Superdirective Beam Patterns

    • Free pre-print version: Loading...

      Authors: Andrea Trucco;
      Pages: 1959 - 1975
      Abstract: Superdirective arrays have been extensively studied because of their considerable potential accompanied, unfortunately, by a high sensitivity to random errors that affect the responses and positions of array elements. However, the statistics of their actual beam pattern (BP) has never been systematically investigated. This paper shows that the Rician probability density function (PDF), sometimes adopted to study the impact of errors in conventional arrays, is a valid approximation for superdirective BP statistics only where some mathematical terms are negligible. The paper also shows that this is the case for all linear end-fire arrays considered. A similar study is proposed concerning the correlation between BP lobes, showing that for the superdirective arrays considered the lobes, especially non-adjacent ones, are almost independent. Furthermore, knowledge of the PDF of the actual BP allows one to define quantile BP functions, whose probability of being exceeded, at any point, is fixed. Combining the lobes’ independence with quantile BP functions, an empirical equation for the probability that the entire actual BP will not exceed a quantile function over an interval larger than a given size is obtained. This new knowledge and these tools make it possible to devise new methods to design robust superdirective arrays via optimization goals with clearer and more relevant statistical meaning.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • $k$ -Nearest+Neighbor+Graphs&rft.title=IEEE+Transactions+on+Signal+Processing&rft.issn=1053-587X&rft.date=2022&rft.volume=70&rft.spage=1976&rft.epage=1986&rft.aulast=Chen;&rft.aufirst=Yi-Wei&rft.au=Yi-Wei+Liu;Hao+Chen;">A Fast and Efficient Change-Point Detection Framework Based on Approximate
           $k$ -Nearest Neighbor Graphs

    • Free pre-print version: Loading...

      Authors: Yi-Wei Liu;Hao Chen;
      Pages: 1976 - 1986
      Abstract: Change-point analysis is thriving in this Big Data era to address problems arising in many fields where massive data sequences are collected to study complicated phenomena over time. It plays an important role in processing these data by segmenting a long sequence into homogeneous parts for follow-up studies. The task requires the method to be able to process large datasets quickly and deal with various types of changes for high-dimensional data. We propose a new approach making use of approximate $k$-nearest neighbor information from the observations, and derive an analytic formula to control the type I error. The time complexity of our proposed method is $O(dn(log n+k log d)+nk^{2})$ for an $n$-length sequence of $d$-dimensional data. The test statistic we consider incorporates a useful pattern for moderate- to high- dimensional data so that the proposed method could detect various types of changes in the sequence. The new approach is also asymptotic distribution free, facilitating its usage for a broader community. We apply our method to fMRI datasets and Neuropixels datasets to illustrate its effectiveness.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Tracking Multiple Spawning Targets Using Poisson Multi-Bernoulli Mixtures
           on Sets of Tree Trajectories

    • Free pre-print version: Loading...

      Authors: Ángel F. García-Fernández;Lennart Svensson;
      Pages: 1987 - 1999
      Abstract: This paper proposes a Poisson multi-Bernoulli mixture (PMBM) filter on the space of sets of tree trajectories for multiple target tracking with spawning targets. A tree trajectory contains all trajectory information of a target and its descendants, which appear due to the spawning process. Each tree contains a set of branches, where each branch has trajectory information of a target or one of the descendants and its genealogy. For the standard dynamic and measurement models with multi-Bernoulli spawning, the posterior is a PMBM density, with each Bernoulli having information on a potential tree trajectory. To enable a computationally efficient implementation, we derive an approximate PMBM filter in which each Bernoulli tree trajectory has multi-Bernoulli branches, obtained by minimising the Kullback-Leibler divergence. The resulting filter improves tracking performance of state-of-the-art algorithms in a simulated scenario.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Deep Generative Models for Downlink Channel Estimation in FDD Massive MIMO
           Systems

    • Free pre-print version: Loading...

      Authors: Javad Mirzaei;Shahram Shahbaz Panahi;Raviraj S. Adve;Navaneetha Krishna Madan Gopal;
      Pages: 2000 - 2014
      Abstract: It is well accepted that acquiring downlink channel state information in frequency division duplexing (FDD) massive multiple-input multiple-output (MIMO) systems is challenging because of the large overhead in training and feedback. In this paper, we propose a deep generative model (DGM)-based technique to address this challenge. Exploiting the partial reciprocity of uplink and downlink channels, we first estimate the frequency-independent underlying channel parameters, i.e., the magnitudes of path gains, delays, angles-of-arrivals (AoAs) and angles-of-departures (AoDs), via uplink training, since these parameters are common in both uplink and downlink. Then, the frequency-specific underlying channel parameters, specifically, the phase of each propagation path, are estimated via downlink training using a very short training signal. In the first step, we incorporate the underlying distribution of the channel parameters as a prior into our channel estimation algorithm. We use DGMs to learn this distribution. Simulation results indicate that our proposed DGM-based channel estimation technique outperforms, by a large gap, the conventional channel estimation techniques in practical ranges of signal-to-noise ratio (SNR). In addition, a near-optimal performance is achieved using only few downlink pilot measurements.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • GRACGE: Graph Signal Clustering and Multiple Graph Estimation

    • Free pre-print version: Loading...

      Authors: Yanli Yuan;De Wen Soh;Xiao Yang;Kun Guo;Tony Q. S. Quek;
      Pages: 2015 - 2030
      Abstract: In graph signal processing (GSP), complex datasets arise from several underlying graphs and in the presence of heterogeneity. Graph learning from heterogeneous graph signals often results in challenging high-dimensional multiple graph estimation problems, and prior information regarding which graph the data was observed is typically unknown. To address the above challenges, we develop a novel framework called GRACGE (GRAph signal Clustering and multiple Graph Estimation) to partition the graph signals into clusters and jointly learn the multiple underlying graphs for each of the clusters. GRACGE advocates a regularized EM (rEM) algorithm where a structure fusion penalty with adaptive regularization parameters is imposed on the M-step. Such a penalty can exploit the structural similarities among graphs to overcome the curse of dimensionality. Moreover, we provide a non-asymptotic bound on the estimation error of the GRACGE algorithm, which establishes its computational and statistical guarantees. Furthermore, this theoretical analysis motivates us to adaptively re-weight the regularization parameters. With the adaptive regularization scheme, the final estimates of GRACGE will geometrically converge to the true parameters within statistical precision. Finally, experimental results on both synthetic and real data demonstrate the performance of the proposed GRACGE algorithm.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • $k$ +Selection+From+ $m$ -Wise+Partial+Rankings+via+Borda+Counting&rft.title=IEEE+Transactions+on+Signal+Processing&rft.issn=1053-587X&rft.date=2022&rft.volume=70&rft.spage=2031&rft.epage=2045&rft.aulast=Shen;&rft.aufirst=Wenjing&rft.au=Wenjing+Chen;Ruida+Zhou;Chao+Tian;Cong+Shen;">On Top- $k$ Selection From $m$ -Wise Partial Rankings via Borda Counting

    • Free pre-print version: Loading...

      Authors: Wenjing Chen;Ruida Zhou;Chao Tian;Cong Shen;
      Pages: 2031 - 2045
      Abstract: We analyze the performance of the Borda counting algorithm in a non-parametric model. The algorithm needs to utilize probabilistic rankings of the items within $m$-sized subsets to accurately determine which items are the overall top-$k$ items in a total of $n$ items. The Borda counting algorithm simply counts the cumulative scores for each item from these partial ranking observations. This generalizes a previous work of a similar nature by Shah et al. using probabilistic pairwise comparison data. The performance of the Borda counting algorithm critically depends on the associated score separation $Delta _{k}$ between the $k$-th item and the $(k+1)$-th item. Specifically, we show that if $Delta _{k}$ is greater than certain value, then the top-$k$ items selected by the algorithm is asymptotically accurate almost surely; if $Delta _{k}$ is below certain value, then the result will be inaccurate with a constant probability. In the special case of $m=2$, i.e., pairwise comparison, the resultant bound is tighter than that given by Shah et al., leading to a reduced gap between the error probability upper and lower bounds. These results are further extended to the approximate top-$k$ selection setting. Numerical experiments demonstrate the effectiveness and accuracy of the Borda counting algorithm, compared with the spectral MLE-based algorithm, particularly when the data does not necessarily follow an assumed parametric model.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Low-Complexity ADMM-Based Algorithm for Robust Multi-Group Multicast
           Beamforming in Large-Scale Systems

    • Free pre-print version: Loading...

      Authors: Niloofar Mohamadi;Min Dong;Shahram ShahbazPanahi;
      Pages: 2046 - 2061
      Abstract: We design an efficient robust multi-group multicast beamforming scheme for massive multiple-input multiple-output (MIMO) systems. Assuming only estimates of the channel covariance matrices are available at the base station with a bounded error, we formulate the robust quality-of-service (QoS) problem, which is to minimize the transmit power subject to the worst-case minimum signal-to-interference-plus-noise-ratio (SINR) guarantee. We directly solve the worst-case SINR problem and convert the robust QoS constraint into a number of non-convex constraints. Based on the recent convergence result of the alternating direction method of multipliers (ADMM) for non-convex problems, we develop an ADMM-based fast algorithm to directly tackle the reformulated non-convex problem with a convergence guarantee. The algorithm contains two layers of ADMM procedures. We design the outer-layer ADMM to decompose the problem into three convex subproblems and solve them alternatingly. We further develop an inner-layer consensus-ADMM-based algorithm to efficiently solve one subproblem. By exploring each subproblem structure and developing the special optimization techniques, we obtain closed-form or semi-closed-form solutions to each subproblem. These results lead to a fast iterative algorithm, which is guaranteed to converge to a stationary point of the original robust QoS problem. Simulation shows that our proposed algorithm provides a favorable performance compared with existing alternative methods with magnitudes of computational complexity reduction.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Approximate Message Passing With Parameter Estimation for Heavily
           Quantized Measurements

    • Free pre-print version: Loading...

      Authors: Shuai Huang;Deqiang Qiu;Trac D. Tran;
      Pages: 2062 - 2077
      Abstract: Designing efficient sparse recovery algorithms that could handle noisy quantized measurements is important in a variety of applications – from radar to source localization, spectrum sensing and wireless networking. We take advantage of the approximate message passing (AMP) framework to achieve this goal given its high computational efficiency and state-of-the-art performance. In AMP, the signal of interest is assumed to follow certain prior distribution with unknown parameters. Previous works focused on finding the parameters that maximize the measurement likelihood via expectation maximization – an increasingly difficult problem to solve in cases involving complicated probability models. In this paper, we treat the parameters as unknown variables and compute their posteriors via AMP. The parameters and signal of interest can then be jointly recovered. Compared to previous methods, the proposed approach leads to a simple and elegant parameter estimation scheme, allowing us to directly work with 1-bit quantization noise model. We then further extend our approach to general multi-bit quantization noise model. Experimental results show that the proposed framework provides significant improvement over state-of-the-art methods across a wide range of sparsity and noise levels.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • New Closed-Form Joint Localization and Synchronization Using Sequential
           One-Way TOAs

    • Free pre-print version: Loading...

      Authors: Ningyan Guo;Sihao Zhao;Xiao-Ping Zhang;Zheng Yao;Xiaowei Cui;Mingquan Lu;
      Pages: 2078 - 2092
      Abstract: It is an essential technique for the moving user nodes (UNs) with clock offset and clock skew to resolve the joint localization and synchronization (JLAS) problem. Existing iterative maximum likelihood methods using sequential one-way time-of-arrival (TOA) measurements from the anchor nodes’ (AN) broadcast signals require a good initial guess and have a computational complexity that grows with the number of iterations, given the size of the problem. In this paper, we propose a new closed-form JLAS approach, namely CFJLAS, which achieves the asymptotically optimal solution in one shot without initialization when the noise is small, and has a low computational complexity. After squaring and differencing the sequential TOA measurement equations, we devise two intermediate variables to reparameterize the non-linear problem, and convert it to a simpler one of solving two simultaneous quadratic equations. We then solve the equations analytically to obtain a raw closed-form JLAS estimation. Finally, we apply a weighted least squares (WLS) step to optimize the estimation. We derive the Cramér-Rao lower bound (CRLB), analyze the estimation error, and show that the estimation accuracy of the CFJLAS reaches the CRLB under the small noise condition. The complexity of the new CFJLAS is only determined by the size of the problem, unlike the conventional iterative method, whose complexity is additionally multiplied by the number of iterations. Simulations in a 2D scene verify that the estimation accuracies of the new CFJLAS method all reach the CRLB under the small noise condition. Compared with the conventional iterative method, the proposed new CFJLAS method does not require initialization, obtains the optimal solution under the small noise condition, and has a low computational complexity.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Signal Reconstruction From Quantized Noisy Samples of the Discrete Fourier
           Transform

    • Free pre-print version: Loading...

      Authors: Mohak Goyal;Animesh Kumar;
      Pages: 2093 - 2104
      Abstract: In this paper, we present two variations of an algorithm for signal reconstruction from one-bit or two-bit noisy observations of the discrete Fourier transform (DFT). The one-bit observations of the DFT correspond to the sign of its real part, whereas, the two-bit observations of the DFT correspond to the signs of both its real and imaginary parts. We focus on images for analysis and simulations, thus using the sign of the 2D-DFT. This choice of the class of signals is inspired by previous works on this problem. For our algorithm, we show that the expected mean squared error (MSE) in signal reconstruction is asymptotically proportional to the inverse of the sampling rate. The samples are affected by additive zero-mean noise of a known distribution. We solve this signal estimation problem by designing an algorithm that uses contraction mapping, based on the Banach fixed point theorem. Numerical tests with four benchmark images are provided to show the effectiveness of our algorithm. Various metrics for image reconstruction quality assessment such as PSNR, SSIM, ESSIM, and MS-SSIM are employed. On all four benchmark images, our algorithm outperforms the state-of-the-art in all of these metrics by a significant margin.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Mixed Near-Field and Far-Field Localization and Array Calibration With
           Partly Calibrated Arrays

    • Free pre-print version: Loading...

      Authors: Jin He;Ting Shu;Linna Li;Trieu-Kien Truong;
      Pages: 2105 - 2118
      Abstract: The problem of passive localization of mixed near-field (NF) and far-field (FF) source signals in the presence of array gain-phase uncertainties is addressed. A new algorithm is aimed to use partly calibrated nonuniform linear arrays (NLAs), in which only three sensors have been fully-calibrated. Most of the existing algorithms deal with this problem by exploiting uniform linear arrays (ULAs). Moreover, they assume a simplified source-array model, in which the propagation magnitude scaling is completely neglected and the spatial phase difference is approximated by Taylor’s polynomial. As an opposite, the proposed algorithm is employed to accommodate a more general situation: the exact spatial geometries and nonuniform linear arrays. In the proposed algorithm, three cumulant matrices are firstly defined to construct two matrix pencils. Unambiguous range and angle parameter estimates of the NF sources are then obtained from the generalized eigenvalues of the two defined matrix pencils. After that, these estimates are utilized to calibrate array gain-phase errors. Finally, a spectrum-MUSIC like approach is applied to accomplish the angle estimation for the FF sources. The new algorithm is shown to be readily simple and effective and will be verified both mathematically and numerically.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Zeroth and First Order Stochastic Frank-Wolfe Algorithms for Constrained
           Optimization

    • Free pre-print version: Loading...

      Authors: Zeeshan Akhtar;Ketan Rajawat;
      Pages: 2119 - 2135
      Abstract: This paper considers stochastic convex optimization problems with two sets of constraints: (a) deterministic constraints on the domain of the optimization variable, which are difficult to project onto; and (b) deterministic or stochastic constraints that admit efficient projection. Problems of this form arise frequently in the context of semidefinite programming as well as when various NP-hard problems are solved approximately via semidefinite relaxation. Since projection onto the first set of constraints is difficult, it becomes necessary to explore projection-free algorithms, such as the stochastic Frank-Wolfe (FW) algorithm. On the other hand, the second set of constraints cannot be handled in the same way, and must be incorporated as an indicator function within the objective function, thereby complicating the application of FW methods. Similar problems have been studied before; however, they suffer from slow convergence rates. This work, equipped with momentum based gradient tracking technique, guarantees fast convergence rates on par with the best-known rates for problems without the second set of constraints. Zeroth-order variants of the proposed algorithms are also developed and again improve upon the state-of-the-art rate results. We further propose the novel trimmed FW variants that enjoy the same convergence rates as their classical counterparts, but are empirically shown to require significantly fewer calls to the linear minimization oracle speeding up the overall algorithm. The efficacy of the proposed algorithms is tested on relevant applications of sparse matrix estimation, clustering via semidefinite relaxation, and uniform sparsest cut problem.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Grassmannian Optimization for Online Tensor Completion and Tracking With
           the t-SVD

    • Free pre-print version: Loading...

      Authors: Kyle Gilman;Davoud Ataee Tarzanagh;Laura Balzano;
      Pages: 2152 - 2167
      Abstract: We propose a new fast streaming algorithm for the tensor completion problem of imputing missing entries of a low-tubal-rank tensor using the tensor singular value decomposition (t-SVD) algebraic framework. We show the t-SVD is a specialization of the well-studied block-term decomposition for third-order tensors, and we present an algorithm under this model that can track changing free submodules from incomplete streaming 2-D data. The proposed algorithm uses principles from incremental gradient descent on the Grassmann manifold of subspaces to solve the tensor completion problem with linear complexity and constant memory in the number of time samples. We provide a local expected linear convergence result for our algorithm. Our empirical results are competitive in accuracy but much faster in compute time than state-of-the-art tensor completion algorithms on real applications to recover temporal chemo-sensing and MRI data under limited sampling.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Multiple Support Recovery Using Very Few Measurements Per Sample

    • Free pre-print version: Loading...

      Authors: Lekshmi Ramesh;Chandra R. Murthy;Himanshu Tyagi;
      Pages: 2193 - 2206
      Abstract: In the problem of multiple support recovery, we are given access to linear measurements of multiple sparse samples in ${mathbb {R}}^{d}$. These samples can be partitioned into $ell$ groups, with samples having the same support belonging to the same group. For a given budget of $m$ measurements per sample, the goal is to recover the $ell$ underlying supports, in the absence of the knowledge of group labels. We study this problem with a focus on the measurement-constrained regime where $m$ is smaller than the support size $k$ of each sample. We design a two-step procedure that estimates the union of the underlying supports first, and then uses a spectral algorithm to estimate the individual supports. Our proposed estimator can recover the supports with $m< k$ measurements per sample, from $tilde{O}(k^{4}ell ^{4}/m^{4})$ samples. Our guarantees hold for a general, generative model assumption on the samples and measurement matrices. We also provide results from experiments conducted on synthetic data and on the MNIST dataset.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Bayesian Estimation of Graph Signals

    • Free pre-print version: Loading...

      Authors: Ariel Kroizer;Tirza Routtenberg;Yonina C. Eldar;
      Pages: 2207 - 2223
      Abstract: We consider the problem of recovering random graph signals from nonlinear measurements. For this setting, closed-form Bayesian estimators are usually intractable and even numerical evaluation may be difficult to compute for large networks. In this paper, we propose a graph signal processing (GSP) framework for random graph signal recovery that utilizes information on the structure behind the data. First, we develop the GSP-linear minimum mean-squared-error (GSP-LMMSE) estimator, which minimizes the mean-squared-error (MSE) among estimators that are represented as an output of a graph filter. The GSP-LMMSE estimator is based on diagonal covariance matrices in the graph frequency domain, and thus, has reduced complexity compared with the LMMSE estimator. This property is especially important when using the sample-mean estimators that are based on a training dataset. We then state conditions under which the low-complexity GSP-LMMSE estimator coincides with the optimal LMMSE estimator. Next, we develop an approximate parametrization of the GSP-LMMSE estimator by graph filters. We present three implementations of the parametric GSP-LMMSE estimator for typical graph filters. These parametric graph filters are more robust to outliers and to network topology changes. In our simulations, we evaluate the performance of the proposed GSP-LMMSE estimators for the problem of state estimation in power systems, which can be interpreted as a graph signal recovery task. We show that the proposed sample-GSP estimators outperform the sample-LMMSE estimator for a limited training dataset and that the parametric GSP-LMMSE estimators are more robust to topology changes in the form of adding/removing vertices/edges.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Infinite Switching Dynamic Probabilistic Network With Bayesian
           Nonparametric Learning

    • Free pre-print version: Loading...

      Authors: Wenchao Chen;Bo Chen;Yicheng Liu;Chaojie Wang;Xiaojun Peng;Hongwei Liu;Mingyuan Zhou;
      Pages: 2224 - 2238
      Abstract: To model sequentially observed multivariate nonstationary count data, we propose a switching Poisson-gamma dynamical systems (SPGDS), a dynamic probabilistic network with switching mechanism. Different from previous models, SPGDS assigns its latent variables into mixture of gamma distributed parameters to model complex sequences and describe the nonlinear dynamics, meanwhile, capture various temporal dependencies. Moreover, SPGDS can model all discrete and nonnegative real data by linking them to latent counts. To take advantage of Bayesian nonparametrics in handling the unknown number of mixture components, we integrate Dirichlet process (DP) mixture into SPGDS and develop an infinite switching Poisson-gamma dynamical systems (iSPGDS). For efficient and nonparametric inference, we develop a infinite switching recurrent variational inference network, combined with a scalable hybrid stochastic gradient-MCMC and variational inference method, which is scalable to large scale sequences and fast in out-of-sample prediction. Besides, to handle the time-series categorization task, we further propose an supervised attention iSPGDS (attn-iSPGDS), which combines the representation power of iSPGDS, discriminative power of deep neural networks, and selection power of the attention mechanism under a principled probabilistic framework. Experiments on both unsupervised and supervised tasks demonstrate that the proposed model not only has excellent fitting and prediction performance on complex sequences, but also separates different dynamical patterns within them.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
  • Unsupervised Phase Retrieval Using Deep Approximate MMSE Estimation

    • Free pre-print version: Loading...

      Authors: Mingqin Chen;Peikang Lin;Yuhui Quan;Tongyao Pang;Hui Ji;
      Pages: 2239 - 2252
      Abstract: Phase retrieval (PR) is about reconstructing a signal from the magnitude of a number of its complex-valued linear measurements. Recent rapid progress has been made on the development of neural network (NN) based methods for PR. Most of these methods employ pre-trained NNs for modeling target signals, and they require collecting large-scale datasets with ground-truth signals for pre-training, which can be very challenging in many scenarios. There are a few unsupervised learning methods employing untrained NN priors for PR which avoid using external datasets; however, their performance is unsatisfactory compared to pre-trained-NN-based methods. This paper proposes an unsupervised learning method for PR which does not rely on pre-trained NNs while providing state-of-the-art performance. The proposed method trains a randomly-initialized generative NN for signal reconstruction directly on the magnitude measurements of a target signal, which approximates the minimum mean squared error estimator via dropout-based model averaging. Such a model-averaging-based approach provides a better internal prior for the target signal than existing untrained-NN-based methods. The experiments on image reconstruction demonstrate both the advantage of our method over existing unsupervised methods and its competitive performance to pre-trained-NN-based methods.
      PubDate: 2022
      Issue No: Vol. 70 (2022)
       
 
JournalTOCs
School of Mathematical and Computer Sciences
Heriot-Watt University
Edinburgh, EH14 4AS, UK
Email: journaltocs@hw.ac.uk
Tel: +00 44 (0)131 4513762
 


Your IP address: 3.236.50.79
 
Home (Search)
API
About JournalTOCs
News (blog, publications)
JournalTOCs on Twitter   JournalTOCs on Facebook

JournalTOCs © 2009-