for Journals by Title or ISSN
for Articles by Keywords
  Subjects -> MATHEMATICS (Total: 864 journals)
    - APPLIED MATHEMATICS (68 journals)
    - GEOMETRY AND TOPOLOGY (19 journals)
    - MATHEMATICS (643 journals)
    - MATHEMATICS (GENERAL) (40 journals)
    - NUMERICAL ANALYSIS (19 journals)

MATHEMATICS (643 journals)                  1 2 3 4 | Last

Showing 1 - 200 of 538 Journals sorted alphabetically
Abakós     Open Access   (Followers: 3)
Abhandlungen aus dem Mathematischen Seminar der Universitat Hamburg     Hybrid Journal   (Followers: 2)
Academic Voices : A Multidisciplinary Journal     Open Access   (Followers: 2)
Accounting Perspectives     Full-text available via subscription   (Followers: 6)
ACM Transactions on Algorithms (TALG)     Hybrid Journal   (Followers: 16)
ACM Transactions on Computational Logic (TOCL)     Hybrid Journal   (Followers: 4)
ACM Transactions on Mathematical Software (TOMS)     Hybrid Journal   (Followers: 6)
ACS Applied Materials & Interfaces     Full-text available via subscription   (Followers: 21)
Acta Applicandae Mathematicae     Hybrid Journal   (Followers: 1)
Acta Mathematica     Hybrid Journal   (Followers: 10)
Acta Mathematica Hungarica     Hybrid Journal   (Followers: 2)
Acta Mathematica Scientia     Full-text available via subscription   (Followers: 5)
Acta Mathematica Sinica, English Series     Hybrid Journal   (Followers: 5)
Acta Mathematica Vietnamica     Hybrid Journal  
Acta Mathematicae Applicatae Sinica, English Series     Hybrid Journal  
Advanced Science Letters     Full-text available via subscription   (Followers: 4)
Advances in Applied Clifford Algebras     Hybrid Journal   (Followers: 3)
Advances in Calculus of Variations     Hybrid Journal   (Followers: 2)
Advances in Catalysis     Full-text available via subscription   (Followers: 5)
Advances in Complex Systems     Hybrid Journal   (Followers: 7)
Advances in Computational Mathematics     Hybrid Journal   (Followers: 15)
Advances in Decision Sciences     Open Access   (Followers: 4)
Advances in Difference Equations     Open Access   (Followers: 1)
Advances in Fixed Point Theory     Open Access   (Followers: 5)
Advances in Geosciences (ADGEO)     Open Access   (Followers: 9)
Advances in Linear Algebra & Matrix Theory     Open Access   (Followers: 1)
Advances in Materials Sciences     Open Access   (Followers: 15)
Advances in Mathematical Physics     Open Access   (Followers: 6)
Advances in Mathematics     Full-text available via subscription   (Followers: 10)
Advances in Numerical Analysis     Open Access   (Followers: 3)
Advances in Operations Research     Open Access   (Followers: 11)
Advances in Porous Media     Full-text available via subscription   (Followers: 4)
Advances in Pure and Applied Mathematics     Hybrid Journal   (Followers: 5)
Advances in Pure Mathematics     Open Access   (Followers: 4)
Advances in Science and Research (ASR)     Open Access   (Followers: 6)
Aequationes Mathematicae     Hybrid Journal   (Followers: 2)
African Journal of Educational Studies in Mathematics and Sciences     Full-text available via subscription   (Followers: 5)
African Journal of Mathematics and Computer Science Research     Open Access   (Followers: 4)
Afrika Matematika     Hybrid Journal   (Followers: 1)
Air, Soil & Water Research     Open Access   (Followers: 7)
AKSIOMA Journal of Mathematics Education     Open Access   (Followers: 1)
Algebra and Logic     Hybrid Journal   (Followers: 2)
Algebra Colloquium     Hybrid Journal   (Followers: 4)
Algebra Universalis     Hybrid Journal   (Followers: 2)
Algorithmic Operations Research     Full-text available via subscription   (Followers: 5)
Algorithms     Open Access   (Followers: 9)
Algorithms Research     Open Access  
American Journal of Biostatistics     Open Access   (Followers: 9)
American Journal of Computational and Applied Mathematics     Open Access   (Followers: 3)
American Journal of Mathematical Analysis     Open Access  
American Journal of Mathematics     Full-text available via subscription   (Followers: 7)
American Journal of Operations Research     Open Access   (Followers: 5)
American Mathematical Monthly     Full-text available via subscription   (Followers: 6)
An International Journal of Optimization and Control: Theories & Applications     Open Access   (Followers: 7)
Analele Universitatii Ovidius Constanta - Seria Matematica     Open Access   (Followers: 1)
Analysis     Hybrid Journal   (Followers: 2)
Analysis and Applications     Hybrid Journal   (Followers: 1)
Analysis and Mathematical Physics     Hybrid Journal   (Followers: 4)
Analysis Mathematica     Full-text available via subscription  
Annales Mathematicae Silesianae     Open Access  
Annales mathématiques du Québec     Hybrid Journal   (Followers: 4)
Annales UMCS, Mathematica     Open Access   (Followers: 1)
Annales Universitatis Paedagogicae Cracoviensis. Studia Mathematica     Open Access  
Annali di Matematica Pura ed Applicata     Hybrid Journal   (Followers: 1)
Annals of Combinatorics     Hybrid Journal   (Followers: 3)
Annals of Data Science     Hybrid Journal   (Followers: 8)
Annals of Discrete Mathematics     Full-text available via subscription   (Followers: 6)
Annals of Mathematics     Full-text available via subscription  
Annals of Mathematics and Artificial Intelligence     Hybrid Journal   (Followers: 6)
Annals of Pure and Applied Logic     Open Access   (Followers: 2)
Annals of the Alexandru Ioan Cuza University - Mathematics     Open Access  
Annals of the Institute of Statistical Mathematics     Hybrid Journal   (Followers: 1)
Annals of West University of Timisoara - Mathematics     Open Access  
Annuaire du Collège de France     Open Access   (Followers: 5)
Applicable Algebra in Engineering, Communication and Computing     Hybrid Journal   (Followers: 2)
Applications of Mathematics     Hybrid Journal   (Followers: 1)
Applied Categorical Structures     Hybrid Journal   (Followers: 2)
Applied Computational Intelligence and Soft Computing     Open Access   (Followers: 12)
Applied Mathematics     Open Access   (Followers: 3)
Applied Mathematics     Open Access   (Followers: 4)
Applied Mathematics & Optimization     Hybrid Journal   (Followers: 4)
Applied Mathematics - A Journal of Chinese Universities     Hybrid Journal  
Applied Mathematics Letters     Full-text available via subscription   (Followers: 1)
Applied Mathematics Research eXpress     Hybrid Journal   (Followers: 1)
Applied Numerical Analysis & Computational Mathematics     Hybrid Journal   (Followers: 5)
Applied Numerical Mathematics     Hybrid Journal   (Followers: 5)
Applied Spatial Analysis and Policy     Hybrid Journal   (Followers: 4)
Arab Journal of Mathematical Sciences     Open Access   (Followers: 2)
Arabian Journal of Mathematics     Open Access   (Followers: 2)
Archive for Mathematical Logic     Hybrid Journal   (Followers: 1)
Archive of Applied Mechanics     Hybrid Journal   (Followers: 4)
Archive of Numerical Software     Open Access  
Archives of Computational Methods in Engineering     Hybrid Journal   (Followers: 4)
Arkiv för Matematik     Hybrid Journal   (Followers: 1)
Arnold Mathematical Journal     Hybrid Journal   (Followers: 1)
Artificial Satellites : The Journal of Space Research Centre of Polish Academy of Sciences     Open Access   (Followers: 17)
Asia-Pacific Journal of Operational Research     Hybrid Journal   (Followers: 3)
Asian Journal of Algebra     Open Access   (Followers: 1)
Asian Journal of Current Engineering & Maths     Open Access  
Asian-European Journal of Mathematics     Hybrid Journal   (Followers: 2)
Australian Mathematics Teacher, The     Full-text available via subscription   (Followers: 6)
Australian Primary Mathematics Classroom     Full-text available via subscription   (Followers: 1)
Australian Senior Mathematics Journal     Full-text available via subscription   (Followers: 1)
Automatic Documentation and Mathematical Linguistics     Hybrid Journal   (Followers: 5)
Axioms     Open Access  
Baltic International Yearbook of Cognition, Logic and Communication     Open Access  
Basin Research     Hybrid Journal   (Followers: 3)
BIBECHANA     Open Access  
BIT Numerical Mathematics     Hybrid Journal  
BoEM - Boletim online de Educação Matemática     Open Access  
Boletim Cearense de Educação e História da Matemática     Open Access  
Boletim de Educação Matemática     Open Access  
Boletín de la Sociedad Matemática Mexicana     Hybrid Journal  
Bollettino dell'Unione Matematica Italiana     Full-text available via subscription   (Followers: 1)
British Journal of Mathematical and Statistical Psychology     Full-text available via subscription   (Followers: 19)
Bruno Pini Mathematical Analysis Seminar     Open Access  
Buletinul Academiei de Stiinte a Republicii Moldova. Matematica     Open Access   (Followers: 5)
Bulletin des Sciences Mathamatiques     Full-text available via subscription   (Followers: 4)
Bulletin of Dnipropetrovsk University. Series : Communications in Mathematical Modeling and Differential Equations Theory     Open Access   (Followers: 1)
Bulletin of Mathematical Sciences     Open Access   (Followers: 2)
Bulletin of the Brazilian Mathematical Society, New Series     Hybrid Journal  
Bulletin of the London Mathematical Society     Hybrid Journal   (Followers: 3)
Bulletin of the Malaysian Mathematical Sciences Society     Hybrid Journal  
Calculus of Variations and Partial Differential Equations     Hybrid Journal  
Canadian Journal of Science, Mathematics and Technology Education     Hybrid Journal   (Followers: 18)
Carpathian Mathematical Publications     Open Access   (Followers: 1)
Catalysis in Industry     Hybrid Journal   (Followers: 1)
CAUCHY     Open Access   (Followers: 1)
CEAS Space Journal     Hybrid Journal  
CHANCE     Hybrid Journal   (Followers: 5)
Chaos, Solitons & Fractals     Hybrid Journal   (Followers: 3)
ChemSusChem     Hybrid Journal   (Followers: 7)
Chinese Annals of Mathematics, Series B     Hybrid Journal  
Chinese Journal of Catalysis     Full-text available via subscription   (Followers: 2)
Chinese Journal of Mathematics     Open Access  
Clean Air Journal     Full-text available via subscription   (Followers: 2)
Cogent Mathematics     Open Access   (Followers: 2)
Cognitive Computation     Hybrid Journal   (Followers: 4)
Collectanea Mathematica     Hybrid Journal  
College Mathematics Journal     Full-text available via subscription   (Followers: 1)
COMBINATORICA     Hybrid Journal  
Combustion Theory and Modelling     Hybrid Journal   (Followers: 13)
Commentarii Mathematici Helvetici     Hybrid Journal   (Followers: 1)
Communications in Contemporary Mathematics     Hybrid Journal  
Communications in Mathematical Physics     Hybrid Journal   (Followers: 1)
Communications On Pure & Applied Mathematics     Hybrid Journal   (Followers: 3)
Complex Analysis and its Synergies     Open Access   (Followers: 2)
Complex Variables and Elliptic Equations: An International Journal     Hybrid Journal  
Complexus     Full-text available via subscription  
Composite Materials Series     Full-text available via subscription   (Followers: 9)
Comptes Rendus Mathematique     Full-text available via subscription   (Followers: 1)
Computational and Applied Mathematics     Hybrid Journal   (Followers: 2)
Computational and Mathematical Methods in Medicine     Open Access   (Followers: 2)
Computational and Mathematical Organization Theory     Hybrid Journal   (Followers: 2)
Computational Complexity     Hybrid Journal   (Followers: 4)
Computational Mathematics and Modeling     Hybrid Journal   (Followers: 8)
Computational Mechanics     Hybrid Journal   (Followers: 4)
Computational Methods and Function Theory     Hybrid Journal  
Computational Optimization and Applications     Hybrid Journal   (Followers: 7)
Computers & Mathematics with Applications     Full-text available via subscription   (Followers: 5)
Concrete Operators     Open Access   (Followers: 4)
Confluentes Mathematici     Hybrid Journal  
COSMOS     Hybrid Journal  
Cryptography and Communications     Hybrid Journal   (Followers: 12)
Cuadernos de Investigación y Formación en Educación Matemática     Open Access  
Cubo. A Mathematical Journal     Open Access  
Czechoslovak Mathematical Journal     Hybrid Journal   (Followers: 1)
Demographic Research     Open Access   (Followers: 11)
Demonstratio Mathematica     Open Access  
Dependence Modeling     Open Access  
Design Journal : An International Journal for All Aspects of Design     Hybrid Journal   (Followers: 28)
Developments in Clay Science     Full-text available via subscription   (Followers: 1)
Developments in Mineral Processing     Full-text available via subscription   (Followers: 3)
Dhaka University Journal of Science     Open Access  
Differential Equations and Dynamical Systems     Hybrid Journal   (Followers: 2)
Discrete Mathematics     Hybrid Journal   (Followers: 7)
Discrete Mathematics & Theoretical Computer Science     Open Access  
Discrete Mathematics, Algorithms and Applications     Hybrid Journal   (Followers: 2)
Discussiones Mathematicae Graph Theory     Open Access   (Followers: 1)
Doklady Mathematics     Hybrid Journal  
Duke Mathematical Journal     Full-text available via subscription   (Followers: 1)
Edited Series on Advances in Nonlinear Science and Complexity     Full-text available via subscription  
Electronic Journal of Graph Theory and Applications     Open Access   (Followers: 2)
Electronic Notes in Discrete Mathematics     Full-text available via subscription   (Followers: 2)
Elemente der Mathematik     Full-text available via subscription   (Followers: 3)
Energy for Sustainable Development     Hybrid Journal   (Followers: 9)
Enseñanza de las Ciencias : Revista de Investigación y Experiencias Didácticas     Open Access  
Ensino da Matemática em Debate     Open Access  
Entropy     Open Access   (Followers: 4)
ESAIM: Control Optimisation and Calculus of Variations     Full-text available via subscription   (Followers: 1)
European Journal of Combinatorics     Full-text available via subscription   (Followers: 4)
European Journal of Mathematics     Hybrid Journal   (Followers: 1)
European Scientific Journal     Open Access   (Followers: 2)
Experimental Mathematics     Hybrid Journal   (Followers: 3)
Expositiones Mathematicae     Hybrid Journal   (Followers: 2)
Facta Universitatis, Series : Mathematics and Informatics     Open Access  
Fasciculi Mathematici     Open Access  
Finite Fields and Their Applications     Full-text available via subscription   (Followers: 4)
Fixed Point Theory and Applications     Open Access   (Followers: 1)
Formalized Mathematics     Open Access   (Followers: 2)

        1 2 3 4 | Last

Journal Cover Cognitive Computation
  [SJR: 0.692]   [H-I: 19]   [4 followers]  Follow
   Hybrid Journal Hybrid journal (It can contain Open Access articles)
   ISSN (Print) 1866-9964 - ISSN (Online) 1866-9956
   Published by Springer-Verlag Homepage  [2335 journals]
  • Semi-supervised Learning for Affective Common-Sense Reasoning
    • Authors: Luca Oneto; Federica Bisio; Erik Cambria; Davide Anguita
      Pages: 18 - 42
      Abstract: Background Big social data analysis is the area of research focusing on collecting, examining, and processing large multi-modal and multi-source datasets in order to discover patterns/correlations and extract information from the Social Web. This is usually accomplished through the use of supervised and unsupervised machine learning algorithms that learn from the available data. However, these are usually highly computationally expensive, either in the training or in the prediction phase, as they are often not able to handle current data volumes. Parallel approaches have been proposed in order to boost processing speeds, but this clearly requires technologies that support distributed computations. Methods Extreme learning machines (ELMs) are an emerging learning paradigm, presenting an efficient unified solution to generalized feed-forward neural networks. ELM offers significant advantages such as fast learning speed, ease of implementation, and minimal human intervention. However, ELM cannot be easily parallelized, due to the presence of a pseudo-inverse calculation. Therefore, this paper aims to find a reliable method to realize a parallel implementation of ELM that can be applied to large datasets typical of Big Data problems with the employment of the most recent technology for parallel in-memory computation, i.e., Spark, designed to efficiently deal with iterative procedures that recursively perform operations over the same data. Moreover, this paper shows how to take advantage of the most recent advances in statistical learning theory (SLT) in order to address the issue of selecting ELM hyperparameters that give the best generalization performance. This involves assessing the performance of such algorithms (i.e., resampling methods and in-sample methods) by exploiting the most recent results in SLT and adapting them to the Big Data framework. The proposed approach has been tested on two affective analogical reasoning datasets. Affective analogical reasoning can be defined as the intrinsically human capacity to interpret the cognitive and affective information associated with natural language. In particular, we employed two benchmarks, each one composed by 21,743 common-sense concepts; each concept is represented according to two models of a semantic network in which common-sense concepts are linked to a hierarchy of affective domain labels. Results The labeled data have been split into two sets: The first 20,000 samples have been used for building the model with the ELM with the different SLT strategies, while the rest of the labeled samples, numbering 1743, have been kept apart as reference set in order to test the performance of the learned model. The splitting process has been repeated 30 times in order to obtain statistically relevant results. We ran the experiments through the use of the Google Cloud Platform, in particular, the Google Compute Engine. We employed the Google Compute Engine Platform with NM = 4 machines with two cores and 1.8 GB of RAM (machine type n1-highcpu-2) and an HDD of 30 GB equipped with Spark. Results on the affective dataset both show the effectiveness of the proposed parallel approach and underline the most suitable SLT strategies for the specific Big Data problem. Conclusion In this paper we showed how to build an ELM model with a novel scalable approach and to carefully assess the performance, with the use of the most recent results from SLT, for a sentiment analysis problem. Thanks to recent technologies and methods, the computational requirements of these methods have been improved to allow for the scaling to large datasets, which are typical of Big Data applications.
      PubDate: 2017-02-01
      DOI: 10.1007/s12559-016-9433-5
      Issue No: Vol. 9, No. 1 (2017)
  • A Digital Communication Analysis of Gene Expression of Proteins in
           Biological Systems: A Layered Network Model View
    • Authors: Yesenia Cevallos; Lorena Molina; Alex Santillán; Floriano De Rango; Ahmad Rushdi; Jesús B. Alonso
      Pages: 43 - 67
      Abstract: Background/Introduction Biological communication is a core component of biological systems, mainly presented in the form of evolution, transmitting information from a generation to the next. Unfortunately, biological systems also include other components and functionalities that would cause unwanted information processing and/or communication problems that manifest as diseases. Methods On the other hand, general communication systems, e.g. digital communications, have been well developed and analysed to yield accuracy, high performance, and efficiency. Therefore, we extend the theories of digital communication systems to analyse biological communications. However, in order to accurately model biological communication as digital ones, an analysis of the analogies between both systems is essential. In this work, we propose a novel stacked-layer network model that presents gene expression (i.e. the process by which the information carried by deoxyribonucleic acid or DNA is transformed into the appropriate proteins) and the role of the Golgi apparatus in transmitting these proteins to a target organ. This is analogous to the transmit process in digital communications where a transmitting device in some network would send digital information to a destination/receiver device in another network through a router. Results The proposed stacked-layer network model exploits key networks’ theories and applies them into the broad field genomic analysis, which in turn can impact our understanding and use of medical methods. For example, it would be useful in detecting a target site (e.g. tumour cells) for drug therapy, improving the targeting accuracy (addressing), and reducing side effects in patients from health and socio-economic perspectives. Conclusions Besides improving our understanding of biological communication systems, the proposed model unleashes the true duality between digital and biological communication systems. Therefore, it could be deployed into leveraging the advantages and efficiencies of biological systems into digital communication systems as well and to further develop efficient models that would overcome the disadvantages of either system.
      PubDate: 2017-02-01
      DOI: 10.1007/s12559-016-9434-4
      Issue No: Vol. 9, No. 1 (2017)
  • H-MRST: A Novel Framework For Supporting Probability Degree Range Query
           Using Extreme Learning Machine
    • Authors: Bin Wang; Rui Zhu; Shiying Luo; Xiaochun Yang; Guoren Wang
      Pages: 68 - 80
      Abstract: Background/Introduction Data classification is an important application in the domain of cognitive computation, which has various applications. In this paper, we use classification techniques to solve some key issues in answering range query over probabilistic data. The key of answering this query is to store the feature of each uncertain object in a lightweight structure and use these structures for pruning/validating. However, in these works, the costly integral calculation has to be carried out when dealing with objects that cannot be pruned/validated, and some of the structure construction algorithms are not general. Methods In this paper, we employ ELM, a popular classification technique, to tackle the above issues. Our proposed methods are as follows: We firstly propose a new query called PDR (short for probabilistic degree range) query to substitute the traditional prob-range query, which helps us avoid the costly integral calculation. We propose an ELM-based “adapter” to construct the lightweight structure for uncertain data in a more general manner. We design the GO-ELM algorithm for answering PDR query. It first avoids most of the integral calculation via using a group of bit vector-based filter. In addition, we propose an ELM-based classifier, which is designed to further avoid integral operations. Results From the experiment results, we find that: (1) our ELM-based adapter is superior compared with both SVM-based and DNN-based adapter due to its better training efficiency and classification efficiency as well; (2) the performance of H-MRST is better than that of U-tree and UD-tree; and (3) ELM-filter could effectively avoid integral calculation. Conclusions This paper studies the problem of PDR query over uncertain data. We firstly define PDR query and propose a general scheme to handle uncertain object if its PDF is discrete. We then design GO-ELM algorithm for answering PDR query. Our experiments faithfully demonstrated the efficiency of our indexing techniques.
      PubDate: 2017-02-01
      DOI: 10.1007/s12559-016-9435-3
      Issue No: Vol. 9, No. 1 (2017)
  • Learning Tone Mapping Function for Dehazing
    • Authors: Xuhang Lian; Yanwei Pang; Yuqing He; Xuelong Li; Aiping Yang
      Pages: 95 - 114
      PubDate: 2017-02-01
      DOI: 10.1007/s12559-016-9437-1
      Issue No: Vol. 9, No. 1 (2017)
  • A Semi-Supervised Predictive Sparse Decomposition Based on Task-Driven
           Dictionary Learning
    • Authors: Le Lv; Dongbin Zhao; Qingqiong Deng
      Pages: 115 - 124
      Abstract: In feature learning field, many methods are inspired by advances in neuroscience. Among them, neural network and sparse coding have been broadly studied. Predictive sparse decomposition (PSD) is a practical variant of these two methods. It trains a neural network to estimate the sparse codes. After training, the neural network is fine-tuned to achieve higher performance on object recognition tasks. It is widely believed that introducing discriminative information can make the features more useful for classification task. Hence, in this work, we propose applying the task-driven dictionary learning framework to the PSD and demonstrate that this new model can be optimized by the stochastic gradient descent (SGD) algorithm. Before our work, the semi-supervised auto-encoder framework has already been proposed to guide neural network to extract discriminative representations. But it does not improve the classification performance of neural network. In the experiments, we compare the proposed method with the semi-supervised auto-encoder method. The performance of PSD is used as the baseline for these two methods. On the MNIST and USPS datasets, our method can generate more discriminative and predictable sparse codes than other methods. Furthermore, the recognition accuracy of neural network can be improved.
      PubDate: 2017-02-01
      DOI: 10.1007/s12559-016-9438-0
      Issue No: Vol. 9, No. 1 (2017)
  • Semi-supervised Echo State Networks for Audio Classification
    • Authors: Simone Scardapane; Aurelio Uncini
      Pages: 125 - 135
      Abstract: Echo state networks (ESNs), belonging to the wider family of reservoir computing methods, are a powerful tool for the analysis of dynamic data. In an ESN, the input signal is fed to a fixed (possibly large) pool of interconnected neurons, whose state is then read by an adaptable layer to provide the output. This last layer is generally trained via a regularized linear least-squares procedure. In this paper, we consider the more complex problem of training an ESN for classification problems in a semi-supervised setting, wherein only a part of the input sequences are effectively labeled with the desired response. To solve the problem, we combine the standard ESN with a semi-supervised support vector machine (S3VM) for training its adaptable connections. Additionally, we propose a novel algorithm for solving the resulting non-convex optimization problem, hinging on a series of successive approximations of the original problem. The resulting procedure is highly customizable and also admits a principled way of parallelizing training over multiple processors/computers. An extensive set of experimental evaluations on audio classification tasks supports the presented semi-supervised ESN as a practical tool for dynamic problems requiring the analysis of partially labeled data.
      PubDate: 2017-02-01
      DOI: 10.1007/s12559-016-9439-z
      Issue No: Vol. 9, No. 1 (2017)
  • Model Based Edge-Preserving and Guided Filter for Real-World Hazy Scenes
           Visibility Restoration
    • Authors: Zi-yang Wang; Jian Luo; Kai-yu Qin; Hou-biao Li; Gun Li
      Abstract: Transmission estimation is the most challenging part for single image haze removal and very sensitive to environment noise. However, most existing single image dehazing algorithms are far from satisfactory in terms of restoring an image’s details and noise removal. To address this issue, an improved haze imaging model with transmission refinement based on dark channel prior is constructed to preserve the edge details and enhance visibility. Then, a fast single image dehazing algorithm called TSGA algorithm is proposed for complex real-world images. A refined transmission map obtained by TGVSH regularity scheme provides more edges and finer details and is less susceptible to noise. Guided filter and adaptive histogram equalization greatly enhance the visibility and color contrast of the scenes and significantly improve the drawback of halo artifacts. A large quantity of comparative experiment results demonstrate that the proposed algorithm simultaneously removes the serious effect of haze and noise, effectively makes the restored images look more natural, and has a lower time complexity. All these make it a good candidate for image segmentation, object recognition, and target tracking in complex real-world weather conditions.
      PubDate: 2017-03-20
      DOI: 10.1007/s12559-017-9458-4
  • Online Training for High-Performance Analogue Readout Layers in Photonic
           Reservoir Computers
    • Authors: Piotr Antonik; Marc Haelterman; Serge Massar
      Abstract: Reservoir computing is a bio-inspired computing paradigm for processing time-dependent signals. The performance of its hardware implementation is comparable to state-of-the-art digital algorithms on a series of benchmark tasks. The major bottleneck of its implementations is the readout layer, based on slow offline post-processing. Few analogue solutions have been proposed, but all suffered from noticeable decrease in performance due to added complexity of the setup. Here, we propose the use of online training to solve these issues. We study the applicability of this method using numerical simulations of an experimentally feasible reservoir computer with an analogue readout layer. We also consider a nonlinear output layer, which would be very difficult to train with traditional methods. We show numerically that online learning allows to circumvent the added complexity of the analogue layer and obtain the same level of performance as with a digital layer. This work paves the way to high-performance fully analogue reservoir computers through the use of online training of the output layers.
      PubDate: 2017-03-11
      DOI: 10.1007/s12559-017-9459-3
  • Neuronal Network and Awareness Measures of Post-Decision Wagering Behavior
           in Detecting Masked Emotional Faces
    • Authors: Remigiusz Szczepanowski; Michał Wierzchoń; Marcin Szulżycki
      Abstract: Awareness can be measured by investigating the patterns of associations between discrimination performance (first-order decisions) and confidence judgments (knowledge). In a typical post-decision wagering (PDW) task, participants judge their performance by wagering on each decision made in a detection task. If participants are aware, they wager advantageously by betting high whenever decisions are correct and low for incorrect decisions. Thus, PDW—like other awareness measures with confidence ratings—quantifies if the knowledge upon which they make their decisions is conscious. The present study proposes a new method of assessing the association between advantageous wagering and awareness in the PDW task with a combination of log-linear (LLM) modeling and neural network simulation to reveal the computational patterns that establish this association. We applied the post-decision wagering measure to a backward masking experiment in which participants made first-order decisions about whether or not a masked emotional face was present, and then used imaginary or real monetary stakes to judge the correctness of their initial decisions. The LLM analysis was then used to examine whether advantageous wagering was aware by testing a hypothesis of partial associations between metacognitive judgments and accuracy of first-order decisions. The LLM outcomes were submitted into a feed-forward neural network. The network served as a general approximator that was trained to learn relationships between input wagers and the output of the corresponding log-linear function. The simulation resulted in a simple network architecture that successfully accounted for wagering behavior. This was a feed-forward network unit consisting of one hidden neuron layer with four inputs and one output. In addition, the study indicated no effect of the monetary incentive cues on wagering strategies, although we observed that only low-wager input weights of the neural network considerably contributed to advantageous wagering.
      PubDate: 2017-03-07
      DOI: 10.1007/s12559-017-9456-6
  • Real-time Audio Processing with a Cascade of Discrete-Time Delay
           Line-Based Reservoir Computers
    • Authors: Lars Keuninckx; Jan Danckaert; Guy Van der Sande
      Abstract: Background: Real-time processing of audio or audio-like signals is a promising research topic for the field of machine learning, with many potential applications in music and communications. We present a cascaded delay line reservoir computer capable of real-time audio processing on standard computing equipment, aimed at black-box system identification of nonlinear audio systems. The cascaded reservoir blocks use two-pole filtered virtual neurons to match their timescales to that of the target signals. The reservoir blocks receive both the global input signal and the target estimate from the previous block (local input). The units in the cascade are trained in a successive manner on a single input output training pair, such that a successively better approximation of the target is reached. A cascade of 5 dual-input reservoir blocks of 100 neurons each is trained to mimic the distortion of a measured guitar amplifier. This cascade outperforms both a single delay reservoir having the same total number of neurons as well as a cascade with only single-input blocks. We show that the presented structure is a viable platform for real-time audio applications on present-day computing hardware. A benefit of this structure is that it works directly from the audio samples as input, avoiding computationally intensive preprocessing.
      PubDate: 2017-03-07
      DOI: 10.1007/s12559-017-9457-5
  • Ensemble-Based Risk Scoring with Extreme Learning Machine for Prediction
           of Adverse Cardiac Events
    • Authors: Nan Liu; Jeffrey Tadashi Sakamoto; Jiuwen Cao; Zhi Xiong Koh; Andrew Fu Wah Ho; Zhiping Lin; Marcus Eng Hock Ong
      Abstract: Accurate prediction of adverse cardiac events for the emergency department (ED) chest pain patients is essential in risk stratification due to the current ambiguity in diagnosing acute coronary syndrome. While most current practices rely on human decision by measuring clinical vital signs, computerized solutions are gaining popularity. We have previously proposed an ensemble-based scoring system (ESS). In this paper, we aim to extend the ESS system using extreme learning machine (ELM), a fast learning algorithm for neural networks. We recruited patients from the ED of Singapore General Hospital, and extracted features such as heart rate variability, 12-lead ECG parameters, and vital signs. We also proposed a novel algorithm called ESS-ELM to predict adverse cardiac events. Different from the original ESS algorithm, ESS-ELM uses the under-sampling technique only in model training. Our proposed method was compared to the original ESS algorithm and several clinical scores in predicting patient outcome. With a cohort of 797 recruited patients, we demonstrated that ESS-ELM outperformed the original ESS algorithm and three established clinical scores, namely HEART, TIMI, and GRACE, in terms of receiver operating characteristic analysis. Furthermore, we have investigated the impact of hidden node number and ensemble size on the predictive performance. ELM has demonstrated the flexibility in its integration with the ESS algorithm. Experiments showed the value of ESS-ELM in prediction of adverse cardiac events. Future works may include the use of new ELM-based learning methods and further validation with a new cohort of patients.
      PubDate: 2017-03-06
      DOI: 10.1007/s12559-017-9455-7
  • Interval-Valued Intuitionistic Fuzzy Power Bonferroni Aggregation
           Operators and Their Application to Group Decision Making
    • Authors: Peide Liu; Honggang Li
      Abstract: The power Bonferroni mean (PBM) operator can take the advantages of power operator and Bonferroni mean operator, which can overcome the influence of the unreasonable attribute values and can also consider the interaction between two attributes. However, it cannot be used to process the interval-valued intuitionistic fuzzy numbers (IVIFNs). It is importantly meaningful to extend the PBM operator to IVIFNs. We extend PBM operator to process IVIFNs and propose some new PBM operators for IVIFNs and apply them to solve the multi-attribute group decision-making (MAGDM) problems. Firstly, the definition, properties, score function, and operational rules of IVIFNs are introduced briefly. Then, the power Bonferroni mean (IVIFPBM) operator, the weighted PBM (IVIFWPBM) operator, the power geometric BM (IVIFPGBM) operator, and the weighted power geometric BM (IVIFWPGBM) operator for IVIFNs are proposed. Furthermore, some deserved properties of them are explored, and several special cases are analyzed. The decision-making methods are developed to deal with the MAGDM problems with the information of the IVIFNs based on the proposed operators, and by an illustrative example, the proposed methods are verified, and their advantages are explained by comparing with the other methods. The proposed methods can effectively solve the MAGDM problems with the IVIFNs, and they can consider the interaction between two attributes and overcome the influence of the unreasonable attribute values.
      PubDate: 2017-03-06
      DOI: 10.1007/s12559-017-9453-9
  • Cross-Linguistic Cognitive Modeling of Verbal Morphology Acquisition
    • Authors: Jesús Oliva; J. Ignacio Serrano; M. Dolores del Castillo; Ángel Iglesias
      Abstract: How children acquire and process inflectional morphology is still an open question. Despite the fact that English past tense acquisition has been studied and modeled in depth, the current approaches do not account for many of the errors made by humans. Moreover, not much work has been done with highly inflected languages, like Spanish. However, the modeling of any linguistic phenomenon in different languages is very important in order to understand the general cognitive processes underlying each particular phenomenon. This paper presents an ACT-R dual-mechanism model that accomplishes the task of acquiring verbal morphology systems from one of the simplest systems (the English one) to one of the most complex systems (the Spanish one), by using a double analogy process of stem and suffix. The model proposed was able to match all types of errors that developing children make (from a sample of them), both in English and Spanish. The models for both languages used very similar parameters. The introduced approach not only shows how children could acquire a highly inflected morphology system in terms of dual-mechanism theories but, given its cross-linguistic character, also sheds light on the possible general processes involved in the acquisition and processing of inflectional morphology.
      PubDate: 2017-03-06
      DOI: 10.1007/s12559-017-9454-8
  • Dolphin Swarm Extreme Learning Machine
    • Authors: Tianqi Wu; Min Yao; Jianhua Yang
      Abstract: As a novel learning algorithm for a single hidden-layer feedforward neural network, the extreme learning machine has attracted much research attention for its fast training speed and good generalization performances. Instead of iteratively tuning the parameters, the extreme machine can be seen as a linear optimization problem by randomly generating the input weights and hidden biases. However, the random determination of the input weights and hidden biases may bring non-optimal parameters, which have a negative impact on the final results or need more hidden nodes for the neural network. To overcome the above drawbacks caused by the non-optimal input weights and hidden biases, we propose a new hybrid learning algorithm named dolphin swarm algorithm extreme learning machine adopting the dolphin swarm algorithm to optimize the input weights and hidden biases efficiently. Each set of input weights and hidden biases is encoded into one vector, namely the dolphin. The dolphins are evaluated by root mean squared error and updated by the four pivotal phases of the dolphin swarm algorithm. Eventually, we will obtain an optimal set of input weights and hidden biases. To evaluate the effectiveness of our method, we compare the proposed algorithm with the standard extreme learning machine and three state-of-the-art methods, which are the particle swarm optimization extreme learning machine, evolutionary extreme learning machine, and self-adaptive evolutionary extreme learning machine, under 13 benchmark datasets obtained from the University of California Irvine Machine Learning Repository. The experimental results demonstrate that the proposed method can achieve superior generalization performances than all the compared algorithms.
      PubDate: 2017-02-27
      DOI: 10.1007/s12559-017-9451-y
  • Extreme Learning Machine for Huge Hypotheses Re-ranking in Statistical
           Machine Translation
    • Authors: Yan Liu; Chi Man Vong; Pak Kin Wong
      Abstract: In statistical machine translation (SMT), a possibly infinite number of translation hypotheses can be decoded from a source sentence, among which re-ranking is applied to sort out the best translation result. Undoubtedly, re-ranking is an essential component of SMT for effective and efficient translation. A novel re-ranking method called Scaled Sorted Classification Re-ranking (SSCR) based on extreme learning machine (ELM) classification and minimum error rate training (MERT) is proposed. SSCR contains four steps: (1) the input features are normalized to the range of 0 to 1; (2) an ELM classification model is constructed for hypothesis ranking; (3) each translation hypothesis is ranked using the ELM classification model; and (4) the highest ranked subset of hypotheses are selected, in which the hypothesis with best predicted score based on MERT (system score) is returned as the final translation result. Compared with the baseline score (lower bound), SSCR with ELM classification can raise the translation quality up to 6.7% in IWSLT 2014 Chinese to English corpus. Compared with the state-of-the-art rank boosting, SSCR has a relatively 7.8% of improvement on BLEU in a larger WMT 2015 English-to-French corpus. Moreover, the training time of the proposed method is about 160 times faster than traditional regression-based re-ranking.
      PubDate: 2017-02-17
      DOI: 10.1007/s12559-017-9452-x
  • CLASS: Collaborative Low-Rank and Sparse Separation for Moving Object
    • Authors: Aihua Zheng; Minghe Xu; Bin Luo; Zhili Zhou; Chenglong Li
      Abstract: Low-rank models have been successfully applied to background modeling and achieved promising results on moving object detection. However, the assumption that moving objects are modelled as sparse outliers limits the performance of these models when the sizes of moving objects are relatively large. Meanwhile, inspired by the visual system of human brain which can cognitively perceive the physical size of the object with different sizes of retina imaging, we propose a novel approach, called Collaborative Low-Rank And Sparse Separation (CLASS), for moving object detection. Given the data matrix that accumulates sequential frames from the input video, CLASS detects the moving objects as sparse outliers against the low-rank structure background while pursuing global appearance consistency for both foreground and background. The sparse and the global appearance consistent constraints are complementary but simultaneously competing, and thus CLASS can detect the moving objects with different sizes effectively. The smoothness constraints of object motion are also introduced in CLASS for further improving the robustness to noises. Moreover, we utilize the edge-preserving filtering method to substantially speed up CLASS without much losing its accuracy. The extensive experiments on both public and newly created video sequences suggest that CLASS achieves superior performance and comparable efficiency against other state-of-the-art approaches.
      PubDate: 2017-02-06
      DOI: 10.1007/s12559-017-9449-5
  • On Global Smooth Path Planning for Mobile Robots using a Novel Multimodal
           Delayed PSO Algorithm
    • Authors: Baoye Song; Zidong Wang; Lei Zou
      Abstract: The planning problem for smooth paths for mobile robots has attracted particular research attention, but the strategy combining the heuristic intelligent optimization algorithm (e.g., particle swarm optimization) with smooth parameter curve (e.g., Bezier curve) for global yet smooth path planning for mobile robots has not been thoroughly discussed because of several difficulties such as the local trapping phenomenon in the searching process. In this paper, a novel multimodal delayed particle swarm optimization (MDPSO) algorithm is developed for the global smooth path planning for mobile robots. By evaluating the evolutionary factor in each iteration, the evolutionary state is classified by equal interval division for the swarm of the particles. Then, the velocity updating model would switch from one mode to another according to the evolutionary state. Furthermore, in order to reduce the occurrence of local trapping phenomenon and expand the search space in the searching process, the so-called multimodal delayed information (which is composed of the local and global delayed best particles selected randomly from the corresponding values in previous iterations) is added into the velocity updating model. A series of simulation experiments are implemented on a standard collection of benchmark functions. The experiment results verify that the comprehensive performance of the developed MDPSO algorithm is superior to other well-known PSO algorithms. Finally, the presented MDPSO algorithm is utilized in the global smooth path planning problem for mobile robots, which further confirms the advantages of the MDPSO algorithm over the traditional genetic algorithm (GA) investigated in previous studies. The multimodal delayed information in the MDPSO reduces the occurrence of local trapping phenomenon and the convergence rate is satisfied at the same time. Based on the testing results on a selection of benchmark functions, the MDPSO’s performance has been shown to be superior to other five well-known PSO algorithms. Successful application of the MDPSO for planning the global smooth path for mobile robots further confirms its excellent performance compared with the some typical existing algorithms.
      PubDate: 2017-01-03
      DOI: 10.1007/s12559-016-9442-4
  • Anatomy of the Mind : a Quick Overview
    • Authors: Ron Sun
      Abstract: The recently published book, “Anatomy of the Mind,” explains psychological (cognitive) mechanisms, processes, and functionalities through a comprehensive computational theory of the human mind—that is, a cognitive architecture. The goal of the work has been to develop a unified framework and then to develop process-based mechanistic understanding of psychological phenomena within the unified framework. In this article, I will provide a quick overview of the work.
      PubDate: 2016-12-27
      DOI: 10.1007/s12559-016-9444-2
  • Human Brain Function in Path Planning: a Task Study
    • Authors: Yeganeh M. Marghi; Farzad Towhidkhah; Shahriar Gharibzadeh
      Abstract: Despite plenty of research being performed in the human movement science, less attention has been paid to the probable method used by the human brain in the higher-level motor planning. The previous studies suggest that the human brain may use a predictive approach to anticipate physical dynamics of the body and the environment to plan a short and collision-free movement trajectory. We propose that the human brain may use a model-based prediction procedure in path planning in which a finite prediction horizon is used to estimate the future state of the body and the environment. A goal-oriented driving task (GDT) in a virtual street was designed to consider the human path planning method in dynamic environments. Two groups of experiments were presented to consider the ability of the human brain in estimation of a dynamic object location and planning a collision-free path. The first group of study includes four GDTs, with different conditions to evaluate how the human planning strategy would change by varying the configuration of the environment. In the second group, the changes of human planning in a visually obscured and blurred situation were considered. The results are in compliance with the theory of using a model-based prediction approach by human brains and indicate that the subjects benefit from a prediction horizon to plan their paths. Our studies provide evidence to introduce possible factors which may be used by the human brain during path planning in dynamic environments.
      PubDate: 2016-12-23
      DOI: 10.1007/s12559-016-9443-3
  • Distance and Aggregation-Based Methodologies for Hesitant Fuzzy Decision
    • Authors: B. Farhadinia; Zeshui Xu
      Abstract: Hesitant fuzzy set (HFS) as an effective tool to reflect human’s hesitancy has received great attention in recent years. The importance weights of possible values in hesitant fuzzy elements (HFEs), which are the basic units of a HFS, have not been taken into account in the existing literature. Thus, the frequently used HFEs cannot deal with the situations where all the possible values are provided by experts with different levels of expertise. Consequently, in this paper, we propose an extension of typical HFS called the ordered weighted hesitant fuzzy set (OWHFS). The basic units of an OWHFS allow the membership of a given element to be defined in terms of several possible values together with their importance weights. Moreover, in order to indicate that the OWHFS has a good performance in decision making, we first present some information measures and several aggregation operators for OWHFSs. Then, we apply them to multi-attribute decision making with ordered weighted hesitant fuzzy information.
      PubDate: 2016-12-16
      DOI: 10.1007/s12559-016-9436-2
School of Mathematical and Computer Sciences
Heriot-Watt University
Edinburgh, EH14 4AS, UK
Tel: +00 44 (0)131 4513762
Fax: +00 44 (0)131 4513327
Home (Search)
Subjects A-Z
Publishers A-Z
Your IP address:
About JournalTOCs
News (blog, publications)
JournalTOCs on Twitter   JournalTOCs on Facebook

JournalTOCs © 2009-2016