for Journals by Title or ISSN
for Articles by Keywords
help
  Subjects -> COMPUTER SCIENCE (Total: 1985 journals)
    - ANIMATION AND SIMULATION (29 journals)
    - ARTIFICIAL INTELLIGENCE (98 journals)
    - AUTOMATION AND ROBOTICS (98 journals)
    - CLOUD COMPUTING AND NETWORKS (63 journals)
    - COMPUTER ARCHITECTURE (9 journals)
    - COMPUTER ENGINEERING (9 journals)
    - COMPUTER GAMES (16 journals)
    - COMPUTER PROGRAMMING (23 journals)
    - COMPUTER SCIENCE (1153 journals)
    - COMPUTER SECURITY (45 journals)
    - DATA BASE MANAGEMENT (13 journals)
    - DATA MINING (32 journals)
    - E-BUSINESS (22 journals)
    - E-LEARNING (27 journals)
    - ELECTRONIC DATA PROCESSING (21 journals)
    - IMAGE AND VIDEO PROCESSING (40 journals)
    - INFORMATION SYSTEMS (104 journals)
    - INTERNET (92 journals)
    - SOCIAL WEB (50 journals)
    - SOFTWARE (33 journals)
    - THEORY OF COMPUTING (8 journals)

COMPUTER SCIENCE (1153 journals)                  1 2 3 4 5 6 | Last

Showing 1 - 200 of 872 Journals sorted alphabetically
3D Printing and Additive Manufacturing     Full-text available via subscription   (Followers: 12)
Abakós     Open Access   (Followers: 3)
Academy of Information and Management Sciences Journal     Full-text available via subscription   (Followers: 67)
ACM Computing Surveys     Hybrid Journal   (Followers: 23)
ACM Journal on Computing and Cultural Heritage     Hybrid Journal   (Followers: 8)
ACM Journal on Emerging Technologies in Computing Systems     Hybrid Journal   (Followers: 13)
ACM Transactions on Accessible Computing (TACCESS)     Hybrid Journal   (Followers: 4)
ACM Transactions on Algorithms (TALG)     Hybrid Journal   (Followers: 16)
ACM Transactions on Applied Perception (TAP)     Hybrid Journal   (Followers: 6)
ACM Transactions on Architecture and Code Optimization (TACO)     Hybrid Journal   (Followers: 9)
ACM Transactions on Autonomous and Adaptive Systems (TAAS)     Hybrid Journal   (Followers: 7)
ACM Transactions on Computation Theory (TOCT)     Hybrid Journal   (Followers: 11)
ACM Transactions on Computational Logic (TOCL)     Hybrid Journal   (Followers: 4)
ACM Transactions on Computer Systems (TOCS)     Hybrid Journal   (Followers: 18)
ACM Transactions on Computer-Human Interaction     Hybrid Journal   (Followers: 12)
ACM Transactions on Computing Education (TOCE)     Hybrid Journal   (Followers: 3)
ACM Transactions on Design Automation of Electronic Systems (TODAES)     Hybrid Journal   (Followers: 1)
ACM Transactions on Economics and Computation     Hybrid Journal  
ACM Transactions on Embedded Computing Systems (TECS)     Hybrid Journal   (Followers: 4)
ACM Transactions on Information Systems (TOIS)     Hybrid Journal   (Followers: 20)
ACM Transactions on Intelligent Systems and Technology (TIST)     Hybrid Journal   (Followers: 9)
ACM Transactions on Interactive Intelligent Systems (TiiS)     Hybrid Journal   (Followers: 4)
ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)     Hybrid Journal   (Followers: 10)
ACM Transactions on Reconfigurable Technology and Systems (TRETS)     Hybrid Journal   (Followers: 7)
ACM Transactions on Sensor Networks (TOSN)     Hybrid Journal   (Followers: 8)
ACM Transactions on Speech and Language Processing (TSLP)     Hybrid Journal   (Followers: 11)
ACM Transactions on Storage     Hybrid Journal  
ACS Applied Materials & Interfaces     Full-text available via subscription   (Followers: 21)
Acta Automatica Sinica     Full-text available via subscription   (Followers: 3)
Acta Universitatis Cibiniensis. Technical Series     Open Access  
Ad Hoc Networks     Hybrid Journal   (Followers: 11)
Adaptive Behavior     Hybrid Journal   (Followers: 11)
Advanced Engineering Materials     Hybrid Journal   (Followers: 26)
Advanced Science Letters     Full-text available via subscription   (Followers: 7)
Advances in Adaptive Data Analysis     Hybrid Journal   (Followers: 8)
Advances in Artificial Intelligence     Open Access   (Followers: 15)
Advances in Artificial Neural Systems     Open Access   (Followers: 4)
Advances in Calculus of Variations     Hybrid Journal   (Followers: 2)
Advances in Catalysis     Full-text available via subscription   (Followers: 5)
Advances in Computational Mathematics     Hybrid Journal   (Followers: 15)
Advances in Computer Science : an International Journal     Open Access   (Followers: 13)
Advances in Computing     Open Access   (Followers: 3)
Advances in Data Analysis and Classification     Hybrid Journal   (Followers: 53)
Advances in Engineering Software     Hybrid Journal   (Followers: 25)
Advances in Geosciences (ADGEO)     Open Access   (Followers: 10)
Advances in Human Factors/Ergonomics     Full-text available via subscription   (Followers: 25)
Advances in Human-Computer Interaction     Open Access   (Followers: 19)
Advances in Materials Sciences     Open Access   (Followers: 16)
Advances in Operations Research     Open Access   (Followers: 11)
Advances in Parallel Computing     Full-text available via subscription   (Followers: 7)
Advances in Porous Media     Full-text available via subscription   (Followers: 4)
Advances in Remote Sensing     Open Access   (Followers: 37)
Advances in Science and Research (ASR)     Open Access   (Followers: 6)
Advances in Technology Innovation     Open Access  
AEU - International Journal of Electronics and Communications     Hybrid Journal   (Followers: 8)
African Journal of Information and Communication     Open Access   (Followers: 6)
African Journal of Mathematics and Computer Science Research     Open Access   (Followers: 4)
Air, Soil & Water Research     Open Access   (Followers: 7)
AIS Transactions on Human-Computer Interaction     Open Access   (Followers: 6)
Algebras and Representation Theory     Hybrid Journal   (Followers: 1)
Algorithms     Open Access   (Followers: 10)
American Journal of Computational and Applied Mathematics     Open Access   (Followers: 3)
American Journal of Computational Mathematics     Open Access   (Followers: 4)
American Journal of Information Systems     Open Access   (Followers: 6)
American Journal of Sensor Technology     Open Access   (Followers: 2)
Anais da Academia Brasileira de Ciências     Open Access   (Followers: 2)
Analog Integrated Circuits and Signal Processing     Hybrid Journal   (Followers: 5)
Analysis in Theory and Applications     Hybrid Journal  
Animation Practice, Process & Production     Hybrid Journal   (Followers: 5)
Annals of Combinatorics     Hybrid Journal   (Followers: 3)
Annals of Data Science     Hybrid Journal   (Followers: 8)
Annals of Mathematics and Artificial Intelligence     Hybrid Journal   (Followers: 6)
Annals of Pure and Applied Logic     Open Access   (Followers: 2)
Annals of Software Engineering     Hybrid Journal   (Followers: 12)
Annual Reviews in Control     Hybrid Journal   (Followers: 6)
Anuario Americanista Europeo     Open Access  
Applicable Algebra in Engineering, Communication and Computing     Hybrid Journal   (Followers: 2)
Applied and Computational Harmonic Analysis     Full-text available via subscription   (Followers: 2)
Applied Artificial Intelligence: An International Journal     Hybrid Journal   (Followers: 14)
Applied Categorical Structures     Hybrid Journal   (Followers: 2)
Applied Clinical Informatics     Hybrid Journal   (Followers: 1)
Applied Computational Intelligence and Soft Computing     Open Access   (Followers: 12)
Applied Computer Systems     Open Access   (Followers: 1)
Applied Informatics     Open Access  
Applied Mathematics and Computation     Hybrid Journal   (Followers: 32)
Applied Medical Informatics     Open Access   (Followers: 10)
Applied Numerical Mathematics     Hybrid Journal   (Followers: 5)
Applied Soft Computing     Hybrid Journal   (Followers: 16)
Applied Spatial Analysis and Policy     Hybrid Journal   (Followers: 4)
Architectural Theory Review     Hybrid Journal   (Followers: 3)
Archive of Applied Mechanics     Hybrid Journal   (Followers: 4)
Archive of Numerical Software     Open Access  
Archives and Museum Informatics     Hybrid Journal   (Followers: 123)
Archives of Computational Methods in Engineering     Hybrid Journal   (Followers: 4)
Artifact     Hybrid Journal   (Followers: 2)
Artificial Life     Hybrid Journal   (Followers: 5)
Asia Pacific Journal on Computational Engineering     Open Access  
Asia-Pacific Journal of Information Technology and Multimedia     Open Access   (Followers: 1)
Asian Journal of Computer Science and Information Technology     Open Access  
Asian Journal of Control     Hybrid Journal  
Assembly Automation     Hybrid Journal   (Followers: 2)
at - Automatisierungstechnik     Hybrid Journal   (Followers: 1)
Australian Educational Computing     Open Access  
Automatic Control and Computer Sciences     Hybrid Journal   (Followers: 3)
Automatic Documentation and Mathematical Linguistics     Hybrid Journal   (Followers: 5)
Automatica     Hybrid Journal   (Followers: 9)
Automation in Construction     Hybrid Journal   (Followers: 6)
Autonomous Mental Development, IEEE Transactions on     Hybrid Journal   (Followers: 8)
Basin Research     Hybrid Journal   (Followers: 4)
Behaviour & Information Technology     Hybrid Journal   (Followers: 52)
Bioinformatics     Hybrid Journal   (Followers: 293)
Biomedical Engineering     Hybrid Journal   (Followers: 16)
Biomedical Engineering and Computational Biology     Open Access   (Followers: 13)
Biomedical Engineering, IEEE Reviews in     Full-text available via subscription   (Followers: 17)
Biomedical Engineering, IEEE Transactions on     Hybrid Journal   (Followers: 32)
Briefings in Bioinformatics     Hybrid Journal   (Followers: 45)
British Journal of Educational Technology     Hybrid Journal   (Followers: 119)
Broadcasting, IEEE Transactions on     Hybrid Journal   (Followers: 10)
c't Magazin fuer Computertechnik     Full-text available via subscription   (Followers: 2)
CALCOLO     Hybrid Journal  
Calphad     Hybrid Journal  
Canadian Journal of Electrical and Computer Engineering     Full-text available via subscription   (Followers: 13)
Catalysis in Industry     Hybrid Journal   (Followers: 1)
CEAS Space Journal     Hybrid Journal  
Cell Communication and Signaling     Open Access   (Followers: 1)
Central European Journal of Computer Science     Hybrid Journal   (Followers: 5)
CERN IdeaSquare Journal of Experimental Innovation     Open Access  
Chaos, Solitons & Fractals     Hybrid Journal   (Followers: 3)
Chemometrics and Intelligent Laboratory Systems     Hybrid Journal   (Followers: 15)
ChemSusChem     Hybrid Journal   (Followers: 7)
China Communications     Full-text available via subscription   (Followers: 7)
Chinese Journal of Catalysis     Full-text available via subscription   (Followers: 2)
CIN Computers Informatics Nursing     Full-text available via subscription   (Followers: 12)
Circuits and Systems     Open Access   (Followers: 16)
Clean Air Journal     Full-text available via subscription   (Followers: 2)
CLEI Electronic Journal     Open Access  
Clin-Alert     Hybrid Journal   (Followers: 1)
Cluster Computing     Hybrid Journal   (Followers: 1)
Cognitive Computation     Hybrid Journal   (Followers: 4)
COMBINATORICA     Hybrid Journal  
Combustion Theory and Modelling     Hybrid Journal   (Followers: 13)
Communication Methods and Measures     Hybrid Journal   (Followers: 11)
Communication Theory     Hybrid Journal   (Followers: 19)
Communications Engineer     Hybrid Journal   (Followers: 1)
Communications in Algebra     Hybrid Journal   (Followers: 3)
Communications in Partial Differential Equations     Hybrid Journal   (Followers: 3)
Communications of the ACM     Full-text available via subscription   (Followers: 53)
Communications of the Association for Information Systems     Open Access   (Followers: 18)
COMPEL: The International Journal for Computation and Mathematics in Electrical and Electronic Engineering     Hybrid Journal   (Followers: 3)
Complex & Intelligent Systems     Open Access  
Complex Adaptive Systems Modeling     Open Access  
Complex Analysis and Operator Theory     Hybrid Journal   (Followers: 2)
Complexity     Hybrid Journal   (Followers: 6)
Complexus     Full-text available via subscription  
Composite Materials Series     Full-text available via subscription   (Followers: 9)
Computación y Sistemas     Open Access  
Computation     Open Access  
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 and Structural Biotechnology Journal     Open Access   (Followers: 2)
Computational and Theoretical Chemistry     Hybrid Journal   (Followers: 9)
Computational Astrophysics and Cosmology     Open Access   (Followers: 1)
Computational Biology and Chemistry     Hybrid Journal   (Followers: 12)
Computational Chemistry     Open Access   (Followers: 2)
Computational Cognitive Science     Open Access   (Followers: 1)
Computational Complexity     Hybrid Journal   (Followers: 4)
Computational Condensed Matter     Open Access  
Computational Ecology and Software     Open Access   (Followers: 8)
Computational Economics     Hybrid Journal   (Followers: 9)
Computational Geosciences     Hybrid Journal   (Followers: 13)
Computational Linguistics     Open Access   (Followers: 23)
Computational Management Science     Hybrid Journal  
Computational Mathematics and Modeling     Hybrid Journal   (Followers: 8)
Computational Mechanics     Hybrid Journal   (Followers: 4)
Computational Methods and Function Theory     Hybrid Journal  
Computational Molecular Bioscience     Open Access   (Followers: 2)
Computational Optimization and Applications     Hybrid Journal   (Followers: 7)
Computational Particle Mechanics     Hybrid Journal   (Followers: 1)
Computational Research     Open Access   (Followers: 1)
Computational Science and Discovery     Full-text available via subscription   (Followers: 2)
Computational Science and Techniques     Open Access  
Computational Statistics     Hybrid Journal   (Followers: 13)
Computational Statistics & Data Analysis     Hybrid Journal   (Followers: 28)
Computer     Full-text available via subscription   (Followers: 83)
Computer Aided Surgery     Hybrid Journal   (Followers: 3)
Computer Applications in Engineering Education     Hybrid Journal   (Followers: 6)
Computer Communications     Hybrid Journal   (Followers: 10)
Computer Engineering and Applications Journal     Open Access   (Followers: 5)
Computer Journal     Hybrid Journal   (Followers: 7)
Computer Methods in Applied Mechanics and Engineering     Hybrid Journal   (Followers: 22)
Computer Methods in Biomechanics and Biomedical Engineering     Hybrid Journal   (Followers: 10)
Computer Methods in the Geosciences     Full-text available via subscription   (Followers: 1)
Computer Music Journal     Hybrid Journal   (Followers: 14)
Computer Physics Communications     Hybrid Journal   (Followers: 6)
Computer Science - Research and Development     Hybrid Journal   (Followers: 7)
Computer Science and Engineering     Open Access   (Followers: 17)
Computer Science and Information Technology     Open Access   (Followers: 11)
Computer Science Education     Hybrid Journal   (Followers: 12)
Computer Science Journal     Open Access   (Followers: 20)

        1 2 3 4 5 6 | 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  [2355 journals]
  • Online Training for High-Performance Analogue Readout Layers in Photonic
           Reservoir Computers
    • Authors: Piotr Antonik; Marc Haelterman; Serge Massar
      Pages: 297 - 306
      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: 2017-06-01
      DOI: 10.1007/s12559-017-9459-3
      Issue No: Vol. 9, No. 3 (2017)
       
  • Real-time Audio Processing with a Cascade of Discrete-Time Delay
           Line-Based Reservoir Computers
    • Authors: Lars Keuninckx; Jan Danckaert; Guy Van der Sande
      Pages: 315 - 326
      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: 2017-06-01
      DOI: 10.1007/s12559-017-9457-5
      Issue No: Vol. 9, No. 3 (2017)
       
  • Training Echo State Networks with Regularization Through Dimensionality
           Reduction
    • Authors: Sigurd Løkse; Filippo Maria Bianchi; Robert Jenssen
      Pages: 364 - 378
      Abstract: In this paper, we introduce a new framework to train a class of recurrent neural network, called Echo State Network, to predict real valued time-series and to provide a visualization of the modeled system dynamics. The method consists in projecting the output of the internal layer of the network on a lower dimensional space, before training the output layer to learn the target task. Notably, we enforce a regularization constraint that leads to better generalization capabilities. We evaluate the performances of our approach on several benchmark tests, using different techniques to train the readout of the network, achieving superior predictive performance when using the proposed framework. Finally, we provide an insight on the effectiveness of the implemented mechanics through a visualization of the trajectory in the phase space and relying on the methodologies of nonlinear time-series analysis. By applying our method on well-known chaotic systems, we provide evidence that the lower dimensional embedding retains the dynamical properties of the underlying system better than the full-dimensional internal states of the network.
      PubDate: 2017-06-01
      DOI: 10.1007/s12559-017-9450-z
      Issue No: Vol. 9, No. 3 (2017)
       
  • Lane Boundary Detection Algorithm Based on Vector Fuzzy Connectedness
    • Authors: Lingling Fang; Xianghai Wang
      Abstract: In most actual autonomous guided vehicles (AGV), path finding and navigational control systems are usually implemented using images captured by cameras mounted on the vehicles. This paper presents and discusses a lane boundary detection technique that is necessary for the task of autonomous driving. In this paper, a new method called vector fuzzy connectedness (VFC) is presented to detect and estimate road lane boundaries. First, a preprocessed technique is used to obtain a skeleton image. Based on the result, the curvatures of the left and right lane boundaries are estimated, and the control points are found by the VFC method. Finally, the non-uniform b-spline (NUBS) interpolation method is introduced to construct the road lane boundaries. The proposed VFC method integrates the vector concept and fuzzy connectedness into the lane boundary detection algorithm. As shown in the example results, the proposed method can extract various road lane shapes and types from real road frames even under complex road environments. For navigation tasks, it is necessary to determine the position of the vehicle relative to the road. These results prove that the proposed detection method can assist in a number of actual AGV assistant applications. In the future, some intelligent techniques will be applied to test the AGV system with obstacle avoidance conditions on real world roads.
      PubDate: 2017-07-06
      DOI: 10.1007/s12559-017-9483-3
       
  • A Semi-blind Model with Parameter Identification for Building Temperature
           Estimation
    • Authors: Xing Luo; Xu Zhu; Eng Gee Lim; Yi Huang
      Abstract: An accurate thermal model for building enables the heating system (HS) to work efficiently as well as save energy. Thermal modelling often requires physical parameters of the building, which are difficult to be accurately determined. The aim of this work is to develop an optimal thermal model for better understanding of thermal dynamics with the goal of using this to estimate temperature variation in a few hours ahead within building. Based on the characteristics of thermal motion, a conventional physics-based (PB) model for building temperature estimation is introduced first. Afterwards, in order to refine the model and improve the actual performance, we propose an innovative semi-blind (SB) model based on data-driven approaches. Additionally, the methodologies including self-adaptive algorithms (SAAs) and grey prediction technique (GPT) have been applied in dealing with the integrated parameters estimation (IPE) process to ensure the practicability of the implemented model. The proposed model schema is validated by testing in a laboratory. The results indicate that the proposed approach achieves much higher accuracy in estimating temperature variation than the conventional PB model, with only limited knowledge of the building characteristics. The root mean square deviation (RMSD) of SB model and PB model are 0.18 and 0.43, respectively. According to the results, it can be concluded that the proposed SB model is able to appropriately estimate the internal temperature values and great improvement has been achieved comparing with the original thermal model.
      PubDate: 2017-06-29
      DOI: 10.1007/s12559-017-9486-0
       
  • Semantic Category-Based Classification Using Nonlinear Features and
           Wavelet Coefficients of Brain Signals
    • Authors: Ali Torabi; Fatemeh Zareayan Jahromy; Mohammad Reza Daliri
      Abstract: The problem of object recognition is solved in the brain using different strategies. These strategies are to some extent known to neuroscientists, but researches on this issue are still in progress to understand more accurately the computational, anatomical, and physiological aspects of this fast and accurate capability of the brain. In this paper, we presented a method, based on extracting nonlinearity of signals such as L-Z complexity, fractal dimension, Lyapunov exponents, Hurst exponents, and entropy, to classify single trials into their related semantic category groups with a linear SVM classifier. Furthermore, we proposed to combine nonlinear features mentioned above with wavelet coefficients to improve the classification accuracy. EEG signals were recorded from human subjects according to 10–20 system while performing a “go/no go” object-categorization task. Combining nonlinear features with wavelet coefficients led to a significant enhancement in classification accuracy (73%) relative to wavelet coefficients alone (54%). Feature-selection results showed that a significantly larger proportion of final selected features include nonlinear features (44%) relative to the first ratio of them (14%) to whole features. This ratio enhancement demonstrates the essential role of nonlinear features in the obtained classification accuracy. In addition, C3 channel and Katz fractal dimension were introduced as the most informative channel and the best nonlinear feature, respectively.
      PubDate: 2017-06-23
      DOI: 10.1007/s12559-017-9487-z
       
  • Nature-Inspired Chemical Reaction Optimisation Algorithms
    • Authors: Nazmul Siddique; Hojjat Adeli
      Abstract: Nature-inspired meta-heuristic algorithms have dominated the scientific literature in the areas of machine learning and cognitive computing paradigm in the last three decades. Chemical reaction optimisation (CRO) is a population-based meta-heuristic algorithm based on the principles of chemical reaction. A chemical reaction is seen as a process of transforming the reactants (or molecules) through a sequence of reactions into products. This process of transformation is implemented in the CRO algorithm to solve optimisation problems. This article starts with an overview of the chemical reactions and how it is applied to the optimisation problem. A review of CRO and its variants is presented in the paper. Guidelines from the literature on the effective choice of CRO parameters for solution of optimisation problems are summarised.
      PubDate: 2017-06-17
      DOI: 10.1007/s12559-017-9485-1
       
  • An Efficient Corpus-Based Stemmer
    • Authors: Jasmeet Singh; Vishal Gupta
      Abstract: Word stemming is a linguistic process in which the various inflected word forms are matched to their base form. It is among the basic text pre-processing approaches used in Natural Language Processing and Information Retrieval. Stemming is employed at the text pre-processing stage to solve the issue of vocabulary mismatch or to reduce the size of the word vocabulary, and consequently also the dimensionality of training data for statistical models. In this article, we present a fully unsupervised corpus-based text stemming method which clusters morphologically related words based on lexical knowledge. The proposed method performs cognitive-inspired computing to discover morphologically related words from the corpus without any human intervention or language-specific knowledge. The performance of the proposed method is evaluated in inflection removal (approximating lemmas) and Information Retrieval tasks. The retrieval experiments in four different languages using standard Text Retrieval Conference, Cross-Language Evaluation Forum, and Forum for Information Retrieval Evaluation collections show that the proposed stemming method performs significantly better than no stemming. In the case of highly inflectional languages, Marathi and Hungarian, the improvement in Mean Average Precision is nearly 50% as compared to unstemmed words. Moreover, the proposed unsupervised stemming method outperforms state-of-the-art strong language-independent and rule-based stemming methods in all the languages. Besides Information Retrieval, the proposed stemming method also performs significantly better in inflection removal experiments. The proposed unsupervised language-independent stemming method can be used as a multipurpose tool for various tasks such as the approximation of lemmas, improving retrieval performance or other Natural Language Processing applications.
      PubDate: 2017-06-07
      DOI: 10.1007/s12559-017-9479-z
       
  • FE-ELM: A New Friend Recommendation Model with Extreme Learning Machine
    • Authors: Zhen Zhang; Xiangguo Zhao; Guoren Wang
      Abstract: Friend recommendation is one of the most popular services in location-based social network (LBSN) platforms, which recommends interested or familiar people to users. Except for the original social property and textual property in social networks, LBSN specially owns the spatial-temporal property. However, none of the existing methods fully utilized all the three properties (i.e., just one or two), which may lead to the low recommendation accuracy. Moreover, these existing methods are usually inefficient. In this paper, we propose a new friend recommendation model to solve the above shortcomings of the existing methods, called feature extraction-extreme learning machine (FE-ELM), where friend recommendation is regarded as a binary classification problem. Classification is an important task in cognitive computation community. First, we use new strategies in our FE-ELM model to extract the spatial-temporal feature, social feature, and textual feature. These features make full use of all above properties of LBSN and ensure the recommendation accuracy. Second, our FE-ELM model also takes advantage of the extreme learning machine (ELM) classifier. ELM has fast learning speed and ensures the recommendation efficiency. Extensive experiments verify the accuracy and efficiency of FE-ELM model.
      PubDate: 2017-06-07
      DOI: 10.1007/s12559-017-9484-2
       
  • Removal of Electrooculogram Artifacts from Electroencephalogram Using
           
    • Authors: Banghua Yang; Tao Zhang; Yunyuan Zhang; Wanquan Liu; Jianguo Wang; Kaiwen Duan
      Abstract: Electrooculogram (EOG) is one of the major artifacts in the design of electroencephalogram (EEG)-based brain computer interfaces (BCIs). That removing EOG artifacts automatically while retaining more neural data will benefit for further feature extraction and classification. In order to remove EOG artifacts automatically as well as reserve more useful information from raw EEG, this paper proposes a novel blind source separation method called CCA-EEMD (canonical correlation analysis, ensemble empirical mode decomposition). Technically, the major steps of CCA-EEMD are as follows: Firstly, the multiple-channel original EEG signals are separated into several uncorrelated components using CCA. Then, the EOG component can be identified automatically by its kurtosis value. Next, the identified EOG component is decomposed into several intrinsic mode functions (IMFs) by EEMD. The IMFs uncorrelated to the EOG component are recognized and retained, and a new component will be constructed by the retained IMFs. Finally, the clean EEG signals are reconstructed. Keep in mind that the novelty of this paper is that the identified EOG component is not removed directly but used to extract neural EEG data, which would keep more effective information. Our tests with the data of seven subjects demonstrate that the proposed method has distinct advantages over other two commonly used methods in terms of average root mean square error [37.71 ± 0.14 (CCA-EEMD), 44.72 ± 0.13 (CCA), 49.59 ± 0.16 (ICA)], signal-to-noise ratio [3.59 ± 0.24 (CCA-EEMD), −6.53 ± 0.18(CCA), −8.43 ± 0.26 (ICA)], and classification accuracy [0.88 ± 0.002 (CCA-EEMD), 0.79 ± 0.001 (CCA), 0.73 ± 0.002 (ICA)]. The proposed method can not only remove EOG artifacts automatically but also keep the integrity of EEG data to the maximum extent.
      PubDate: 2017-06-05
      DOI: 10.1007/s12559-017-9478-0
       
  • Application of Rough Set-Based Feature Selection for Arabic Sentiment
           Analysis
    • Authors: Qasem A. Al-Radaideh; Ghufran Y. Al-Qudah
      Abstract: Sentiment analysis is considered as one of the recent applications of text categorization that categories the emotions expressed in text as negative, positive, and natural. Rough set theory is a mathematical tool used to analyze uncertainty, incomplete information, and data reduction. Indiscernibility, reduct, and core are essential concepts in rough set theory that can be employed for data classification and knowledge reduction. This paper proposes to use the rough set-based methods for sentiment analysis to classify tweets that are written in the Arabic language. The paper investigates the application of the reduct concept of rough set theory as a feature selection method for sentiment analysis. This paper investigates four reduct computation techniques to generate the set of reducts. For classification purposes, two rule generation algorithms have been studied to build the rough set rule-based classifier. An Arabic data set of 4800 tweets is used in the experiments to validate the use of reduct computation for Arabic sentiment analysis. The results of the experiments showed that using rough set reducts techniques lead to different results and some of them can perform better than non-rough set classifier. The best classification accuracy rate was for rough set classifier using the full attribute weighting reduct generation algorithm which achieved an accuracy of 74%. The primary results indicate that using the rough set theory framework for sentiment analysis is an appealing option where it can enhance the overall accuracy and reduce the number of used terms for classification which in turn will lead to a faster classification process, especially with a large dataset.
      PubDate: 2017-06-03
      DOI: 10.1007/s12559-017-9477-1
       
  • Multi-criteria Outranking Methods with Hesitant Probabilistic Fuzzy Sets
    • Authors: Jian Li; Jian-qiang Wang
      Abstract: Due to the defects of hesitant fuzzy sets (HFSs) in the actual decision-making process, it is necessary to add the probabilities corresponding to decision maker’s preferences to the values in HFSs. Hesitant probabilistic fuzzy sets (HPFSs) are suitable for presenting this kind of information and contribute positively to the efficiency of depicting decision maker’s preferences in practice. However, some important issues in HPFSs utilization remain to be addressed. In this paper, the qualitative flexible multiple criteria method (QUALIFLEX) and the preference ranking organization method for enrichment evaluations II (PROMETHEE II) are extended to HPFSs. First, we provide a comparison method for hesitant probabilistic fuzzy elements (HPFEs). Second, we propose a novel possibility degree depicting the relations between two HPFEs, and then, employ the possibility degree to extend the QUALIFLEX and PROMETHEE II methods to hesitant probabilistic fuzzy environments based on the proposed possibility degree. Third, an information integration method is introduced to simplify the processing of HPFE evaluation information. Finally, we provide an example to demonstrate the usefulness of the proposed methods. An illustrative example in conjunction with comparative analyses is employed to demonstrate that our proposed methods are feasible for practical multi-criteria decision-making (MCDM) problems, and the final ranking results show that the proposed methods are more accurate than the compared methods in an actual decision-making processes. HPFSs are more practical than HFSs due to their efficiency in comprehensively representing uncertain, vague, and probabilistic information. The proposed methods are effective for solving hesitant probabilistic MCDM problems and are expected to contribute to the solution of MCDM problems involving uncertain or vague information.
      PubDate: 2017-05-29
      DOI: 10.1007/s12559-017-9476-2
       
  • Orthogonal Echo State Networks and Stochastic Evaluations of Likelihoods
    • Authors: N. Michael Mayer; Ying-Hao Yu
      Abstract: We report about probabilistic likelihood estimates that are performed on time series using an echo state network with orthogonal recurrent connectivity. The results from tests using synthetic stochastic input time series with temporal inference indicate that the capability of the network to infer depends on the balance between input strength and recurrent activity. This balance has an influence on the network with regard to the quality of inference from the short-term input history versus inference that accounts for influences that date back a long time. Sensitivity of such networks against noise and the finite accuracy of network states in the recurrent layer are investigated. In addition, a measure based on mutual information between the output time series and the reservoir is introduced. Finally, different types of recurrent connectivity are evaluated. Orthogonal matrices not only show the best results of all investigated connectivity types overall but also in the way how the network performance scales with the size of the recurrent layer.
      PubDate: 2017-05-16
      DOI: 10.1007/s12559-017-9466-4
       
  • Echo State Property of Deep Reservoir Computing Networks
    • Authors: Claudio Gallicchio; Alessio Micheli
      Abstract: In the last years, the Reservoir Computing (RC) framework has emerged as a state of-the-art approach for efficient learning in temporal domains. Recently, within the RC context, deep Echo State Network (ESN) models have been proposed. Being composed of a stack of multiple non-linear reservoir layers, deep ESNs potentially allow to exploit the advantages of a hierarchical temporal feature representation at different levels of abstraction, at the same time preserving the training efficiency typical of the RC methodology. In this paper, we generalize to the case of deep architectures the fundamental RC conditions related to the Echo State Property (ESP), based on the study of stability and contractivity of the resulting dynamical system. Besides providing a necessary condition and a sufficient condition for the ESP of layered RC networks, the results of our analysis provide also insights on the nature of the state dynamics in hierarchically organized recurrent models. In particular, we find out that by adding layers to a deep reservoir architecture, the regime of network’s dynamics can only be driven towards (equally or) less stable behaviors. Moreover, our investigation shows the intrinsic ability of temporal dynamics differentiation at the different levels in a deep recurrent architecture, with higher layers in the stack characterized by less contractive dynamics. Such theoretical insights are further supported by experimental results that show the effect of layering in terms of a progressively increased short-term memory capacity of the recurrent models.
      PubDate: 2017-05-05
      DOI: 10.1007/s12559-017-9461-9
       
  • Reservoir Computing with Both Neuronal Intrinsic Plasticity and
           Multi-Clustered Structure
    • Authors: Fangzheng Xue; Qian Li; Hongjun Zhou; Xiumin Li
      Abstract: In the echo state networks, both reservoir states and network structure are essential for the performance of reservoir computing. In neuroscience, it has been confirmed that a single neuron can adaptively change its intrinsic excitability to fit various synaptic inputs. This mechanism is called intrinsic plasticity (IP) mechanism in the literature. This adaptive adjustment of neuronal response to external inputs is believed to maximize input-output mutual information. Meanwhile, the existence of multi-clustered structure with small-world-like property in the brain has been strongly supported by many neurophysiological experiments. Thus, it is advisable to consider both the intrinsic plasticity and multi-clustered structure of a reservoir network, rather than a random network with a non-adaptive reservoir response. In this paper, reservoir models with neuronal intrinsic plasticity and multi-clustered structure are investigated. The effects of two types of IP rules on the performance of several computational tasks have been investigated in detail by combining neuronal IP with multi-clustered reservoir structures. The first type is the Triesch’s IP rule, which drives the output activities of neurons to approximate exponential distributions; another is the Li’s IP rule, which generates a Gaussian distribution of neuronal firing. Results show that both the multi-clustered structures and IP rules can improve the computational accuracy of reservoir computing. However, before the application of the IP rules, the enhancement of computational performance for multi-clustered reservoirs is minor. Both IP rules contribute to improvement of the computational performance, where the Li’s IP rule is more advantageous than the Triesch’s IP. The results indicate that the combination of multi-clustered reservoir structures and IP learning can increase the dynamic diversity of reservoir states, especially for the IP’s learning. The adaptive tuning of reservoir states based on IP improves the dynamic complexity of neuronal activity, which helps train output weights. This biologically inspired reservoir model may give insights for the optimization of reservoir computing.
      PubDate: 2017-05-04
      DOI: 10.1007/s12559-017-9467-3
       
  • A Multiple-Input Strategy to Efficient Integrated Photonic Reservoir
           Computing
    • Authors: Andrew Katumba; Matthias Freiberger; Peter Bienstman; Joni Dambre
      Abstract: Photonic reservoir computing has evolved into a viable contender for the next generation of analog computing platforms as industry looks beyond standard transistor-based computing architectures. Integrated photonic reservoir computing, particularly on the silicon-on-insulator platform, presents a CMOS-compatible, wide bandwidth, parallel platform for implementation of optical reservoirs. A number of demonstrations of the applicability of this platform for processing optical telecommunication signals have been made in the recent past. In this work, we take it a stage further by performing an architectural search for designs that yield the best performance while maintaining power efficiency. We present numerical simulations for an optical circuit model of a 16-node integrated photonic reservoir with the input signal injected in combinations of 2, 4, and 8 nodes, or into all 16 nodes. The reservoir is composed of a network of passive photonic integrated circuit components with the required nonlinearity introduced at the readout point with a photodetector. The resulting error performance on the temporal XOR task for these multiple input cases is compared with that of the typical case of input to a single node. We additionally introduce for the first time in our simulations a realistic model of a photodetector. Based on this, we carry out a full power-level exploration for each of the above input strategies. Multiple-input reservoirs achieve better performance and power efficiency than single-input reservoirs. For the same input power level, multiple-input reservoirs yield lower error rates. The best multiple-input reservoir designs can achieve the error rates of single-input ones with at least two orders of magnitude less total input power. These results can be generally attributed to the increase in richness of the reservoir dynamics and the fact that signals stay longer within the reservoir. If we account for all loss and noise contributions, the minimum input power for error-free performance for the optimal design is found to be in the ≈1 mW range.
      PubDate: 2017-04-28
      DOI: 10.1007/s12559-017-9465-5
       
  • Advances in Biologically Inspired Reservoir Computing
    • Authors: Simone Scardapane; John B. Butcher; Filippo M. Bianchi; Zeeshan K. Malik
      PubDate: 2017-04-28
      DOI: 10.1007/s12559-017-9469-1
       
  • Optimizing Echo State Networks for Static Pattern Recognition
    • Authors: Adam J. Wootton; Sarah L. Taylor; Charles R. Day; Peter W. Haycock
      Abstract: Static pattern recognition requires a machine to classify an object on the basis of a combination of attributes and is typically performed using machine learning techniques such as support vector machines and multilayer perceptrons. Unusually, in this study, we applied a successful time-series processing neural network architecture, the echo state network (ESN), to a static pattern recognition task. The networks were presented with clamped input data patterns, but in this work, they were allowed to run until their output units delivered a stable set of output activations, in a similar fashion to previous work that focused on the behaviour of ESN reservoir units. Our aim was to see if the short-term memory developed by the reservoir and the clamped inputs could deliver improved overall classification accuracy. The study utilized a challenging, high dimensional, real-world plant species spectroradiometry classification dataset with the objective of accurately detecting one of the world’s top 100 invasive plant species. Surprisingly, the ESNs performed equally well with both unsettled and settled reservoirs. Delivering a classification accuracy of 96.60%, the clamped ESNs outperformed three widely used machine learning techniques, namely support vector machines, extreme learning machines and multilayer perceptrons. Contrary to past work, where inputs were clamped until reservoir stabilization, it was found that it was possible to obtain similar classification accuracy (96.49%) by clamping the input patterns for just two repeats. The chief contribution of this work is that a recurrent architecture can get good classification accuracy, even while the reservoir is still in an unstable state.
      PubDate: 2017-04-28
      DOI: 10.1007/s12559-017-9468-2
       
  • An Investigation of the Dynamical Transitions in Harmonically Driven
           Random Networks of Firing-Rate Neurons
    • Authors: Kyriacos Nikiforou; Pedro A. M. Mediano; Murray Shanahan
      Abstract: Continuous-time recurrent neural networks are widely used as models of neural dynamics and also have applications in machine learning. But their dynamics are not yet well understood, especially when they are driven by external stimuli. In this article, we study the response of stable and unstable networks to different harmonically oscillating stimuli by varying a parameter ρ, the ratio between the timescale of the network and the stimulus, and use the dimensionality of the network’s attractor as an estimate of the complexity of this response. Additionally, we propose a novel technique for exploring the stationary points and locally linear dynamics of these networks in order to understand the origin of input-dependent dynamical transitions. Attractors in both stable and unstable networks show a peak in dimensionality for intermediate values of ρ, with the latter consistently showing a higher dimensionality than the former, which exhibit a resonance-like phenomenon. We explain changes in the dimensionality of a network’s dynamics in terms of changes in the underlying structure of its vector field by analysing stationary points. Furthermore, we uncover the coexistence of underlying attractors with various geometric forms in unstable networks. As ρ is increased, our visualisation technique shows the network passing through a series of phase transitions with its trajectory taking on a sequence of qualitatively distinct figure-of-eight, cylinder, and spiral shapes. These findings bring us one step closer to a comprehensive theory of this important class of neural networks by revealing the subtle structure of their dynamics under different conditions.
      PubDate: 2017-04-07
      DOI: 10.1007/s12559-017-9464-6
       
  • Reservoir Computing with an Ensemble of Time-Delay Reservoirs
    • Authors: Silvia Ortín; Luis Pesquera
      Abstract: Reservoir computing (RC) has attracted a lot of attention in the field of machine learning because of its promising performance in a broad range of applications. However, it is difficult to implement standard RC in hardware. Reservoir computers with a single nonlinear neuron subject to delayed feedback (delay-based RC) allow efficient hardware implementation with similar performance to standard RC. We propose and study two different ways to build ensembles of delay-based RC with several delayed neurons (time-delay reservoirs): one using decoupled neurons and the other using coupled neurons through the feedback lines. In both cases, the outputs of the different neurons are linearly combined to solve some benchmark tasks. Simulation results show that these schemes achieve better performance than the single-neuron case. Moreover, the proposed architectures boost the RC processing speed with respect to the single-neuron case. Both schemes are found to be robust against small mismatches between delayed neuron parameters.
      PubDate: 2017-04-05
      DOI: 10.1007/s12559-017-9463-7
       
 
 
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
Fax: +00 44 (0)131 4513327
 
Home (Search)
Subjects A-Z
Publishers A-Z
Customise
APIs
Your IP address: 54.162.164.247
 
About JournalTOCs
API
Help
News (blog, publications)
JournalTOCs on Twitter   JournalTOCs on Facebook

JournalTOCs © 2009-2016