Computational Intelligence and Neuroscience (Comput Intell Neurosci )

Publisher: Hindawi Publishing Corporation, Hindawi Publishing Corporation


  • Impact factor
  • 5-year impact
  • Cited half-life
  • Immediacy index
  • Eigenfactor
  • Article influence
  • Website
    Computational Intelligence and Neuroscience website
  • Other titles
    Computational intelligence and neuroscience (online), CIN
  • ISSN
  • OCLC
  • Material type
    Document, Periodical, Internet resource
  • Document type
    Internet Resource, Computer File, Journal / Magazine / Newspaper

Publisher details

Hindawi Publishing Corporation

  • Pre-print
    • Author can archive a pre-print version
  • Post-print
    • Author can archive a post-print version
  • Conditions
    • Publisher's version/PDF may be used
    • Creative Commons Attribution License
    • Eligible UK authors may deposit in OpenDepot
    • All titles are open access journals
  • Classification
    ‚Äč green

Publications in this journal

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The minimum audible angle test which is commonly used for evaluating human localization ability depends on interaural time delay, interaural level differences, and spectral information about the acoustic stimulus. These physical properties are estimated at different stages along the brainstem auditory pathway. The interaural time delay is ambiguous at certain frequencies, thus confusion arises as to the source of these frequencies. It is assumed that in a typical minimum audible angle experiment, the brain acts as an unbiased optimal estimator and thus the human performance can be obtained by deriving optimal lower bounds. Two types of lower bounds are tested: the Cramer-Rao and the Barankin. The Cramer-Rao bound only takes into account the approximation of the true direction of the stimulus; the Barankin bound considers other possible directions that arise from the ambiguous phase information. These lower bounds are derived at the output of the auditory nerve and of the superior olivary complex where binaural cues are estimated. An agreement between human experimental data was obtained only when the superior olivary complex was considered and the Barankin lower bound was used. This result suggests that sound localization is estimated by the auditory nuclei using ambiguous binaural information.
    Computational Intelligence and Neuroscience 01/2014; 2014:575716.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper details a novel probabilistic method for automatic neural spike sorting which uses stochastic point process models of neural spike trains and parameterized action potential waveforms. A novel likelihood model for observed firing times as the aggregation of hidden neural spike trains is derived, as well as an iterative procedure for clustering the data and finding the parameters that maximize the likelihood. The method is executed and evaluated on both a fully labeled semiartificial dataset and a partially labeled real dataset of extracellular electric traces from rat hippocampus. In conditions of relatively high difficulty (i.e., with additive noise and with similar action potential waveform shapes for distinct neurons) the method achieves significant improvements in clustering performance over a baseline waveform-only Gaussian mixture model (GMM) clustering on the semiartificial set (1.98% reduction in error rate) and outperforms both the GMM and a state-of-the-art method on the real dataset (5.04% reduction in false positive + false negative errors). Finally, an empirical study of two free parameters for our method is performed on the semiartificial dataset.
    Computational Intelligence and Neuroscience 01/2014; 2014:643059.
  • [Show abstract] [Hide abstract]
    ABSTRACT: We propose a biologically motivated brain-inspired single neuron perceptron (SNP) with universal approximation and XOR computation properties. This computational model extends the input pattern and is based on the excitatory and inhibitory learning rules inspired from neural connections in the human brain's nervous system. The resulting architecture of SNP can be trained by supervised excitatory and inhibitory online learning rules. The main features of proposed single layer perceptron are universal approximation property and low computational complexity. The method is tested on 6 UCI (University of California, Irvine) pattern recognition and classification datasets. Various comparisons with multilayer perceptron (MLP) with gradient decent backpropagation (GDBP) learning algorithm indicate the superiority of the approach in terms of higher accuracy, lower time, and spatial complexity, as well as faster training. Hence, we believe the proposed approach can be generally applicable to various problems such as in pattern recognition and classification.
    Computational Intelligence and Neuroscience 01/2014; 2014:746376.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Cuckoo search (CS) is a new robust swarm intelligence method that is based on the brood parasitism of some cuckoo species. In this paper, an improved hybrid encoding cuckoo search algorithm (ICS) with greedy strategy is put forward for solving 0-1 knapsack problems. First of all, for solving binary optimization problem with ICS, based on the idea of individual hybrid encoding, the cuckoo search over a continuous space is transformed into the synchronous evolution search over discrete space. Subsequently, the concept of confidence interval (CI) is introduced; hence, the new position updating is designed and genetic mutation with a small probability is introduced. The former enables the population to move towards the global best solution rapidly in every generation, and the latter can effectively prevent the ICS from trapping into the local optimum. Furthermore, the greedy transform method is used to repair the infeasible solution and optimize the feasible solution. Experiments with a large number of KP instances show the effectiveness of the proposed algorithm and its ability to achieve good quality solutions.
    Computational Intelligence and Neuroscience 01/2014; 2014:970456.
  • [Show abstract] [Hide abstract]
    ABSTRACT: When confronting the complex problems, radial basis function (RBF) neural network has the advantages of adaptive and self-learning ability, but it is difficult to determine the number of hidden layer neurons, and the weights learning ability from hidden layer to the output layer is low; these deficiencies easily lead to decreasing learning ability and recognition precision. Aiming at this problem, we propose a new optimized RBF neural network algorithm based on genetic algorithm (GA-RBF algorithm), which uses genetic algorithm to optimize the weights and structure of RBF neural network; it chooses new ways of hybrid encoding and optimizing simultaneously. Using the binary encoding encodes the number of the hidden layer's neurons and using real encoding encodes the connection weights. Hidden layer neurons number and connection weights are optimized simultaneously in the new algorithm. However, the connection weights optimization is not complete; we need to use least mean square (LMS) algorithm for further leaning, and finally get a new algorithm model. Using two UCI standard data sets to test the new algorithm, the results show that the new algorithm improves the operating efficiency in dealing with complex problems and also improves the recognition precision, which proves that the new algorithm is valid.
    Computational Intelligence and Neuroscience 01/2014; 2014:982045.
  • [Show abstract] [Hide abstract]
    ABSTRACT: The aim of this work is to propose a new feature and score fusion based iris recognition approach where voting method on Multiple Classifier Selection technique has been applied. Four Discrete Hidden Markov Model classifiers output, that is, left iris based unimodal system, right iris based unimodal system, left-right iris feature fusion based multimodal system, and left-right iris likelihood ratio score fusion based multimodal system, is combined using voting method to achieve the final recognition result. CASIA-IrisV4 database has been used to measure the performance of the proposed system with various dimensions. Experimental results show the versatility of the proposed system of four different classifiers with various dimensions. Finally, recognition accuracy of the proposed system has been compared with existing N hamming distance score fusion approach proposed by Ma et al., log-likelihood ratio score fusion approach proposed by Schmid et al., and single level feature fusion approach proposed by Hollingsworth et al.
    Computational Intelligence and Neuroscience 01/2014; 2014:380585.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Feature selection plays an important role in machine learning and data mining. In recent years, various feature measurements have been proposed to select significant features from high-dimensional datasets. However, most traditional feature selection methods will ignore some features which have strong classification ability as a group but are weak as individuals. To deal with this problem, we redefine the redundancy, interdependence, and independence of features by using neighborhood entropy. Then the neighborhood entropy-based feature contribution is proposed under the framework of cooperative game. The evaluative criteria of features can be formalized as the product of contribution and other classical feature measures. Finally, the proposed method is tested on several UCI datasets. The results show that neighborhood entropy-based cooperative game theory model (NECGT) yield better performance than classical ones.
    Computational Intelligence and Neuroscience 01/2014; 2014:479289.
  • Source
    Computational Intelligence and Neuroscience 01/2014; 2014:161203.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Topics identification (TI) is the process that consists in determining the main themes present in natural language documents. The current TI modeling paradigm aims at acquiring semantic information from statistic properties of large text datasets. We investigate the mental mechanisms responsible for the identification of topics in a single document given existing knowledge. Our main hypothesis is that topics are the result of accumulated neural activation of loosely organized information stored in long-term memory (LTM). We experimentally tested our hypothesis with a computational model that simulates LTM activation. The model assumes activation decay as an unavoidable phenomenon originating from the bioelectric nature of neural systems. Since decay should negatively affect the quality of topics, the model predicts the presence of short-term memory (STM) to keep the focus of attention on a few words, with the expected outcome of restoring quality to a baseline level. Our experiments measured topics quality of over 300 documents with various decay rates and STM capacity. Our results showed that accumulated activation of loosely organized information was an effective mental computational commodity to identify topics. It was furthermore confirmed that rapid decay is detrimental to topics quality but that limited capacity STM restores quality to a baseline level, even exceeding it slightly.
    Computational Intelligence and Neuroscience 01/2014; 2014:920892.
  • [Show abstract] [Hide abstract]
    ABSTRACT: Cognitive agents are expected to interact with and adapt to a nonstationary dynamic environment. As an initial process of decision making in a real-world agent interaction, familiarity judgment leads the following processes for intelligence. Familiarity judgment includes knowing previously encoded data as well as completing original patterns from partial information, which are fundamental functions of recognition memory. Although previous computational memory models have attempted to reflect human behavioral properties on the recognition memory, they have been focused on static conditions without considering temporal changes in terms of lifelong learning. To provide temporal adaptability to an agent, in this paper, we suggest a computational model for recognition memory that enables lifelong learning. The proposed model is based on a hypergraph structure, and thus it allows a high-order relationship between contextual nodes and enables incremental learning. Through a simulated experiment, we investigate the optimal conditions of the memory model and validate the consistency of memory performance for lifelong learning.
    Computational Intelligence and Neuroscience 01/2014; 2014:354703.
  • [Show abstract] [Hide abstract]
    ABSTRACT: Many of the multichannel extracellular recordings of neural activity consist of attempting to sort spikes on the basis of shared characteristics with some feature detection techniques. Then spikes can be sorted into distinct clusters. There are in general two main statistical issues: firstly, spike sorting can result in well-sorted units, but by with no means one can be sure that one is dealing with single units due to the number of neurons adjacent to the recording electrode. Secondly, the waveform dimensionality is reduced in a small subset of discriminating features. This shortening dimension effort was introduced as an aid to visualization and manual clustering, but also to reduce the computational complexity in automatic classification. We introduce a metric based on common neighbourhood to introduce sparsity in the dataset and separate data into more homogeneous subgroups. The approach is particularly well suited for clustering when the individual clusters are elongated (that is nonspherical). In addition it does need not to select the number of clusters, it is very efficient to visualize clusters in a dataset, it is robust to noise, it can handle imbalanced data, and it is fully automatic and deterministic.
    Computational Intelligence and Neuroscience 01/2014; 2014:757068.