A Recurrent Log-Linearized Gaussian Mixture Network

IEEE Transactions on Neural Networks Volume 14 Issue 2 Page 304-316 published_at 2003
アクセス数 : 1167
ダウンロード数 : 317

今月のアクセス数 : 4
今月のダウンロード数 : 4
File
IEEE_TNN_14_2_304-316_2003.pdf 861 KB 種類 : fulltext
Title ( eng )
A Recurrent Log-Linearized Gaussian Mixture Network
Creator
Bu Nan
Fukuda Osamu
Kaneko Makoto
Source Title
IEEE Transactions on Neural Networks
Volume 14
Issue 2
Start Page 304
End Page 316
Abstract
Context in time series is one of the most useful andinteresting characteristics for machine learning. In some cases, thedynamic characteristic would be the only basis for achieving a possibleclassification. A novel neural network, which is named “a recurrentlog-linearized Gaussian mixture network (R-LLGMN)," isproposed in this paper for classification of time series. The structureof this network is based on a hidden Markov model (HMM),which has been well developed in the area of speech recognition.R-LLGMN can as well be interpreted as an extension of a probabilisticneural network using a log-linearized Gaussian mixturemodel, in which recurrent connections have been incorporated tomake temporal information in use. Some simulation experimentsare carried out to compare R-LLGMN with the traditional estimatorof HMM as classifiers, and finally, pattern classification experimentsfor EEG signals are conducted. It is indicated from theseexperiments that R-LLGMN can successfully classify not only artificialdata but real biological data such as EEG signals.
Keywords
EEG
Gaussian mixture model
hidden Markov model (HMM)
log-linearized model
neural networks (NNs)
pattern classification
recurrent neural networks (RNNs)
NDC
Mechanical engineering [ 530 ]
Language
eng
Resource Type journal article
Publisher
IEEE
Date of Issued 2003
Rights
Copyright (c) 2003 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Publish Type Version of Record
Access Rights open access
Source Identifier
[ISSN] 1045-9227
[DOI] 10.1109/TNN.2003.809403
[NCID] AA10736045
[DOI] http://dx.doi.org/10.1109/TNN.2003.809403 isVersionOf