DocumentCode :
1465825
Title :
A log-linearized Gaussian mixture network and its application to EEG pattern classification
Author :
Tsuji, Toshio ; Fukuda, Osamu ; Ichinobe, Hiroyuki ; Kaneko, Makoto
Author_Institution :
Dept. of Ind. & Syst. Eng., Hiroshima Univ., Japan
Volume :
29
Issue :
1
fYear :
1999
fDate :
2/1/1999 12:00:00 AM
Firstpage :
60
Lastpage :
72
Abstract :
Proposes a new probabilistic neural network (NN) that can estimate the a-posteriori probability for a pattern classification problem. The structure of the proposed network is based on a statistical model composed by a mixture of log-linearized Gaussian components. However, the forward calculation and the backward learning rule can be defined in the same manner as the error backpropagation NN. In this paper, the proposed network is applied to the electroencephalogram (EEG) pattern classification problem. In the experiments described, two types of a photic stimulation, which are caused by eye opening/closing and artificial light, are used to collect the data to be classified. It is shown that the EEG signals can be classified successfully and that the classification rates change depending on the amount of training data and the dimension of the feature vectors
Keywords :
Gaussian distribution; backpropagation; electroencephalography; eye; feedforward neural nets; medical signal processing; pattern classification; recurrent neural nets; EEG pattern classification; a-posteriori probability; artificial light; backward learning rule; classification rates; data collection; electroencephalogram; error backpropagation; eye closing; eye opening; feature vector dimension; feedforward neural networks; forward calculation; log-linearized Gaussian mixture network; photic stimulation; probabilistic neural network; recurrent neural networks; signal classification; statistical model; training data; Artificial neural networks; Associate members; Backpropagation; Brain modeling; Electroencephalography; Neural networks; Parameter estimation; Pattern classification; Probability; Training data;
fLanguage :
English
Journal_Title :
Systems, Man, and Cybernetics, Part C: Applications and Reviews, IEEE Transactions on
Publisher :
ieee
ISSN :
1094-6977
Type :
jour
DOI :
10.1109/5326.740670
Filename :
740670
Link To Document :
بازگشت