Classification of single trial EEG signals by a combined principal+independent component analysis and probabilistic neural network approach

Tetsuya Hoya, Gen Hori, Hovagim Bakardjian, Tomoaki Nishimura, Taiji Suzuki, Yoichi Miyawaki, Arao Funase, Jianting Cao

Abstract:

In this paper, an attempt is made to classify the
EEG signals of letter imagery tasks using a combined
independent component analysis and probabilistic neu
ral network. The role of the principal/independent com
ponent analysis is to mitigate the effect of EOG arti
facts within each single-trial EEG pattern. Experimen
tal results show an overall performance improvement
of around in terms of the pattern classification
accuracy, in comparison with the LPC spectral analy
sis which is commonly employed in speech recogni
tion tasks.