Identification of Motor Imagery EEG Signal
Dan Xiao, Jianfeng Hu · 2010
To identify subjects by classifying motor imagery EEG signal. Second-order blind identification (SOBI), a blind source separation (BSS) algorithm was applied to preprocess EEG data in for higher signal-to-noise ratio. Subsequently, Fisher distance was used to extract features. Finally, classification of extracted features was performed by back-propagation neural networks. Four types motor imagery EEG of three subjects was classified respectively. The results showed that the average classification accuracy achieved over 80%, and the highest was 88.1% on tongue movement imagery EEG.