Motor Imagery EEG Classification Based on Dynamic ICA Mixing Matrix

Recently the mu rhythm by motor imagination has been used as a reliable EEG pattern for brain-computer interface (BCI) system. To motor-imagery-based BCI, feature extraction and classification are two critical stages. This paper explores a dynamic ICA base on sliding window Infomax algorithm to analyze motor imagery EEG. The method can get a dynamic mixing matrix with the new data inputting, which is unlike the static mixing matrix in traditional ICA algorithm. And by using the feature patterns based on total energy of dynamic mixing matrix coefficients in a certain time window, the classification accuracy without training can be achieved beyond 85% for BCI competition 2003 data set III. The results demonstrate that the method can be used for the extraction and classification of motor imagery EEG. In the present study, it suggests that the proposed algorithm may provide a valuable alternative to study motor imagery EEG for BCI applications.