Classification of imagery movement tasks for brain-computer interfaces based on energy

In order to extract the feature of electroencephalogram (EEG) quickly and efficiently, to improve the classification accuracy rate, band-pass filter and wavelet package were used to get mu and beta rhythms. In the time domain, energy feature was formed by the squared-amplitude of electroencephalogram (EEG) samples over the trials. The subtracted energy value of lead C3 and C4 was averaged by each trial. The polarity (positive or negative) of subtracted value for each trial indicates the kind of imagery movement and was used to classify. The method is simple and the classification accuracy rate is up to 87.857%.