A method for classifying mental tasks in the space of EEG transforms

In this article we describe a new method for supervised classification of EEG signals. This method applies to the power spectrum density data and assigns class-dependent information weights to individual pixels, so that the decision is defined by the summary weights of the most informative pixel features. We experimentally analyze several versions of the approach. The informative features appear to be rather similar among different individuals, thus supporting the view that there are subject independent general brain patterns for the same mental task