Classification of movement-related single-trial MEG data using adaptive spatial filter

In this paper, a method for extracting and classifying movement-related brain signals is proposed. A single-trial MEG observation is first processed with a pre-whitening filter so that strong stationary interference is eliminated. Next, a brain signal effective for classification is extracted using an adaptive spatial filter. The extracted signal is then classified with a support vector machine. From the experimental results, it is shown that the classification rate of 62.6 % is obtained for the brain signals related to the three types of hand movements (“scissors-paper-rock”).