Automatic differentiation of multichannel EEG signals

Intention of movement of left or right index finger, or right foot is recog nized in electroencephalograms (EEGs) from three subjects. We present a mul tichannel classification method that uses a "committee" of artificial neura l networks to do this. The classification method automatically finds spatia l regions on the skull relevant for the classification task. Depending on s ubject, correct recognition of intended movement was achieved in 75%-98% of trials not seen previously by the committee, on the basis of single EEGs o f one-second duration. Frequency filtering did not improve recognition. Cla ssification was optimal during the actual movement, but a first peak in the classification success rate was observed in all subjects already when they had been cued which movement later to perform.