ONLINE EEG CLASSIFICATION DURING EXTERNALLY-PACED HAND MOVEMENTS USING A NEURAL-NETWORK-BASED CLASSIFIER

EEGs of 6 normal subjects were recorded during sequences of periodic l eft or right hand movement. Left or right was indicated by a visual cu e. The question posed was: 'Is it possible to move a cursor on a monit or to the right or left side using the EEG signals for cursor control? ' For this purpose the EEG during performance of hand movement was ana lyzed and classified on-line. a neural network in form of a learning v ector quantizertion (LVQ) with an input dimension of 16 was trained to classify EEG patterns from two electrodes and two time windows. After two training session on 2 different days, 4 subjects showed a classif ication accuracy of 89-100%. For two subjects classification was not p ossible. These results show that in general movement specific EEG-patt erns can be found, classified in real time and used to move a cursor o n a monitor to the left or right. On-line EEG classification is necess ary when the EEG is used as input signal to a brain computer interface (BCI). Such a BCI can be a help for handicapped people.