Imaginary motor movement EEG classification by Accumulative-Autocorrelation-Pulse
Mayer, I.V.; Takahashi, H.; Sakamoto, K.
Electromyography and Clinical Neurophysiology 41(3): 159-169
2001
ISSN/ISBN: 0301-150X PMID: 11402508 Document Number: 535965
Analysis of motor imaginary electroencephalogram (EEG) signals provide a feasible low-level communication channel for handicap people. We propose a classification method for imaginary right and left motor EEG using the Accumulative-Autocorrelation-Pulse (AAP) technique. This technique is based on the spatio-temporal pulse patterns generated from the accumulative autocorrelation values of selected electrodes in the ongoing EEG data. A feed forward neural network trained with the back propagation learning algorithm is used for classification. The network structure preserves and extracts the pulse-temporal feature patterns of the signal. Classification results reach 100% generalization accuracy in some single subjects and a 91% generalization over all subjects when the correct pair of electrodes are selected. Robust generalization results indicate that the autocorrelation nature of the human EEG signal contains typical patterns for classification in imaginary left and right motor events.