Recognition of imagined hand surface movements with low resolution surfaceLaplacian and linear classifiers

EEG-based Brain Computer Interfaces (BCIs) require on-line detection of men tal states from spontaneous EEG signals. In this framework, it was suggeste d that EEG patterns can be better detected with EEG data transformed with S urface Laplacian computation (SL) than with the unprocessed raw potentials. However, accurate SL estimates require the use of many EEG electrodes, whe n local estimation methods are used. Since BCI devices have to use a limite d number of electrodes for practical reasons, we investigated the performan ces of spline methods for SL estimates using a limited number of electrodes (low resolution SQ. Recognition of mental activity was attempted on both r aw and SL-transformed EEG data from five healthy people performing two ment al tasks, namely imagined right and left hand movements. Linear classifiers were used including Signal Space Projection (SSP) and Fisher's linear disc riminant. Results showed an acceptable average correlation between the wave forms obtained with the low resolution SL and these obtained with the SL co mputed from 26 electrodes (full resolution SL). More importantly, satisfact orily recognition scores for mental EEG-patterns were obtained with the low -resolution surface Laplacian transformation of the recorded potentials whe n compared with those obtained by using full resolution SL (82%). These res ults demonstrated also the utility of linear classifiers for the detection of mental patterns in the BCI field. (C) 2001 IPEM. Published by Elsevier S cience Ltd. Ali rights reserved.