OPTIMAL CHANNEL SELECTION FOR MULTI-CHANNEL SSVEP DETECTION AND CLASSIFICATION IN BCIS

摘要

Many multi-channel techniques for Steady-State Visual-Evoked Potential (SSVEP) detection from EEGhave shown signicant improvement in the performance of Brain-Computer Interfaces (BCIs). Multichannelmethods, generally involve deriving a spatial filter to linearly combine the EEG channels so as tominimize the noise energy and enhance the SSVEP response. In this paper, three state of the art multichanneltechniques are studied and compared. The performance of the classifiers for varying number andcombination of the EEG channels is studied to determine the optimal choice of channels that yield maximumclassification accuracy. The correlation of different channel parameters with the net montage performanceis also investigated. Results indicate that Minimum Energy Channel (MEC) based classifier yields thehighest accuracy values using 6 channels for all the 3 subjects. Signicance of non-occipital locations forsignal acquisition has been observed. Further, results indicate that the choice of channels to be used in themontage is to be made keeping in mind their eective signal strength, co-channel noise correlation valuesand signal to noise ratios. This ensures that a particular montage has eectively assimilated the signal andnoise components.