BMFLC with neural network and DE for better event classification

Abstract

The event-related desynchronization(ERD) is a well known phenomenon that is commonly used for classification in brain-computer interface(BCI) applications. The classification accuracy of ERD based BCI can be improved by selection of subject-specific reactive band rather than complete μ-band. After obtaining time-frequency(TF) mapping of EEG signal with a Fourier based adaptive method, differential evolution(DE) is used for the identification of the reactive band. Compared to classical band-power based method, the proposed method based on subject-specific reactive band yields better accuracy with BCI competition dataset IV.