Performance increase by using a EEG sparse representation based classification method

Attempts are being made to make brain-computer interface system (BCIs) commercially viable for normal person. Stable performance is essential so that BCIs could widely be used for general public. We propose a new classification method based on sparse representation of EEG signals and L1 minimization. The proposed method use the common spatial filtering (CSP) and band power feature for classification. We compare the classification accuracy of proposed method to that of the conventional linear discriminant analysis (LDA) method. Our method shows improved accuracy over the LDA classification method regardless of the number of CSP filters.