Multi-channel Flexible Local Discriminant Bases for Classification of Left/right Finger Movement Imagery Related Eeg

This paper presents a feature extraction scheme called multichannel flexible local discriminant bases (MF-LDB) for left/right index finger movement imagery classification of a multi-channel electroencephalogram (EEG). The MF-LDB is obtained by calculating the local cosine packets (LCP) of the decided channel over nonuniform time-segments. The proposed method combines information from neighboring channels based on hard and soft decision. Simulation results show that the proposed feature extraction scheme can improve classification accuracies of the left/right index finger movement imagery signals by more than 3%. By applying the minimum variance distortionless response (MVDR) to find the spectra over nonoverlapping time-segments of each EEG channel, a nonredundant time-frequency transform called local MVDR packets transform which can provide highly selective frequency responses is also presented with approximately 4% improvement in classification accuracy.