Optimizing low-frequency common spatial pattern features for multi-class classification of hand movement directions

Recent studies have demonstrated that hand movement directions can be decoded from low-frequency electroencephalographic (EEG) signals. This paper proposes a novel framework that can optimally select dyadic filter bank common spatial pattern (CSP) features in low-frequency band (0-8 Hz) for multi-class classification of four orthogonal hand movement directions. The proposed framework encompasses EEG signal enhancement, dyadic filter bank CSP feature extraction, fuzzy mutual information (FMI)-based feature selection, and one-versus-rest Fisher's linear discriminant analysis. Experimental results on data collected from seven human subjects show that (1) signal enhancement can boost accuracy by at least 4%; (2) low-frequency band (0-8 Hz) can adequately and effectively discriminate hand movement directions; and (3) dyadic filter bank CSP feature extraction and FMI-based feature selection are indispensable for analyzing hand movement directions, increasing accuracy by 6.06%, from 60.02% to 66.08%.