Motor Imagery Classification via Clustered-Group Sparse Representation

A significant limitation on the wide use of a Motor Imagery (MI) Brain-Computer Interfaces is the acquisition of electroenchephalogram (EEG) data over a significant amount of EEG trials to achieve accurate classification. In this work, we propose a new sparse representation classification scheme to overcome the above limitation by training the proposed model using only a limited amount of EEG trials. Our algorithm extends current sparse representation classification schemes by exploiting the group sparsity of EEG features. We have evaluated the proposed algorithm on two MI EEG datasets, showing state-of-the-art performance against well known classification methods of MI BCI literature.