Dictionary update based adaptive EEG classification for real time brain-computer interface applications

Due to the non-stationarity of EEG signals, classification performance is deteriorated during experimental sessions. Therefore, adaptive classification techniques are required for real-time BCI applications. In this paper, we propose simple adaptive sparse representation based classification (SRC) methods. We study supervised and unsupervised dictionary update schemes for new test data. The proposed methods are very simple and additional computation for the re-training of the classifier is not needed. We evaluate the proposed methods using an online BCI experimental dataset. The proposed methods are assessed by comparing classification results with the conventional SRC and other adaptive classification methods. We find that the proposed adaptive schemes show improved classification accuracy as compared to conventional methods without additional computation.