Unsupervised adaptation based on fuzzy C-means for brain-computer interface

An important property of brain signals is their nonstationarity. How to adapt a Brain-Computer Interface (BCI) to the changing brain states is one of the challenges faced by BCI researchers, especially in a real application scenario where the subject's real intent is unknown to the system. In this paper, an unsupervised approach based on Fuzzy C-Means (FCM) algorithm is proposed for the online adaptation of the LDA classifier for electroencephalogram (EEG) based BCI. The FCM method and other two existing unsupervised adaptation methods are applied to groups of constructed artificial data with different data properties. The performances of these methods in different situation are analyzed. Compared with the other two unsupervised methods, the proposed method shows a better ability of adapting to changes and discovering class information from unlabelled data. At last, the methods are applied to real EEG data from data set IIb of the BCI Competition IV. Results of the real data agree with the analysis based on the artificial data, which confirms the effectiveness of the proposed method.