Classifying EEG for Brain-Computer Interface Using Spatio-Temporal Filters

摘要

Brain computer interface (BCI) is a new device which provides user a communication system between the brain and the external devices. EEGs recorded from scalp were analyzed in order to identify the human's intentions. The feature extraction of EEG signals plays an important role for classifying these spontaneous mental activities. In this paper, three subjects participated in the BCI experiment which contains three mental tasks including imagination of left hand, right hand and foot movement.After preprocessing, Spatio-temporal filters were applied to extract the feature of EEG signals. Then, Linear discriminant analysis (LDA) was used to classify the feature extracted. After that, a comparison of feature extract methods between Spatio-temporal filters and band power (BP) was made. The results show that it can be used as an effective method for classifying three different motor imaginations by Spatio-temporal filters.