Feature recognition of multi-class imaginary movements in brain-computer interface

Feature recognition of multi-class imaginary movements is an important subject of brain-computer interface based on imaginary movement. In this paper, using the method of two-dimensional time-frequency analysis combined with Fisher separability analysis to study multi-channel synchronization, multi-class imaginary movements potential information of typical subjects. Also we have extracted the feature data of event related resynchronization/synchronization that could be used to identify different classes, and then use the support vector machine to establish classifiers, and have completed a higher accuracy rate of classification for multi-motor patterns. The result shows that the identification accuracy could basically satisfy the requirements of BCI systems under the circumstances that the subjects are better trained.