Classification of EEG Multiple Imagination Tasks Based on Independent Component Analysis and Relevant Vector Machines

To solve the problem of feature extraction in braincomputer interface (BCI), the position, size and direction of dipole are located by using dipole localization method, so as to locate the active part of advanced nerve activity and remove a series of physiological and electrical artifacts such as electro-ophthalmogram. The common space pattern and correlation vector machine are used to extract the effective components of EEG signals and classify multiple motor imagery tasks. The results show that the combination of EEG dipole localization and common spatial pattern can effectively improve the signal-to-noise ratio of EEG signals and extract more obvious features. The correlation vector machine provides better classification results and is an effective method to complete the classification and recognition of motor imagery signals.