EEG channel optimization via sparse common spatial filter

In this paper, we propose a novel sparse common spatial pattern (CSP) algorithm to optimally select channels of EEG signals. Compared to the traditional CSP, which maximizes the variance of signals in one class and minimizes the variance of signals in the other class, the classification accuracy is guaranteed by a constraint that the ratio of variances of signals in two different classes is lower bounded. Then, a sparse spatial filter is achieved by minimizing the l1-norm of filter coefficients and channels of EEG signals can be further optimized. The original nonconvex optimization problem is relaxed to a semidefinite program (SDP), which can be efficiently solved by well-developed numerical solvers. Experimental results demonstrate that the proposed algorithm can identify and discard about 50% channels with only 1% decrease of classification accuracy.