Binary multi-objective particle swarm optimization for channel selection in motor imagery based brain-computer interfaces

The development of brain-computer interface (BCI) systems has attracted lots of researchers, and they are now attempting to put current BCI techniques into practical application. However, the BCI system based on motor imagery is still not used for real-life application due to the decreasing performance of common spatial pattern algorithm especially when the number of channels is large. In addition, with the increase of channel numbers, multi-channel EEG signals need inconvenient recording preparation and complex calculation, which will be time-consuming and lead to lower classification accuracy. To address this problem, a novel method, named binary multi-objective particle swarm optimization (BMOPSO), is proposed for channel reduction in this paper. The results indicate that the proposed approach is successful in reducing channel number and running time without lowering the classification accuracy.