EEG Effective Channel Selection based on Target Detection

In the target detection task of brain-computer interface based on the fast sequence visual presentation (RSVP), P300 is usually used as the most effective feature to capture the target image in the rapidly presented image stream. For online rsvp experiments, the target detection speed is one of the important parameters in the application. For EEG data from whole brain channels, too many channels will bring too much redundant information, which will bring more time complexity and invalid features to the data processing. In the p300-based target detection experiment, people usually simply select the channel data of the central area of the p300 fixed brain area for target detection in the experiment, but there is no detailed analysis of the selection of different brain areas and the quantitative comparison of results. This paper selects the frontal and parietal areas, and does an interpretation experiment of infrared ship images. The experimental results of different brain areas are compared and analyzed offline. Compared with other electrode selection schemes, the EEG signals of 53 electrodes related to frontal region, parietal region and central region reached the highest classification accuracy, the accuracy is 89.38%. In addition, the test results may provide some ideas for the reduction of channels in wearable devices.