EEG channel selection algorithm based on Reinforcement Learning

Abstract

Multichannel EEG is generally used to collect brain activities from various locations across the brain. However, BCIs using lesser channels will be more convenient for subjects. What's more, information acquired from adjacent channels is usually inter-correlated or irrelevant to the task. And some channels are noisy. This paper proposes a novel channel selection algorithm based on reinforcement learning. It can adaptively transform the full-channel EEG data to the optimal-channel-number EEG format conditioned on different input trials to make a trade-off between brain decoding accuracy and efficiency. Experimen-tal results showed that the proposed model can improve the classification accuracy by 2% ~ 6% compared to channel set $\{C3,C4,Cz\}$.