Hand Movement Direction Decoding from EEG Signals under Dual Movement Tasks

Decoding human motor intention from electroencephalograms (EEG) signals is valuable for developing intelligent driver-assistive systems. However, existing studies about human motion decoding from EEG signals are only focused on one main movement task without considering the influence of other movement tasks. In this work, we explore the decoding of right-hand movement direction from EEG signals in the presence of a left-hand movement. A corresponding experimental paradigm was designed. The phase-locking value (PLV), amplitude in the time domain, and spectrum energy in the frequency domain from different frequency bands were used as classification features, respectively, and linear discrimination analysis (LDA) was used as a classifier to decode movement direction of the right hand. Experimental results showed that the decoding model based on the amplitude in the delta band performed best with a mean accuracy of 73.01% for the left-and-right direction pair, showing the feasibility of movement direction decoding of a single hand from EEG signals under a movement of the other hand.