Abstract:

Current motor imagery brain-computer interface (MI-BCI) rehabilitation training methods suffer from a lack of diversity in experimental approaches, insufficient real-time feedback optimization, and low decoding rates of electroencephalogram (EEG) signals. This paper innovatively proposes an MI-BCI rehabilitation training method to address these problems, integrating concentration assessment and feedback optimization. A paradigm of EEG signals acquisition is explored by incorporating concentration level assessment. The efficiency of decoding motor imagery EEG signals is significantly improved, benefiting from the feedback of concentration assessment of the subjects in a task state. Experimental results demonstrate that the proposed novel MI-BCI rehabilitation training method improves the concentration levels of subjects, and simultaneously validates the differences in EEG signals with varying degree of concentration. Furthermore, an MI-EEG binary classification accuracy of 84.37% is achieved.

Key words: BCI, motor imagery, integrating concentration assessment and feedback, rehabilitation training