Optimization method of error-related potentials to improve MI-BCI performance

Abstract

This paper proposes an optimization method of error-related potentials (ErrPs). The method is used to improve motor imagery (MI)-BCI performance by rapidly correcting MI-BCI errors. We used the linear discriminant analysis and spatial-temporal domain analysis (STDA) algorithms to detect ErrP, which is the brain response measured immediately after MI-BCI error. We found the optimal conditions for detecting ErrPs by comparing the performances of the algorithms in terms of the resampling rate, spatial domain, and temporal domain. The best sample size was obtained at a resampling rate of 21 Hz. In the spatial domain, using the data from 8 or 16 channels provided better performance compared to using a higher number of channels. For epoch selection in the temporal domain, the highest accuracy was obtained for the data at 1000 ms. Finally, the best performers among all subjects exhibited 86% accuracy in the optimal condition (21 Hz, 1000 ms, 16 ch), while the worst performers exhibited 58.67% accuracy in the first trial in the STDA algorithm.