A New Method for Features Normalization in Motor Imagery Few-Shot Learning using Resting-State

TL;DR

This paper introduces a novel feature normalization method for motor imagery BCI systems that reduces calibration time and improves classification accuracy by leveraging resting-state signals in different eye states.

Contribution

The study proposes a new feature calibration approach using resting-state signals in various eye conditions, enhancing BCI performance and reducing user calibration effort.

Findings

Resting-state signals in open-eye mode yield the highest classification accuracy.

The proposed method increases accuracy by 3.64% to 74.04%.

Recording time and eye state significantly impact classification performance.

Abstract

Brain-computer interface (BCI) systems are usually designed specifically for each subject based on motor imagery. Therefore, the usability of these networks has become a significant challenge. The network has to be designed separately for each user, which is time-consuming for the user. Therefore, this study proposes a method by which the calibration time is significantly reduced while the classification accuracy is increased. In this method, we calibrated the features extracted from the motor imagery task by dividing the features extracted from the resting-state into both open-eye and closed-eye modes and the state in which the subject moves his eyes. The best classification accuracy was obtained using the SVM classifier using the resting-state signal in the open eye, which increased by 3.64% to 74.04%. In this paper, we also investigated the effect of recording time of the resting-state signal and the impact of eye state on the classification accuracy.