Spatial and Spectral Features Fusion for EEG Classification during Motor Imagery in BCI

TL;DR

This paper introduces a novel EEG classification algorithm that fuses spatial and spectral features to improve motor imagery detection accuracy in BCI systems.

Contribution

It proposes a feature fusion method combining CSP and wavelet coefficients for enhanced EEG classification in BCI applications.

Findings

Fusion algorithm outperforms traditional methods

Improved accuracy on BCI dataset IVa

Effective combination of spatial and spectral features

Abstract

Brain computer interface (BCI) is the only way for some special patients to communicate with the outside world and provide a direct control channel between brain and the external devices. As a non-invasive interface, the scalp electroencephalography (EEG) has a significant potential to be a major input signal for future BCI systems. Traditional methods only focus on a particular feature in the EEG signal, which limits the practical applications of EEG-based BCI. In this paper, we propose a algorithm for EEG classification with the ability to fuse multiple features. First, use the common spatial pattern (CSP) as the spatial feature and use wavelet coefficient as the spectral feature. Second, fuse these features with a fusion algorithm in orchestrate way to improve the accuracy of classification. Our algorithms are applied to the dataset IVa from BCI complete \uppercase\expandafter{\romannumeral3}. By analyzing the experimental results, it is possible to conclude that we can speculate that our algorithm perform better than traditional methods.