A Computationally Efficient Multiclass Time-Frequency Common Spatial Pattern Analysis on EEG Motor Imagery

TL;DR

This paper introduces a modified multi-class EEG motor imagery analysis method that enhances classification accuracy and computational efficiency by combining time-frequency analysis, signal selection, and parallel classifiers.

Contribution

It proposes a novel multi-class CSP algorithm with improved efficiency and accuracy, outperforming traditional methods in EEG motor imagery classification.

Findings

Reduced computation time by 37.22% compared to FBCSP

Achieved high classification accuracy with a top 2nd kappa value

Effective signal selection based on energy improves feature extraction

Abstract

Common spatial pattern (CSP) is a popular feature extraction method for electroencephalogram (EEG) motor imagery (MI). This study modifies the conventional CSP algorithm to improve the multi-class MI classification accuracy and ensure the computation process is efficient. The EEG MI data is gathered from the Brain-Computer Interface (BCI) Competition IV. At first, a bandpass filter and a time-frequency analysis are performed for each experiment trial. Then, the optimal EEG signals for every experiment trials are selected based on the signal energy for CSP feature extraction. In the end, the extracted features are classified by three classifiers, linear discriminant analysis (LDA), na\"ive Bayes (NVB), and support vector machine (SVM), in parallel for classification accuracy comparison. The experiment results show the proposed algorithm average computation time is 37.22% less than the FBCSP (1st winner in the BCI Competition IV) and 4.98% longer than the conventional CSP method. For the classification rate, the proposed algorithm kappa value achieved 2nd highest compared with the top 3 winners in BCI Competition IV.