Spatial Filtering for Brain Computer Interfaces: A Comparison between the Common Spatial Pattern and Its Variant

TL;DR

This paper compares the traditional common spatial pattern (CSP) filter with a new variant for EEG classification in brain-computer interfaces, demonstrating that the traditional approach generally performs better, and regularization improves results.

Contribution

The paper introduces a new CSP variant and systematically compares it with the traditional method, highlighting the effectiveness of regularization in EEG spatial filtering.

Findings

Traditional CSP outperforms the new variant in most cases.

Regularization of covariance matrices enhances classification accuracy.

Both methods benefit from covariance regularization.

Abstract

The electroencephalogram (EEG) is the most popular form of input for brain computer interfaces (BCIs). However, it can be easily contaminated by various artifacts and noise, e.g., eye blink, muscle activities, powerline noise, etc. Therefore, the EEG signals are often filtered both spatially and temporally to increase the signal-to-noise ratio before they are fed into a machine learning algorithm for recognition. This paper considers spatial filtering, particularly, the common spatial pattern (CSP) filters for EEG classification. In binary classification, CSP seeks a set of filters to maximize the variance for one class while minimizing it for the other. We first introduce the traditional solution, and then a new solution based on a slightly different objective function. We performed comprehensive experiments on motor imagery to compare the two approaches, and found that generally the traditional CSP solution still gives better results. We also showed that adding regularization to the covariance matrices can improve the final classification performance, no matter which objective function is used.