Spectrally Adaptive Common Spatial Patterns

TL;DR

This paper introduces SACSP, a novel spectral adaptation method for CSP in EEG-based BCI, enhancing generalization, accuracy, and neurophysiological insights by learning user-specific spectral filters.

Contribution

SACSP extends CSP by learning spectral filters for each spatial filter, improving robustness and interpretability in motor imagery BCI systems.

Findings

SACSP outperforms existing CSP methods in classification accuracy.

SACSP provides neurophysiologically relevant spectral information.

SACSP demonstrates better generalization from calibration to online control.

Abstract

The method of Common Spatial Patterns (CSP) is widely used for feature extraction of electroencephalography (EEG) data, such as in motor imagery brain-computer interface (BCI) systems. It is a data-driven method estimating a set of spatial filters so that the power of the filtered EEG signal is maximized for one motor imagery class and minimized for the other. This method, however, is prone to overfitting and is known to suffer from poor generalization especially with limited calibration data. Additionally, due to the high heterogeneity in brain data and the non-stationarity of brain activity, CSP is usually trained for each user separately resulting in long calibration sessions or frequent re-calibrations that are tiring for the user. In this work, we propose a novel algorithm called Spectrally Adaptive Common Spatial Patterns (SACSP) that improves CSP by learning a temporal/spectral filter for each spatial filter so that the spatial filters are concentrated on the most relevant temporal frequencies for each user. We show the efficacy of SACSP in providing better generalizability and higher classification accuracy from calibration to online control compared to existing methods. Furthermore, we show that SACSP provides neurophysiologically relevant information about the temporal frequencies of the filtered signals. Our results highlight the differences in the motor imagery signal among BCI users as well as spectral differences in the signals generated for each class, and show the importance of learning robust user-specific features in a data-driven manner.