Score-Based Data Generation for EEG Spatial Covariance Matrices: Towards Boosting BCI Performance

TL;DR

This paper introduces a score-based generative model for synthesizing EEG spatial covariance matrices to enhance data availability and improve BCI classifier performance, demonstrating high-quality sample generation and increased classification accuracy.

Contribution

We propose a novel score-based generative modeling approach for EEG covariance matrices, enabling realistic data synthesis to boost BCI classifier accuracy.

Findings

Generated samples achieved 84.3% prediction accuracy.

Samples showed neurophysiological consistency with known EEG patterns.

Classifier accuracy improved by up to 8.7% in tests.

Abstract

The efficacy of Electroencephalogram (EEG) classifiers can be augmented by increasing the quantity of available data. In the case of geometric deep learning classifiers, the input consists of spatial covariance matrices derived from EEGs. In order to synthesize these spatial covariance matrices and facilitate future improvements of geometric deep learning classifiers, we propose a generative modeling technique based on state-of-the-art score-based models. The quality of generated samples is evaluated through visual and quantitative assessments using a left/right-hand-movement motor imagery dataset. The exceptional pixel-level resolution of these generative samples highlights the formidable capacity of score-based generative modeling. Additionally, the center (Frechet mean) of the generated samples aligns with neurophysiological evidence that event-related desynchronization and synchronization occur on electrodes C3 and C4 within the Mu and Beta frequency bands during motor imagery processing. The quantitative evaluation revealed that 84.3% of the generated samples could be accurately predicted by a pre-trained classifier and an improvement of up to 8.7% in the average accuracy over ten runs for a specific test subject in a holdout experiment.