Removing Neural Signal Artifacts with Autoencoder-Targeted Adversarial Transformers (AT-AT)

TL;DR

This paper introduces AT-AT, a lightweight autoencoder-targeted adversarial transformer that effectively removes EMG noise from EEG data, achieving high performance with significantly reduced model size compared to existing methods.

Contribution

The study presents a novel, efficient deep learning architecture for EMG artifact removal in EEG, combining autoencoder and adversarial transformer techniques to reduce model size and maintain accuracy.

Findings

Achieved over 90% reduction in model size compared to existing models.

Attained a mean correlation coefficient above 0.95 at 2 dB SNR.

Maintained a correlation coefficient of 0.70 at -7 dB SNR.

Abstract

Electromyogenic (EMG) noise is a major contamination source in EEG data that can impede accurate analysis of brain-specific neural activity. Recent literature on EMG artifact removal has moved beyond traditional linear algorithms in favor of machine learning-based systems. However, existing deep learning-based filtration methods often have large compute footprints and prohibitively long training times. In this study, we present a new machine learning-based system for filtering EMG interference from EEG data using an autoencoder-targeted adversarial transformer (AT-AT). By leveraging the lightweight expressivity of an autoencoder to determine optimal time-series transformer application sites, our AT-AT architecture achieves a >90% model size reduction compared to published artifact removal models. The addition of adversarial training ensures that filtered signals adhere to the fundamental characteristics of EEG data. We trained AT-AT using published neural data from 67 subjects and found that the system was able to achieve comparable test performance to larger models; AT-AT posted a mean reconstructive correlation coefficient above 0.95 at an initial signal-to-noise ratio (SNR) of 2 dB and 0.70 at -7 dB SNR. Further research generalizing these results to broader sample sizes beyond these isolated test cases will be crucial; while outside the scope of this study, we also include results from a real-world deployment of AT-AT in the Appendix.