Boosting Generalization in Bio-Signal Classification by Learning the Phase-Amplitude Coupling

TL;DR

This paper introduces a novel self-supervised learning method called Phase-Swap that leverages phase-amplitude coupling in bio-signals, improving generalization across subjects and sessions in bio-signal classification.

Contribution

The paper presents a new self-supervised task, Phase-Swap, that exploits phase-amplitude coupling to enhance bio-signal classification generalization.

Findings

Neural networks trained on Phase-Swap generalize better across subjects.

Phase-Swap improves robustness to noise compared to traditional methods.

The approach captures biologically relevant information in bio-signals.

Abstract

Various hand-crafted features representations of bio-signals rely primarily on the amplitude or power of the signal in specific frequency bands. The phase component is often discarded as it is more sample specific, and thus more sensitive to noise, than the amplitude. However, in general, the phase component also carries information relevant to the underlying biological processes. In fact, in this paper we show the benefits of learning the coupling of both phase and amplitude components of a bio-signal. We do so by introducing a novel self-supervised learning task, which we call Phase-Swap, that detects if bio-signals have been obtained by merging the amplitude and phase from different sources. We show in our evaluation that neural networks trained on this task generalize better across subjects and recording sessions than their fully supervised counterpart.