A Knowledge Distillation Framework For Enhancing Ear-EEG Based Sleep Staging With Scalp-EEG Data

TL;DR

This paper introduces a knowledge distillation framework that improves ear-EEG sleep staging accuracy by leveraging scalp-EEG data, addressing the performance gap between these modalities.

Contribution

It proposes a cross-modal knowledge distillation method for domain adaptation, enhancing ear-EEG sleep staging performance using existing architectures.

Findings

Ear-EEG sleep staging accuracy improved by 3.46%.

Cohen's kappa coefficient increased by 0.038.

Validates effectiveness across multiple architectures.

Abstract

Sleep plays a crucial role in the well-being of human lives. Traditional sleep studies using Polysomnography are associated with discomfort and often lower sleep quality caused by the acquisition setup. Previous works have focused on developing less obtrusive methods to conduct high-quality sleep studies, and ear-EEG is among popular alternatives. However, the performance of sleep staging based on ear-EEG is still inferior to scalp-EEG based sleep staging. In order to address the performance gap between scalp-EEG and ear-EEG based sleep staging, we propose a cross-modal knowledge distillation strategy, which is a domain adaptation approach. Our experiments and analysis validate the effectiveness of the proposed approach with existing architectures, where it enhances the accuracy of the ear-EEG based sleep staging by 3.46% and Cohen's kappa coefficient by a margin of 0.038.