A Systematic Evaluation of Self-Supervised Learning for Label-Efficient Sleep Staging with Wearable EEG

One-line Summary

Self-supervised learning (SSL) significantly improves sleep staging accuracy using wearable EEG, requiring far fewer labeled data than traditional methods.

Plain-language Overview

This study explores how self-supervised learning (SSL) can enhance sleep analysis using wearable EEG devices. These devices offer a more accessible alternative to traditional sleep studies but generate large amounts of data that are difficult to label manually. By using SSL, researchers can effectively use this unlabeled data, improving accuracy in sleep stage classification even when only a small portion of the data is labeled. This approach could make sleep monitoring more affordable and scalable, requiring less manual effort from clinicians.

Technical Details