English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The past few years have witnessed a remarkable advance in deep learning forEEG-based sleep stage classification (SSC). However, the success of thesemodels is attributed to possessing a massive amount of labeled data fortraining, limiting their applicability in real-world scenarios. In suchscenarios, sleep labs can generate a massive amount of data, but labeling thesedata can be expensive and time-consuming. Recently, the self-supervisedlearning (SSL) paradigm has shined as one of the most successful techniques toovercome the scarcity of labeled data. In this paper, we evaluate the efficacyof SSL to boost the performance of existing SSC models in the few-labelsregime. We conduct a thorough study on three SSC datasets, and we find thatfine-tuning the pretrained SSC models with only 5% of labeled data can achievecompetitive performance to the supervised training with full labels. Moreover,self-supervised pretraining helps SSC models to be more robust to dataimbalance and domain shift problems. The code is publicly available athttps://github.com/emadeldeen24/eval_ssl_ssc.

Self-supervised Learning for Label-Efficient Sleep Stage Classification: A Comprehensive Evaluation