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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Sleep quality has a significant impact on human physical and mental health. The detection of sleep-wake states is thus of significant importance in the study of sleep. The performance of classical machine learning models for automated sleep detection depends on the signals considered and feature extraction methods. Moreover, hand-crafted features are highly dependent on the experts’ experience and their prior knowledge about different physiological signals and conditions of the subjects. To overcome this limitation, this paper develops an end-to-end deep learning approach for automated feature extraction and detection of sleep-wake states using single channel raw EEG signals. Moreover, we leverage transfer learning to train and fine tune the proposed model to avoid the complexities associated with building a deep learning model from scratch. Using polysomnography (PSG) data of 20 patients, our results demonstrate the effectiveness of the proposed deep learning pipeline, achieving an excellent test performance in detecting sleep events with an overall sensitivity and precision of 92.7% and 92.1% respectively. The results demonstrate that the proposed approach can achieve superior performance compared to state-of-the-art studies on Sleep- Wake classification. Furthermore, it can attain reliable results as an alternative to classical methods that heavily rely on expert defined features.

An End-to-End Deep Leaning Approach for Sleep-Wake Classification Using Single Channel EEG Signals