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

Sleep stage classification is essential for sleep assessment and diseasediagnosis. Although previous attempts to classify sleep stages have achievedhigh classification performance, several challenges remain open: 1) How toeffectively utilize time-varying spatial and temporal features frommulti-channel brain signals remains challenging. Prior works have not been ableto fully utilize the spatial topological information among brain regions. 2)Due to the many differences found in individual biological signals, how toovercome the differences of subjects and improve the generalization of deepneural networks is important. 3) Most deep learning methods ignore theinterpretability of the model to the brain. To address the above challenges, wepropose a multi-view spatial-temporal graph convolutional networks (MSTGCN)with domain generalization for sleep stage classification. Specifically, weconstruct two brain view graphs for MSTGCN based on the functional connectivityand physical distance proximity of the brain regions. The MSTGCN consists ofgraph convolutions for extracting spatial features and temporal convolutionsfor capturing the transition rules among sleep stages. In addition, attentionmechanism is employed for capturing the most relevant spatial-temporalinformation for sleep stage classification. Finally, domain generalization andMSTGCN are integrated into a unified framework to extract subject-invariantsleep features. Experiments on two public datasets demonstrate that theproposed model outperforms the state-of-the-art baselines.

Multi-View Spatial-Temporal Graph Convolutional Networks with Domain Generalization for Sleep Stage Classification