Cargando…

Multi-Layer Graph Attention Network for Sleep Stage Classification Based on EEG

Graph neural networks have been successfully applied to sleep stage classification, but there are still challenges: (1) How to effectively utilize epoch information of EEG-adjacent channels owing to their different interaction effects. (2) How to extract the most representative features according to...

Descripción completa

Detalles Bibliográficos
Autores principales: Wang, Qi, Guo, Yecai, Shen, Yuhui, Tong, Shuang, Guo, Hongcan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9735886/
https://www.ncbi.nlm.nih.gov/pubmed/36501974
http://dx.doi.org/10.3390/s22239272
_version_ 1784846883643981824
author Wang, Qi
Guo, Yecai
Shen, Yuhui
Tong, Shuang
Guo, Hongcan
author_facet Wang, Qi
Guo, Yecai
Shen, Yuhui
Tong, Shuang
Guo, Hongcan
author_sort Wang, Qi
collection PubMed
description Graph neural networks have been successfully applied to sleep stage classification, but there are still challenges: (1) How to effectively utilize epoch information of EEG-adjacent channels owing to their different interaction effects. (2) How to extract the most representative features according to confused transitional information in confused stages. (3) How to improve classification accuracy of sleep stages compared with existing models. To address these shortcomings, we propose a multi-layer graph attention network (MGANet). Node-level attention prompts the graph attention convolution and GRU to focus on and differentiate the interaction between channels in the time-frequency domain and the spatial domain, respectively. The multi-head spatial-temporal mechanism balances the channel weights and dynamically adjusts channel features, and a multi-layer graph attention network accurately expresses the spatial sleep information. Moreover, stage-level attention is applied to easily confused sleep stages, which effectively improves the limitations of a graph convolutional network in large-scale graph sleep stages. The experimental results demonstrated classification accuracy; MF1 and Kappa reached 0.825, 0.814, and 0.775 and 0.873, 0.801, and 0.827 for the ISRUC and SHHS datasets, respectively, which showed that MGANet outperformed the state-of-the-art baselines.
format Online
Article
Text
id pubmed-9735886
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-97358862022-12-11 Multi-Layer Graph Attention Network for Sleep Stage Classification Based on EEG Wang, Qi Guo, Yecai Shen, Yuhui Tong, Shuang Guo, Hongcan Sensors (Basel) Article Graph neural networks have been successfully applied to sleep stage classification, but there are still challenges: (1) How to effectively utilize epoch information of EEG-adjacent channels owing to their different interaction effects. (2) How to extract the most representative features according to confused transitional information in confused stages. (3) How to improve classification accuracy of sleep stages compared with existing models. To address these shortcomings, we propose a multi-layer graph attention network (MGANet). Node-level attention prompts the graph attention convolution and GRU to focus on and differentiate the interaction between channels in the time-frequency domain and the spatial domain, respectively. The multi-head spatial-temporal mechanism balances the channel weights and dynamically adjusts channel features, and a multi-layer graph attention network accurately expresses the spatial sleep information. Moreover, stage-level attention is applied to easily confused sleep stages, which effectively improves the limitations of a graph convolutional network in large-scale graph sleep stages. The experimental results demonstrated classification accuracy; MF1 and Kappa reached 0.825, 0.814, and 0.775 and 0.873, 0.801, and 0.827 for the ISRUC and SHHS datasets, respectively, which showed that MGANet outperformed the state-of-the-art baselines. MDPI 2022-11-28 /pmc/articles/PMC9735886/ /pubmed/36501974 http://dx.doi.org/10.3390/s22239272 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Wang, Qi
Guo, Yecai
Shen, Yuhui
Tong, Shuang
Guo, Hongcan
Multi-Layer Graph Attention Network for Sleep Stage Classification Based on EEG
title Multi-Layer Graph Attention Network for Sleep Stage Classification Based on EEG
title_full Multi-Layer Graph Attention Network for Sleep Stage Classification Based on EEG
title_fullStr Multi-Layer Graph Attention Network for Sleep Stage Classification Based on EEG
title_full_unstemmed Multi-Layer Graph Attention Network for Sleep Stage Classification Based on EEG
title_short Multi-Layer Graph Attention Network for Sleep Stage Classification Based on EEG
title_sort multi-layer graph attention network for sleep stage classification based on eeg
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9735886/
https://www.ncbi.nlm.nih.gov/pubmed/36501974
http://dx.doi.org/10.3390/s22239272
work_keys_str_mv AT wangqi multilayergraphattentionnetworkforsleepstageclassificationbasedoneeg
AT guoyecai multilayergraphattentionnetworkforsleepstageclassificationbasedoneeg
AT shenyuhui multilayergraphattentionnetworkforsleepstageclassificationbasedoneeg
AT tongshuang multilayergraphattentionnetworkforsleepstageclassificationbasedoneeg
AT guohongcan multilayergraphattentionnetworkforsleepstageclassificationbasedoneeg