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

被引:6
作者
Wang, Qi [1 ]
Guo, Yecai [1 ]
Shen, Yuhui [1 ]
Tong, Shuang [1 ]
Guo, Hongcan [1 ]
机构
[1] Nanjing Univ Informat Sci & Technol, Sch Elect & Informat Engn, Nanjing 210044, Peoples R China
基金
中国国家自然科学基金;
关键词
graph attention network; gated recurrent unit; node-level and stage-level attention; sleep staging; transitional stage estimator; SIGNALS;
D O I
10.3390/s22239272
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
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.
引用
收藏
页数:17
相关论文
共 37 条
  • [1] Non-linear analysis of EEG signals at various sleep stages
    Acharya, R
    Faust, O
    Kannathal, N
    Chua, T
    Laxminarayan, S
    [J]. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2005, 80 (01) : 37 - 45
  • [2] Alexander N.O, 2021, SLEEP, V44, P161
  • [3] Ensemble SVM Method for Automatic Sleep Stage Classification
    Alickovic, Emina
    Subasi, Abdulhamit
    [J]. IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2018, 67 (06) : 1258 - 1265
  • [4] Allam J.P., 2022, Artificial Intelligence-Based BrainComputer Interface, P189
  • [5] Multi-channel spectrograms for speech processing applications using deep learning methods
    Arias-Vergara, T.
    Klumpp, P.
    Vasquez-Correa, J. C.
    Noeth, E.
    Orozco-Arroyave, J. R.
    Schuster, M.
    [J]. PATTERN ANALYSIS AND APPLICATIONS, 2021, 24 (02) : 423 - 431
  • [6] Batista GE., 2004, ACM SIGKDD EXPLOR NE, V6, P20, DOI [DOI 10.1145/1007730.1007735, 10.1145/1007730.1007735, 10.1145/1007730.1007735.2]
  • [7] Berry R.B., 2012, AASM MANUAL SCORING
  • [8] Rules for Scoring Respiratory Events in Sleep: Update of the 2007 AASM Manual for the Scoring of Sleep and Associated Events
    Berry, Richard B.
    Budhiraja, Rohit
    Gottlieb, Daniel J.
    Gozal, David
    Iber, Conrad
    Kapur, Vishesh K.
    Marcus, Carole L.
    Mehra, Reena
    Parthasarathy, Sairam
    Quan, Stuart F.
    Redline, Susan
    Strohl, Kingman P.
    Ward, Sally L. Davidson
    Tangredi, Michelle M.
    [J]. JOURNAL OF CLINICAL SLEEP MEDICINE, 2012, 8 (05): : 597 - 619
  • [9] A scoping review of behavioral sleep stage classification methods for preterm infants
    Bik, Anne
    Sam, Chanel
    de Groot, Eline R.
    Visser, Simone S. M.
    Wang, Xiaowan
    Tataranno, Maria Luisa
    Benders, Manon J. N. L.
    van den Hoogen, Agnes
    Dudink, Jeroen
    [J]. SLEEP MEDICINE, 2022, 90 : 74 - 82
  • [10] Carskadon MA, 2011, PRINCIPLES PRACTICE, P16, DOI DOI 10.1016/B978-1-4160-6645-3.00002-5