Abstract
Sleep staging is significant for the capture of sleep patterns and the assessment of sleep quality. Although previous studies attempted to automatically detect sleep stages and achieved high classification performance, several challenges remain: 1) How to correctly classify the sleep stages end-to-end. 2) How to capture the representations and sleep transition rules effectively. 3) How to capture the sleep features adaptively from multimodal data for sleep staging. To address these problems, a multimodal channel attention-based sleep staging network named MCASleepNet is proposed. Specifically, the proposed network is a mixed model composed of a dual-stream convolutional neural network (CNN) structure, a solitary long short-term memory (LSTM) module and a multimodal channel attention module. The dual-stream CNN structure is designed for the extraction of sleep representation characteristics from multimodal data. Meanwhile, the LSTM module is developed to learn transition rules between sleep stages. In addition, the multimodal channel attention module is developed to extract meaningful features of specific sleep stages from multimodal sleep data, electroencephalogram (EEG) and electrooculogram (EOG) signals. The sleep staging experiment demonstrates that the MCASleepNet proposed in this study exceeds the state-of-the-art baseline methods, with an overall accuracy of 89.1% and a macro F1 score of 84.4 on the publicly available Sleep-EDF dataset.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Czeisler, C.A.: Duration, timing and quality of sleep are each vital for health, performance and safety. Sleep Health: J. Natl. Sleep Found. 1(1), 5–8 (2015)
De Biase, S., et al.: The importance of polysomnography in the evaluation of prolonged disorders of consciousness: sleep recordings more adequately correlate than stimulus-related evoked potentials with patients’ clinical status. Sleep Med. 15(4), 393–400 (2014)
Eldele, E., et al.: An attention-based deep learning approach for sleep stage classification with single-channel EEG. IEEE Trans. Neural Syst. Rehabil. Eng. 29, 809–818 (2021)
Feng, L.X., et al.: Automatic sleep staging algorithm based on time attention mechanism. Front. Hum. Neurosci. 15, 692054 (2021)
Fraiwan, L., Lweesy, K., Khasawneh, N., Wenz, H., Dickhaus, H.: Automated sleep stage identification system based on time-frequency analysis of a single EEG channel and random forest classifier. Comput. Methods Prog. Biomed. 108(1), 10–19 (2012)
Hassan, A.R., Bhuiyan, M.I.H.: A decision support system for automatic sleep staging from EEG signals using tunable q-factor wavelet transform and spectral features. J. Neurosci. Methods 271, 107–118 (2016)
Iber, C., Ancoli-Isreal, S., Chesson, A.L., Quan, S.F.: The aasm manual for the scoring of sleep and associated events: rules, terminology, and techinical specifications (2007)
Jia, Z., Lin, Y., Wang, J., Wang, X., Xie, P., Zhang, Y.: Salientsleepnet: Multimodal salient wave detection network for sleep staging. arXiv preprint arXiv:2105.13864 (2021)
Kemp, B., Zwinderman, A.H., Tuk, B., Kamphuisen, H.A., Oberye, J.J.: Analysis of a sleep-dependent neuronal feedback loop: the slow-wave microcontinuity of the EEG. IEEE Trans. Biomed. Eng. 47(9), 1185–1194 (2000)
Liu, C., Yin, Y., Sun, Y., Ersoy, O.K.: Multi-scale ResNet and BiGRU automatic sleep staging based on attention mechanism. PLoS ONE 17(6), e0269500 (2022)
Mousavi, S., Afghah, F., Acharya, U.R.: SleepEEGNet: automated sleep stage scoring with sequence to sequence deep learning approach. PLoS ONE 14(5), e0216456 (2019)
Ohayon, M.M.: Epidemiology of insomnia: what we know and what we still need to learn. Sleep Med. Rev. 6(2), 97–111 (2002)
Phan, H., Andreotti, F., Cooray, N., Chén, O.Y., De Vos, M.: SeqSleepNet: end-to-end hierarchical recurrent neural network for sequence-to-sequence automatic sleep staging. IEEE Trans. Neural Syst. Rehabil. Eng. 27(3), 400–410 (2019)
Phan, H., Chén, O.Y., Tran, M.C., Koch, P., Mertins, A., De Vos, M.: Xsleepnet: multi-view sequential model for automatic sleep staging. IEEE Trans. Pattern Anal. Mach. Intell. 44(9), 5903–5915 (2021)
Rechtschaffen, A.: A manual of standardized terminology, techniques and scoring system for sleep of human subjects (1968)
Supratak, A., Dong, H., Wu, C., Guo, Y.: DeepSleepNet: a model for automatic sleep stage scoring based on raw single-channel EEG. IEEE Trans. Neural Syst. Rehabil. Eng. 25(11), 1998–2008 (2017)
Supratak, A., Guo, Y.: TinySleepNet: an efficient deep learning model for sleep stage scoring based on raw single-channel EEG. In: 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), pp. 641–644. IEEE (2020)
Xu, Z., Yang, X., Sun, J., Liu, P., Qin, W.: Sleep stage classification using time-frequency spectra from consecutive multi-time points. Front. Neurosci. 14, 14 (2020)
Acknowledgement
This work was supported in part by the National Natural Science Foundation of China under grant 62076103 and the Special Innovation Project of Colleges and Universities in Guangdong Province under grant 2022KTSCX035.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Yu, Y., Chen, S., Pan, J. (2023). MCASleepNet: Multimodal Channel Attention-Based Deep Neural Network for Automatic Sleep Staging. In: Iliadis, L., Papaleonidas, A., Angelov, P., Jayne, C. (eds) Artificial Neural Networks and Machine Learning – ICANN 2023. ICANN 2023. Lecture Notes in Computer Science, vol 14263. Springer, Cham. https://doi.org/10.1007/978-3-031-44204-9_26
Download citation
DOI: https://doi.org/10.1007/978-3-031-44204-9_26
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44203-2
Online ISBN: 978-3-031-44204-9
eBook Packages: Computer ScienceComputer Science (R0)