AUTOMATIC SLEEP STAGE CLASSIFICATION USING MULTI-PHYSIOLOGICAL SIGNALS BASED ON PCBSLEEPNET

Authors

  • YuLi Yang School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China.
  • Ying Liu School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China.
  • HaoWei Zhang (Corresponding Author) School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China.

Keywords:

Deep learning, Sleep staging, Multi-physiological signals, Polysomnography

Abstract

Automatic sleep staging, a key technology in sleep medicine, faces feature selection challenges due to multi-modal physiological signal heterogeneity. This study establishes a framework to evaluate bioelectrical signals' impacts on deep neural network feature representation, aiming to identify optimal integration paradigms.We propose a multi-branch hybrid neural network with: 1) a three-channel parallel convolutional module incorporating cascaded residual and dilated convolutions for time-frequency feature extraction, and 2) bidirectional long short-term memory (BiLSTM) layers for temporal dependency modeling. We systematically analyzed multi-channel electroencephalogram (EEG), single-channel physiological signals, and their combinations covering both single-channel and multi-channel configurations of EEG, electrooculogram (EOG), and electromyogram (EMG). Results demonstrate that six-channel EEG configurations outperformed single/dual-channel implementations. In the single- and dual-channel EEG settings, the C3-M2 and C4-M1 + C3-M2 channels exhibited superior performance. EEG maintained superior classification capability over EOG/EMG. The tri-modal fusion (EEG+EOG+EMG) achieved peak performance (accuracy: 89.5%, Cohen’s κ: 0.85). This demonstrates EEG's central role in sleep staging, while EOG/EMG synergistically enhance model performance. The findings reveal heterogeneous bioelectric signal interactions in deep neural networks, providing foundations for optimizing signal fusion strategies and model architectures.

References

[1] Smith M G, Witte M, Rocha S, et al. Effectiveness of incentives and follow-up on increasing survey response rates and participation in field studies. BMC Medical Research Methodology, 2019, 19(1).

[2] Phan H, Andreotti F, Cooray N, et al. Joint Classification and Prediction CNN Framework for Automatic Sleep Stage Classification. IEEE Transactions on Biomedical Engineering, 2019, 66(5): 1285-1296.

[3] Czeisler C A. Duration, timing and quality of sleep are each vital for health, performance and safety. Sleep Health: Journal of the National Sleep Foundation, 2015, 1(1): 5-8.

[4] Korkalainen H, Aakko J, Nikkonen S, et al. Accurate Deep Learning-Based Sleep Staging in a Clinical Population With Suspected Obstructive Sleep Apnea. IEEE Journal of Biomedical and Health Informatics, 2020, 24(7): 2073-2081.

[5] Rundo J V, Downey R. Chapter 25 - Polysomnography. In: Levin K H, Chauvel P (Eds.), Handbook of Clinical Neurology, Elsevier, 2019: 381-392.

[6] Berry R B, Brooks R, Gamaldo C, et al. AASM Scoring Manual Updates for 2017 (Version 2.4). Journal of Clinical Sleep Medicine, 2017, 13(5): 665-666.

[7] Silber M H, Ancoli-Israel S, Bonnet M H, et al. The Visual Scoring of Sleep in Adults. Journal of Clinical Sleep Medicine, 2007, 3(2): 121-131.

[8] Chapotot F, Becq G. Automated sleep-wake staging combining robust feature extraction, artificial neural network classification, and flexible decision rules. International Journal of Adaptive Control and Signal Processing, 2010, 24(5): 409-423.

[9] Allan Hobson J. A manual of standardized terminology, techniques and scoring system for sleep stages of human subjects: A. Rechtschaffen and A. Kales (Editors). Electroencephalography and Clinical Neurophysiology, 1969, 26(6): 644.

[10] Rosenberg R S, Hout S V. The American Academy of Sleep Medicine Inter-scorer Reliability Program: Respiratory Events. Journal of Clinical Sleep Medicine, 2014, 10(4): 447-454.

[11] Grigg-Damberger M M. The AASM scoring manual: a critical appraisal. Current Opinion in Pulmonary Medicine, 2009, 15(6).

[12] Zhang L, Fabbri D, Upender R, et al. Automated sleep stage scoring of the Sleep Heart Health Study using deep neural networks. Sleep, 2019, 42(11).

[13] Ben Hamouda G, Rejeb L, Ben Said L. Ensemble learning for multi-channel sleep stage classification. Biomedical Signal Processing and Control, 2024, 93: 106184.

[14] Heng X, Wang M, Wang Z, et al. Leveraging discriminative features for automatic sleep stage classification based on raw single-channel EEG. Biomedical Signal Processing and Control, 2024, 88: 105631.

[15] Fu G, Zhou Y, Gong P, et al. A Temporal-Spectral Fused and Attention-Based Deep Model for Automatic Sleep Staging. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2023, 31: 1008-1018.

[16] Jiang D, Ma Y, Wang Y. Sleep stage classification using covariance features of multi-channel physiological signals on Riemannian manifolds. Computer Methods and Programs in Biomedicine, 2019, 178: 19-30.

[17] Wang X, Bik A, de Groot E R, et al. Feasibility of automated early postnatal sleep staging in extremely and very preterm neonates using dual-channel EEG. Clinical Neurophysiology, 2023, 146: 55-64.

[18] Satapathy S K, Bhoi A K, Loganathan D, et al. Machine learning with ensemble stacking model for automated sleep staging using dual-channel EEG signal. Biomedical Signal Processing and Control, 2021, 69: 102898.

[19] Sokolovsky M, Guerrero F, Paisarnsrisomsuk S, et al. Deep Learning for Automated Feature Discovery and Classification of Sleep Stages. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2020, 17(6): 1835-1845.

[20] Zhuang L, Dai M, Zhou Y, et al. Intelligent automatic sleep staging model based on CNN and LSTM. Frontiers in Public Health, 2022, 10.

[21] Fiorillo L, Favaro P, Faraci F D. DeepSleepNet-Lite: A Simplified Automatic Sleep Stage Scoring Model With Uncertainty Estimates. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2021, 29: 2076-2085.

[22] Haowei Z, Zhe X, Chengmei Y, et al. Automatic sleep staging model based on single channel electroencephalogram signal. Journal of Biomedical Engineering, 2023, 40(3): 458-464+473.

[23] Yang Y, Li S, Li C, et al. Research on ultrasonic signal processing algorithm based on CEEMDAN joint wavelet packet thresholding. Measurement, 2022, 201: 111751.

[24] He H B, Bai Y, Garcia E A, et al. ADASYN: Adaptive Synthetic Sampling Approach for Imbalanced Learning. 2008 IEEE International Joint Conference on Neural Networks, 2008: 1322-1328.

[25] Michielli N, Acharya U R, Molinari F. Cascaded LSTM recurrent neural network for automated sleep stage classification using single-channel EEG signals. Computers in Biology and Medicine, 2019, 106: 71-81.

[26] Willoughby A R, Alikhani I, Karsikas M, et al. Country differences in nocturnal sleep variability: Observations from a large-scale, long-term sleep wearable study. Sleep Medicine, 2023, 110: 155-165.

Downloads

Published

2026-04-03

How to Cite

YuLi Yang, Ying Liu, HaoWei Zhang. Automatic Sleep Stage Classification Using Multi-Physiological Signals Based On Pcbsleepnet. Eurasia Journal of Science and Technology. 2026, 8(2): 1-8. DOI: https://doi.org/10.61784/ejst3140.