Multi-view signal integration via manifold learning for sleep stage classification_Journal of Biomedical Engineering

Authors：

TONG Wei ^1,2 , LIN Xi ³ , WU Xinying ^4,5 ,  LI Tao ¹ ,  WU Qi ⁵

1. School of Automation, Nanjing University of Information Science and Technology, Nanjing 210044, P. R. China;
2. School of Automation, Nanjing University of Posts and Telecommunications, Nanjing 210023, P. R. China;
3. School of Computer and Information Technology, Shanxi University, Taiyuan 030006, P. R. China;
4. SINOPEC Safety Engineering Institute, Qingdao, Shandong 266101, P. R. China;
5. School of Computer Science, Shanghai Jiaotong University, Shanghai 200042, P. R. China;

Corresponding?author：

LI Tao, Email: litaojia@nuist.edu.cn; WU Qi, Email: edmondqwu@sjtu.edu.cn

Keywords：

Sleep stage classification; Spatial topology; Attention; Manifold learning; Multi-modal

DOI：

10.7507/1001-5515.202512024

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Sleep disorders and sleep disturbances are gaining increasing attention, and accurate sleep staging is key to assessing sleep quality. Existing studies utilize spatio-temporal features of multi-channel physiological signals such as EEG and spatial topological information of brain regions for sleep staging, but they suffer from insufficient mining of spatio-temporal correlations, neglect of the nonlinear geometric structure of signals, and feature redundancy, leading to low accuracy in sleep stage classification. To address these problems, this paper proposes a multi-view spatio-temporal convolutional integration network based on manifold learning. Firstly, three types of feature representations of multi-physiological signals are constructed via short-time Fourier transform, discrete wavelet transform, and raw signal processing. Secondly, an attention module that fuses Euclidean space and manifold geometry is designed to represent and enhance multi-modal physiological signals on the Riemannian symmetric positive definite manifold, mining their potential spatio-temporal representations. Finally, combining these three types of sleep features from adjacent time segments, long short-term memory (LSTM) is used to model temporal dependencies to accomplish sleep stage classification. Experimental results on public sleep stage classification datasets show that the proposed method outperforms existing mainstream methods in accuracy, F1-score, and Kappa coefficient, and ablation studies validate the effectiveness of the manifold attention mechanism and multi-view feature combination. This work provides a new method for nonlinear fusion of multi-modal physiological signals.

Citation： TONG Wei, LIN Xi, WU Xinying, LI Tao, WU Qi. Multi-view signal integration via manifold learning for sleep stage classification. Journal of Biomedical Engineering, 2026, 43(4): 729-740. doi: 10.7507/1001-5515.202512024 Copy

1.	姚璐媛. 基于深度學習的腦電信號睡眠分期方法研究[D]. 蘭州: 蘭州理工大學, 2023: 12.
2.	王琪. 基于混合神經網絡的自動睡眠分期算法研究[D]. 南京: 南京信息工程大學, 2023: 56.
3.	田蘊郅, 周強, 李婉. 基于遷移學習的隨機深度殘差網絡自動睡眠分期算法[J]. 生物醫學工程學雜志, 2023, 40(2): 286-294.
4.	胡凱蕾, 陳景霞, 張鵬偉, 等. 用于睡眠精準分期的多模態生理時頻特征提取網絡[J]. 生物醫學工程學雜志, 2024, 41(1): 26-33.
5.	金崢, 賈克斌. 一種基于Transformer架構的多層級自動睡眠分期模型[J]. 電子學報, 2025, 53(2): 545-557.
6.	劉虹梅, 彭才靜, 韓芳, 等. 基于腦電多視圖混合神經網絡的時空半監督睡眠分期[J]. 工程科學學報, 2023, 45(5): 797-806.
7.	韓亮, 羅統軍, 蒲秀娟, 等. 使用異質集成學習和心電信號異構特征融合的睡眠呼吸暫停分類方法[J]. 儀器儀表學報, 2024, 45(6): 320-327.
8.	李思恒, 金蓓弘, 張扶桑, 等. 基于多任務注意力網絡的非接觸式睡眠監測[J]. 計算機研究與發展, 2024, 61(11): 2739-2753.
9.	趙倩, 李錦, 鳳飛龍, 等. 基于U2-Net和CBAM融合注意力的雙模態睡眠分期研究[J]. 陜西師范大學學報(自然科學版), 2025, 53(1): 1-11.
10.	王依純, 丁寧, 吳婷, 等. 腦機接口在睡眠障礙監測與干預中的應用進展[J]. 生物醫學轉化, 2025, 6(4): 1-6, 20.
11.	Mads O, Jamie M Z, Risa N R, et al. A deep transfer learning approach for sleep stage classification and sleep apnea detection using wrist-worn consumer sleep technologies[J]. IEEE Trans Biomed Eng, 2024, 71(8): 2506-2517.
12.	Wan C, Nnamdi M C, Shi W, et al. Advancing sleep disorder diagnostics: a transformer-based EEG model for sleep stage classification and OSA prediction[J]. IEEE J Biomed Health Inform, 2025, 29(2): 878-886.
13.	Wang Z, Yang T, Zhu Y, et al. Multi-task learning for OSA detection and sleep staging via multi-scale modeling[J]. IEEE J Biomed Health Inform, 2026, 30(7): 5881-5893.
14.	Zhang Z, Lin B S, Peng C W, et al. Multi-modal sleep stage classification with two-stream encoder-decoder[J]. IEEE Trans Neural Syst Rehabil Eng, 2024, 32: 2096-2105.
15.	Zhou F, Lu Z, Wu Z, et al. WN-Sleep: modeling whole-night data for improved sleep staging classification[J]. IEEE J Biomed Health Inform, 2026, 30(4): 3013-3026.
16.	Cong Z, Zhao M, Gao H, et al. BiTS-SleepNet: an attention-based two stage temporal-spectral fusion model for sleep staging with single-channel EEG[J]. IEEE J Biomed Health Inform, 2025, 29(5): 3366-3376.
17.	Ren Z, Ma J, Ding Y. FlexibleSleepNet: a model for automatic sleep stage classification based on multi-channel polysomnography[J]. IEEE J Biomed Health Inform, 2025, 29(5): 3488-3501.
18.	Wang J, Wang X, Ning X, et al. Subject-adaptation salient wave detection network for multimodal sleep stage classification[J]. IEEE J Biomed Health Inform, 2025, 29(3): 2172-2184.
19.	Wolpert A E. A manual of standardized terminology, techniques and scoring system for sleep stages of human subjects[J]. Arch Gen Psychiatry, 1969, 20(2): 246-247.
20.	Alickovic E, Subasi A. Ensemble SVM method for automatic sleep stage classification[J]. IEEE Trans Instrum Meas, 2018, 67(6): 1258-1265.
21.	Phan H, Andreotti F, Cooray N, et al. SeqSleepNet: end-to-end hierarchical recurrent neural network for sequence-to-sequence automatic sleep staging[J]. IEEE Trans Neural Syst Rehabil Eng, 2019, 27(3): 400-410.
22.	Jia Z, Lin Y F, Wang J, et al. Multi-view spatial-temporal graph convolutional networks with domain generalization for sleep stage classification[J]. IEEE Trans Neural Syst Rehabil Eng, 2021, 29: 1977-1986.
23.	Chen J Y, Dai Y D, Chen X H, et al. StAGN: spatial-temporal adaptive graph network via contrastive learning for sleep stage classification[C]//Proceedings of the 2023 SIAM International Conference on Data Mining, Seattle: SIAM, 2025, 25(1): 199-207.
24.	Li Y, Chen J, Ma W, et al. MVF-SleepNet: multi-view fusion network for sleep stage classification[J]. IEEE J Biomed Health Inform, 2024, 28(5): 2485-2495.
25.	Dong H, Supratak A, Pan W, et al. Mixed neural network approach for temporal sleep stage classification[J]. IEEE Trans Neural Syst Rehabil Eng, 2017, 26(2): 324-333.
26.	Lyu J, Shi W, Zhang C, et al. A novel sleep staging method based on EEG and ECG multimodal features combination[J]. IEEE Trans Neural Syst Rehabil Eng, 2023, 31: 4073-4084.
27.	Lee Minji, Kang H, Yu S H, et al. Automatic sleep stage classification using nasal pressure decoding based on a multi-kernel convolutional BiLSTM network[J]. IEEE Trans Neural Syst Rehabil Eng, 2024, 32: 2533-2544.
28.	Eldele E, Ragab M, Chen Z, et al. Self-supervised learning for label-efficient sleep stage classification: a comprehensive evaluation[J]. IEEE Trans Neural Syst Rehabil Eng, 2023, 31: 1333-1342.
29.	Arsigny V, Fillard P, Pennec X, et al. Log-Euclidean metrics for fast and simple calculus on diffusion tensors[J]. Magn Reson Med, 2006, 56(2): 411-421.
30.	Ji X P, Li Y, Wen P. 3DSleepNet: a multi-channel bio-signal based sleep stages classification method using deep learning[J]. IEEE Trans Neural Syst Rehabil Eng, 2023, 31: 3513-3523.
31.	Huang Z W, Gool L V. A riemannian network for spd matrix learning[C]//Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, San Francisco: AAAI, 2017: 2036-2042.
32.	Memar P, Faradji F. A novel multi-class EEG-based sleep stage classification system[J]. IEEE Trans Neural Syst Rehabil Eng, 2018, 26(2): 84-95.
33.	Ji X P, Li Y, Wen P, et al. MixSleepNet: a multi-type convolution combined sleep stage classification model[J]. Comput Methods Programs Biomed, 2024, 244: 107992.
34.	Supratak A, Dong H, Wu C, et al. DeepSleepNet: a model for automatic sleep stage scoring based on raw single-channel EEG[J]. IEEE Trans Neural Syst Rehabil Eng, 2017, 25(11): 1998-2008.

1. 姚璐媛. 基于深度學習的腦電信號睡眠分期方法研究[D]. 蘭州: 蘭州理工大學, 2023: 12.
2. 王琪. 基于混合神經網絡的自動睡眠分期算法研究[D]. 南京: 南京信息工程大學, 2023: 56.
3. 田蘊郅, 周強, 李婉. 基于遷移學習的隨機深度殘差網絡自動睡眠分期算法[J]. 生物醫學工程學雜志, 2023, 40(2): 286-294.
4. 胡凱蕾, 陳景霞, 張鵬偉, 等. 用于睡眠精準分期的多模態生理時頻特征提取網絡[J]. 生物醫學工程學雜志, 2024, 41(1): 26-33.
5. 金崢, 賈克斌. 一種基于Transformer架構的多層級自動睡眠分期模型[J]. 電子學報, 2025, 53(2): 545-557.
6. 劉虹梅, 彭才靜, 韓芳, 等. 基于腦電多視圖混合神經網絡的時空半監督睡眠分期[J]. 工程科學學報, 2023, 45(5): 797-806.
7. 韓亮, 羅統軍, 蒲秀娟, 等. 使用異質集成學習和心電信號異構特征融合的睡眠呼吸暫停分類方法[J]. 儀器儀表學報, 2024, 45(6): 320-327.
8. 李思恒, 金蓓弘, 張扶桑, 等. 基于多任務注意力網絡的非接觸式睡眠監測[J]. 計算機研究與發展, 2024, 61(11): 2739-2753.
9. 趙倩, 李錦, 鳳飛龍, 等. 基于U2-Net和CBAM融合注意力的雙模態睡眠分期研究[J]. 陜西師范大學學報(自然科學版), 2025, 53(1): 1-11.
10. 王依純, 丁寧, 吳婷, 等. 腦機接口在睡眠障礙監測與干預中的應用進展[J]. 生物醫學轉化, 2025, 6(4): 1-6, 20.
11. Mads O, Jamie M Z, Risa N R, et al. A deep transfer learning approach for sleep stage classification and sleep apnea detection using wrist-worn consumer sleep technologies[J]. IEEE Trans Biomed Eng, 2024, 71(8): 2506-2517.
12. Wan C, Nnamdi M C, Shi W, et al. Advancing sleep disorder diagnostics: a transformer-based EEG model for sleep stage classification and OSA prediction[J]. IEEE J Biomed Health Inform, 2025, 29(2): 878-886.
13. Wang Z, Yang T, Zhu Y, et al. Multi-task learning for OSA detection and sleep staging via multi-scale modeling[J]. IEEE J Biomed Health Inform, 2026, 30(7): 5881-5893.
14. Zhang Z, Lin B S, Peng C W, et al. Multi-modal sleep stage classification with two-stream encoder-decoder[J]. IEEE Trans Neural Syst Rehabil Eng, 2024, 32: 2096-2105.
15. Zhou F, Lu Z, Wu Z, et al. WN-Sleep: modeling whole-night data for improved sleep staging classification[J]. IEEE J Biomed Health Inform, 2026, 30(4): 3013-3026.
16. Cong Z, Zhao M, Gao H, et al. BiTS-SleepNet: an attention-based two stage temporal-spectral fusion model for sleep staging with single-channel EEG[J]. IEEE J Biomed Health Inform, 2025, 29(5): 3366-3376.
17. Ren Z, Ma J, Ding Y. FlexibleSleepNet: a model for automatic sleep stage classification based on multi-channel polysomnography[J]. IEEE J Biomed Health Inform, 2025, 29(5): 3488-3501.
18. Wang J, Wang X, Ning X, et al. Subject-adaptation salient wave detection network for multimodal sleep stage classification[J]. IEEE J Biomed Health Inform, 2025, 29(3): 2172-2184.
19. Wolpert A E. A manual of standardized terminology, techniques and scoring system for sleep stages of human subjects[J]. Arch Gen Psychiatry, 1969, 20(2): 246-247.
20. Alickovic E, Subasi A. Ensemble SVM method for automatic sleep stage classification[J]. IEEE Trans Instrum Meas, 2018, 67(6): 1258-1265.
21. Phan H, Andreotti F, Cooray N, et al. SeqSleepNet: end-to-end hierarchical recurrent neural network for sequence-to-sequence automatic sleep staging[J]. IEEE Trans Neural Syst Rehabil Eng, 2019, 27(3): 400-410.
22. Jia Z, Lin Y F, Wang J, et al. Multi-view spatial-temporal graph convolutional networks with domain generalization for sleep stage classification[J]. IEEE Trans Neural Syst Rehabil Eng, 2021, 29: 1977-1986.
23. Chen J Y, Dai Y D, Chen X H, et al. StAGN: spatial-temporal adaptive graph network via contrastive learning for sleep stage classification[C]//Proceedings of the 2023 SIAM International Conference on Data Mining, Seattle: SIAM, 2025, 25(1): 199-207.
24. Li Y, Chen J, Ma W, et al. MVF-SleepNet: multi-view fusion network for sleep stage classification[J]. IEEE J Biomed Health Inform, 2024, 28(5): 2485-2495.
25. Dong H, Supratak A, Pan W, et al. Mixed neural network approach for temporal sleep stage classification[J]. IEEE Trans Neural Syst Rehabil Eng, 2017, 26(2): 324-333.
26. Lyu J, Shi W, Zhang C, et al. A novel sleep staging method based on EEG and ECG multimodal features combination[J]. IEEE Trans Neural Syst Rehabil Eng, 2023, 31: 4073-4084.
27. Lee Minji, Kang H, Yu S H, et al. Automatic sleep stage classification using nasal pressure decoding based on a multi-kernel convolutional BiLSTM network[J]. IEEE Trans Neural Syst Rehabil Eng, 2024, 32: 2533-2544.
28. Eldele E, Ragab M, Chen Z, et al. Self-supervised learning for label-efficient sleep stage classification: a comprehensive evaluation[J]. IEEE Trans Neural Syst Rehabil Eng, 2023, 31: 1333-1342.
29. Arsigny V, Fillard P, Pennec X, et al. Log-Euclidean metrics for fast and simple calculus on diffusion tensors[J]. Magn Reson Med, 2006, 56(2): 411-421.
30. Ji X P, Li Y, Wen P. 3DSleepNet: a multi-channel bio-signal based sleep stages classification method using deep learning[J]. IEEE Trans Neural Syst Rehabil Eng, 2023, 31: 3513-3523.
31. Huang Z W, Gool L V. A riemannian network for spd matrix learning[C]//Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, San Francisco: AAAI, 2017: 2036-2042.
32. Memar P, Faradji F. A novel multi-class EEG-based sleep stage classification system[J]. IEEE Trans Neural Syst Rehabil Eng, 2018, 26(2): 84-95.
33. Ji X P, Li Y, Wen P, et al. MixSleepNet: a multi-type convolution combined sleep stage classification model[J]. Comput Methods Programs Biomed, 2024, 244: 107992.
34. Supratak A, Dong H, Wu C, et al. DeepSleepNet: a model for automatic sleep stage scoring based on raw single-channel EEG[J]. IEEE Trans Neural Syst Rehabil Eng, 2017, 25(11): 1998-2008.

Journal of Biomedical Engineering

Multi-view signal integration via manifold learning for sleep stage classification

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content