Detection of Deep Sleep Stages in Multi-Channel EEG Signals Based on Spectral Feature Quantification Methods

Jinsha Liu; Chengyuan Shen; Liangyu Zhao; Taiyo Maeda; Jianting Cao

doi:10.24297/ijct.v25i.9809

Authors

Jinsha Liu Graduate School of Engineering, Saitama Institute of Technology, Fukaya City, Saitama, Japan
Chengyuan Shen RIKEN Center for Advanced Intelligence Project (AIP), Chuo-ku, Tokyo, Japan
Liangyu Zhao Keio University, Yokohama City, Kanagawa, Japan
Taiyo Maeda More & More Company Limited, Zushi City, 2490006, Kanagawa, Japan
Jianting Cao Graduate School of Engineering, Saitama Institute of Technology, Fukaya City, Saitama, Japan

DOI:

https://doi.org/10.24297/ijct.v25i.9809

Keywords:

Data Processing, Deep learning, Sleep Monitoring, BCI, EEG

Abstract

Deep sleep is essential for physical recovery and cognitive function. Accurate detection is crucial for evaluating sleep quality and diagnosing related disorders. Electroencephalography (EEG) remains the most reliable tool for assessing deep sleep. However, while deep learning methods have shown high performance, they often suffer from limited interpretability and require substantial computational resources, which can hinder real-time clinical applications. This study proposes a novel multi-channel EEG analysis approach combining Turning Tangent Empirical Mode Decomposition (2T-EMD) and Multi-Taper Power Spectral Density (MT-PSD) to extract physiologically meaningful spectral features, followed by classification using a Random Forest (RF) model. The method was validated on 61 recordings from 41 participants, achieving 95.57% accuracy, 97.35% recall, 97.58% F1-score, and 99.00% AUC. Compared with existing approaches, our method demonstrates (1) physiologically interpretable feature extraction; (2) favorable computational efficiency under our experimental setup; and (3) robust generalizability across different demographics, indicating its potential utility in clinical sleep monitoring scenarios.

Downloads

Download data is not yet available.

References

Aboalayon, K. A. I., Faezipour, M., Almuhammadi, W. S., & Moslehpour, S. (2016). Sleep stage classification using eeg signal analysis: A comprehensive survey and new investigation. Entropy, 18(9), 272.

Andrzejak, R. G., Schindler, K., & Rummel, C. (2012). Nonrandomness, nonlinear dependence, and nonstationarity of electroencephalographic recordings from epilepsy patients [DOI: https://doi.org/10.1103/PhysRevE.86.046206]. Physical Review E, 86(4), 046206. Babadi, B., & Brown, E. N. (2014). A review of multitaper spectral analysis. IEEE Transactions on Biomedical Engineering, 61(5), 1555–1564. Cao, J., & Chen, Z. (2008). Advanced eeg signal processing in brain death diagnosis [DOI: https://doi.org/10.1007/978-0387-74367-7_15]. In Signal processing techniques for knowledge extraction and information fusion (pp. 275–298). Springer. Chambon, S., Thorey, V., Arnal, P., Mignot, E., & Olivetti, A. H. (2018). A deep learning architecture for temporal sleep stage classification using multivariate and multimodal time series. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 26(4), 758–769. https://doi.org/10.1109/TNSRE.2018.2813138 Chen, Q., Yuan, L., Miao, Y., Zhao, Q., Tanaka, T., & Cao, J. (2019). Quasi-brain-death eeg diagnosis based on tensor train decomposition [DOI: https://doi.org/10.1007/978-3-030-22808-8_49]. International Symposium on Neural Networks, 501–511. Chokroverty, S. (2010). Overview of sleep & sleep disorders. Indian Journal of Medical Research, 131(2), 126–140. Eldele, E., Chen, Z., Liu, C., Wu, M., Kwoh, C.-K., Li, X., & Guan, C. (2021). An attention-based deep learning approach for sleep stage classification with single-channel eeg [DOI: https://doi.org/10.1109/TNSRE.2021.3076234]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 29, 809–818. Fattinger, S., de Beukelaar, T. T., Ruddy, K. L., Volk, C., Heyse, N. C., Herbst, J. A., Hahnloser, R. H., Wenderoth, N., & Huber, R. (2017). Deep sleep maintains learning efficiency of the human brain. Nature communications, 8(1), 15405. Flandrin, P., Rilling, G., & Goncalves, P. (2004). Empirical mode decomposition as a filter bank [DOI: https://10.1109/LSP.2003.821662]. IEEE signal processing letters, 11(2), 112–114. Fleureau, J., Nunes, J.-C., Kachenoura, A., Albera, L., & Senhadji, L. (2010). Turning tangent empirical mode decomposition: A framework for mono-and multivariate signals [DOI: https://10.1109/TSP.2010.2097254]. IEEE Transactions on signal Processing, 59(3), 1309–1316. Gabriel-Alexandru, V., & Mihaela-Ruxandra, L. (2024). Deep learning for sleep staging using eeg signals [DOI: https://10.1109/ISETC63109.2024.10797312]. 2024 International Symposium on Electronics and Telecommunications (ISETC), 1–8. Heckbert, P. (1995). Fourier transforms and the fast fourier transform (fft) algorithm [Lecture Notes, Carnegie Mellon University]. Computer Graphics, 2, 15–463. https://www.cs.cmu.edu/afs/cs/project/anim/ph/463.95/pub/ www/notes.toc.html Jin, Z., & Jia, K. (2023). Sagsleepnet: A deep learning model for sleep staging based on self-attention graph of polysomnography [DOI: https://doi.org/10.1016/j.bspc.2023.105062]. Biomedical Signal Processing and Control, 86, 105062. Kemp, B., Zwinderman, A. H., Tuk, B., Kamphuisen, H. A., & Oberye, J. J. (2000). Analysis of a sleep-dependent neuronal feedback loop: The slow-wave microcontinuity of the eeg [DOI: https://ieeexplore.ieee.org/document/867928]. IEEE Transactions on Biomedical Engineering, 47(9), 1185–1194. Lozzi, D., Di Matteo, A., Mattei, E., Cipriani, A., Caianiello, P., Mignosi, F., & Placidi, G. (2024). Asis: A smart alarm clock based on deep learning for the safety of night workers [DOI: https://10.1109/MetroXRAINE62247.2024.10796738]. 2024 IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering (MetroXRAINE), 1129–1134.

Andrzejak, R. G., Schindler, K., & Rummel, C. (2012). Nonrandomness, nonlinear dependence, and nonstationarity of electroencephalographic recordings from epilepsy patients [DOI: https://doi.org/10.1103/PhysRevE.86.046206]. Physical Review E, 86(4), 046206. Babadi, B., & Brown, E. N. (2014). A review of multitaper spectral analysis. IEEE Transactions on Biomedical Engineering, 61(5), 1555–1564. Cao, J., & Chen, Z. (2008). Advanced eeg signal processing in brain death diagnosis [DOI: https://doi.org/10.1007/978-0387-74367-7_15]. In Signal processing techniques for knowledge extraction and information fusion (pp. 275–298). Springer. Chambon, S., Thorey, V., Arnal, P., Mignot, E., & Olivetti, A. H. (2018). A deep learning architecture for temporal sleep stage classification using multivariate and multimodal time series. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 26(4), 758–769. https://doi.org/10.1109/TNSRE.2018.2813138 Chen, Q., Yuan, L., Miao, Y., Zhao, Q., Tanaka, T., & Cao, J. (2019). Quasi-brain-death eeg diagnosis based on tensor train decomposition [DOI: https://doi.org/10.1007/978-3-030-22808-8_49]. International Symposium on Neural Networks, 501–511. Chokroverty, S. (2010). Overview of sleep & sleep disorders. Indian Journal of Medical Research, 131(2), 126–140. Eldele, E., Chen, Z., Liu, C., Wu, M., Kwoh, C.-K., Li, X., & Guan, C. (2021). An attention-based deep learning approach for sleep stage classification with single-channel eeg [DOI: https://doi.org/10.1109/TNSRE.2021.3076234]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 29, 809–818. Fattinger, S., de Beukelaar, T. T., Ruddy, K. L., Volk, C., Heyse, N. C., Herbst, J. A., Hahnloser, R. H., Wenderoth, N., & Huber, R. (2017). Deep sleep maintains learning efficiency of the human brain. Nature communications, 8(1), 15405. Flandrin, P., Rilling, G., & Goncalves, P. (2004). Empirical mode decomposition as a filter bank [DOI: https://10.1109/LSP.2003.821662]. IEEE signal processing letters, 11(2), 112–114. Fleureau, J., Nunes, J.-C., Kachenoura, A., Albera, L., & Senhadji, L. (2010). Turning tangent empirical mode decomposition: A framework for mono-and multivariate signals [DOI: https://10.1109/TSP.2010.2097254]. IEEE Transactions on signal Processing, 59(3), 1309–1316. Gabriel-Alexandru, V., & Mihaela-Ruxandra, L. (2024). Deep learning for sleep staging using eeg signals [DOI: https://10.1109/ISETC63109.2024.10797312]. 2024 International Symposium on Electronics and Telecommunications (ISETC), 1–8. Heckbert, P. (1995). Fourier transforms and the fast fourier transform (FFT) algorithm [Lecture Notes, Carnegie Mellon University]. Computer Graphics, 2, 15–463. https://www.cs.cmu.edu/afs/cs/project/anim/ph/463.95/pub/ www/notes.toc.html Jin, Z., & Jia, K. (2023). Sagsleepnet: A deep learning model for sleep staging based on self-attention graph of polysomnography [DOI: https://doi.org/10.1016/j.bspc.2023.105062]. Biomedical Signal Processing and Control, 86, 105062. Kemp, B., Zwinderman, A. H., Tuk, B., Kamphuisen, H. A., & Oberye, J. J. (2000). Analysis of a sleep-dependent neuronal feedback loop: The slow-wave microcontinuity of the EEG [DOI: https://ieeexplore.ieee.org/document/867928]. IEEE Transactions on Biomedical Engineering, 47(9), 1185–1194. Lozzi, D., Di Matteo, A., Mattei, E., Cipriani, A., Caianiello, P., Mignosi, F., & Placidi, G. (2024). Asis: A smart alarm clock based on deep learning for the safety of night workers [DOI: https://10.1109/MetroXRAINE62247.2024.10796738]. 2024 IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering (MetroXRAINE), 1129–1134.