Hybrid CNN for Sleep Stage Classification Based on EEG
DOI:
https://doi.org/10.30871/jaic.v10i3.12999Keywords:
CNN, EEG, Hybrid Features, Sleep Stage Classification, Stacking EnsembleAbstract
Sleep stage classification is essential for diagnosing sleep disorders such as insomnia and sleep apnea. However, manual scoring of polysomnography (PSG) is time consuming and subjective. Automatic systems based on single channel EEG are promising for home based monitoring, but they face challenges due to class imbalance and inter subject variability. This study proposes a hybrid model that combines 15 handcrafted features (statistical and spectral) with 128 dimensional features extracted by a one dimensional Convolutional Neural Network (1D CNN), followed by a stacking ensemble (Random Forest and Support Vector Machine as base learners, Logistic Regression as meta learner). Using 40 subjects from the Sleep EDF Expanded dataset, a strict subject independent split (80% train / 20% test) was applied to avoid data leakage. The dataset contained 107,258 epochs with extreme imbalance (Wake 67.6%, N1 2.95%). After SMOTE oversampling on the training set, the model achieved an accuracy of 67.5%, macro F1 score of 31.4%, and Cohen’s Kappa of 0.34. An ablation study showed that CNN features alone (72.2% accuracy) outperformed handcrafted features (70.4%) and hybrid features (67.5%). The confusion matrix revealed that minority stages (especially N1, N3, REM) were poorly recognized. These results highlight that cross subject generalization remains a major challenge in EEG based sleep staging, and proper subject independent validation is critical to avoid overoptimistic claims.
Downloads
References
[1] K. Aboalayon, M. Faezipour, W. Almuhammadi, and S. Moslehpour, “Sleep Stage Classification Using EEG Signal Analysis: A Comprehensive Survey and New Investigation,” Entropy, vol. 18, no. 9, p. 272, Aug. 2016, doi: 10.3390/e18090272.
[2] S. K. Satapathy, B. Brahma, B. Panda, P. Barsocchi, and A. K. Bhoi, “Machine learning-empowered sleep staging classification using multi-modality signals,” BMC Med. Inform. Decis. Mak., vol. 24, no. 1, p. 119, May 2024, doi: 10.1186/s12911-024-02522-2.
[3] Y. Zhang et al., “Sleep Stage Classification Using Bidirectional LSTM in Wearable Multi-sensor Systems,” Sep. 24, 2019, arXiv: arXiv:1909.11141. doi: 10.48550/arXiv.1909.11141.
[4] H. Almutairi, G. M. Hassan, and A. Datta, “Machine-Learning-Based-Approaches for Sleep Stage Classification Utilising a Combination of Physiological Signals: A Systematic Review,” Appl. Sci., vol. 13, no. 24, p. 13280, Dec. 2023, doi: 10.3390/app132413280.
[5] X. Cheng, K. Huang, Y. Zou, and S. Ma, “SleepEGAN: A GAN-enhanced Ensemble Deep Learning Model for Imbalanced Classification of Sleep Stages,” Jul. 04, 2023, arXiv: arXiv:2307.05362. doi: 10.48550/arXiv.2307.05362.
[6] X. Huang, K. Shirahama, M. T. Irshad, M. A. Nisar, A. Piet, and M. Grzegorzek, “Sleep Stage Classification in Children Using Self-Attention and Gaussian Noise Data Augmentation,” Sensors, vol. 23, no. 7, p. 3446, Mar. 2023, doi: 10.3390/s23073446.
[7] L. A. Moctezuma, Y. Suzuki, J. Furuki, M. Molinas, and T. Abe, “GRU-powered sleep stage classification with permutation-based EEG channel selection,” Sci. Rep., vol. 14, no. 1, p. 17952, Aug. 2024, doi: 10.1038/s41598-024-68978-4.
[8] Z. N. Nemer, S. A. W. Saddam, R. J. AL-Sukeinee, and E. J. Harfash, “A Comparative Performance Analysis of CNN, LSTM, and CNNLSTM Models for Classifying Sleep Stages Using Electroencephalography Signals,” Informatica, vol. 49, no. 28, Jul. 2025, doi: 10.31449/inf.v49i28.8082.
[9] Q. Wan et al., “Automated sleep staging from single-channel electroencephalogram using hybrid neural network with manual features and attention,” iScience, vol. 28, no. 8, p. 113169, Aug. 2025, doi: 10.1016/j.isci.2025.113169.
[10] T. I. Toma and S. Choi, “An End-to-End Multi-Channel Convolutional Bi-LSTM Network for Automatic Sleep Stage Detection,” Sensors, vol. 23, no. 10, p. 4950, May 2023, doi: 10.3390/s23104950.
[11] M. K. Delimayanti et al., “Classification of Brainwaves for Sleep Stages by High-Dimensional FFT Features from EEG Signals,” Appl. Sci., vol. 10, no. 5, p. 1797, Mar. 2020, doi: 10.3390/app10051797.
[12] B. Kemp, A. H. Zwinderman, B. Tuk, H. A. C. Kamphuisen, and J. J. L. Oberye, “Analysis of a sleep-dependent neuronal feedback loop: the slow-wave microcontinuity of the EEG,” IEEE Trans. Biomed. Eng., vol. 47, no. 9, pp. 1185–1194, 2000, doi: 10.1109/10.867928.
[13] H. W. Loh et al., “Automated Detection of Sleep Stages Using Deep Learning Techniques: A Systematic Review of the Last Decade (2010–2020),” Appl. Sci., vol. 10, no. 24, p. 8963, Dec. 2020, doi: 10.3390/app10248963.
[14] A. K. Singh and S. Krishnan, “Trends in EEG signal feature extraction applications,” Front. Artif. Intell., vol. 5, p. 1072801, Jan. 2023, doi: 10.3389/frai.2022.1072801.
[15] M. Kolhar et al., “Automated Sleep Stage Classification Using PSO-Optimized LSTM on CAP EEG Sequences,” Brain Sci., vol. 15, no. 8, p. 854, Aug. 2025, doi: 10.3390/brainsci15080854.
[16] H. Jalali, M. Pouladian, A. M. Nasrabadi, and A. Movahed, “Sleep stages classification based on feature extraction from music of brain,” Heliyon, vol. 11, no. 1, p. e41147, Jan. 2025, doi: 10.1016/j.heliyon.2024.e41147.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Maria Angelina Cahyani Candrakasih, Bagus Adhi Kusuma, Pungkas Subarkah
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
