Optimization of The Process of Identifying Sleep-Disordered‎Breathing Based on CNN and LSTM Recurrent NeuralNetworks ‎Using PSG EEG Signals

  • Authors

    • Manoj K College of Engineering, Anna University, Chennai, India
    • Athiamaan R College of Engineering, Anna University, Chennai, India
    https://doi.org/10.14419/d7tqy474

    Received date: October 14, 2025

    Accepted date: December 4, 2025

    Published date: December 10, 2025

  • Respiratory Effort-Related Arousal; Polysomnographic; Electroencephalography; Long-Short Term Memory; Convolutional Neural Networks

  • Abstract

    One of the challenges of Clinical polysomnographic (PSG) Datasets is the volume of information they contain, as they can consist of hun-‎dreds to thousands of PSG records, and each PSG record contains more than a dozen clinical time series about eight hours in length. Manu-‎al analysis of such datasets is a slow and laborious process, which is highly dependent on the experience and skill of the sleep technologist ‎and consequently limits PSG-based sleep-related studies. The main objective of this project is the automatic identification of arousals due to ‎respiratory events, specifically RERA (Respiratory Effort-Related Arousal) events and events associated with apnea/hypopnea using PSG ‎electroencephalography (EEG) signals. This paper implements technique to deal with data imbalance and improve systems performance in ‎identifying Respiratory events, design and implements different classification systems for identifying arousals related to respiratory events ‎using PSG EEG signals. Also analyze the performance obtained for each of the implemented classifiers compared to the models presented ‎in the literature. For this four systems were developed based on convolutional neural networks (CNN) and Long-Short Term Memory ‎‎(LSTM) recurrent neural networks. In this context, this research aims to contribute to the optimization of the process of identifying sleep-‎disordered breathing.

  • References

    1. Salari, N., Hosseinian, A. F., Mohammadi, M. H., et al. (2022). Detection of sleep apnea using machine learning algorithms based on ECG signals: A comprehensive systematic review. Expert Systems with Applications, 187, Article ID 115950. https://doi.org/10.1016/j.eswa.2021.115950.
    2. Devnani, P. A., & Hegde, A. U. (2015). Autism and sleep disorders. Journal of Pediatric Neurosciences, 10, 304. https://doi.org/10.4103/1817-1745.174438
    3. French, I. T., & Muthusamy, K. A. (2016). A review of sleep and its disorders in patients with Parkinson’s disease in relation to various brain struc-tures. Frontiers in Aging Neuroscience, 8, 114. https://doi.org/10.3389/fnagi.2016.00114
    4. Dauvilliers, Y., Zammit, G., Fietze, I., et al. (2020). Daridorexant, a new dual orexin receptor antagonist to treat insomnia disorder. Annals of Neu-rology, 87, 347–356. https://doi.org/10.1002/ana.25680.
    5. Korompili, G., Kokkalas, L., Mitilineos, S. A., Tatlas, N. A., & Potirakis, S. M. (2021). Detecting apnea/hypopnea events time location from sound recordings for patients with severe or moderate sleep apnea syndrome. Applied Sciences, 11, 6888. https://doi.org/10.3390/app11156888
    6. Hospitals, M. G., Laboratory, C. C. N., & The Clinical Data Animation Laboratory. (2018). Physionet/CinC Challenge 2018: Training/test sets.
    7. Zhang, R., Zheng, X., Zhang, L., Xu, Y., Lin, X., Wang, X., Wu, C., Jiang, F., & Wang, J. (2024). LANMAO sleep recorder versus polysomnogra-phy in neonatal EEG recording and sleep analysis. Journal of Neuroscience Methods, 410, 110222. https://doi.org/10.1016/j.jneumeth.2024.110222.
    8. Dritsas, E., & Trigka, M. (2024). Utilizing multi-class classification methods for automated sleep disorder prediction. Information, 15, 426. https://doi.org/10.3390/info15080426
    9. Hamouda, G. B., Rejeb, L., & Said, L. B. (2024). Ensemble learning for multi-channel sleep stage classification. Biomedical Signal Processing and Control, 93, 106184. https://doi.org/10.1016/j.bspc.2024.106184
    10. Jha, P. K., Valekunja, U. K., & Reddy, A. B. (2024). SlumberNet: Deep learning classification of sleep stages using residual neural networks. Scien-tific Reports, 14, 4797. https://doi.org/10.1038/s41598-024-54727-0.
    11. Famà, F., Arnulfo, G., Arnaldi, D., Kim, H. J., & Jung, K. Y. (2024). EEG-based machine learning models for the prediction of phenoconversion time and subtype in isolated rapid eye movement sleep behavior disorder. Sleep, 47, zsae031. https://doi.org/10.1093/sleep/zsae031
    12. Hidalgo Rogel, J. M., Martínez Beltrán, E. T., Quiles Pérez, M., López Bernal, S., Martínez Pérez, G., & Huertas Celdrán, A. (2024). Studying drowsiness detection performance while driving through scalable machine learning models using electroencephalography. Cognitive Computation, 16, 1253–1267. https://doi.org/10.1007/s12559-023-10233-5
    13. El Hadiri, A., Bahatti, L., El Magri, A., & Lajouad, R. (2024). Sleep stages detection based on analysis and optimisation of non-linear brain signal parameters. Results in Engineering, 23, 102664. https://doi.org/10.1016/j.rineng.2024.102664
    14. Guo, Y., Nowakowski, M., & Dai, W. (2024). FlexSleepTransformer: A transformer-based sleep staging model with flexible input channel configu-rations. Scientific Reports, 14, 26312. https://doi.org/10.1038/s41598-024-76197-0.
    15. Heremans, E. R., Seedat, N., Buyse, B., Testelmans, D., van der Schaar, M., & De Vos, M. (2024). U-PASS: An uncertainty-guided deep learning pipeline for automated sleep staging. Computers in Biology and Medicine, 171, 108205. https://doi.org/10.1016/j.compbiomed.2024.108205.
    16. Ganglberger, W., Nasiri, S., Sun, H., Kim, S., Shin, C., Westover, M. B., & Thomas, R. J. (2024). Transfer learning coupled with scorability models to improve sleep staging accuracy. Sleep, 47, zsae202. https://doi.org/10.1093/sleep/zsae202
    17. Zaman, A., Kumar, S., Shatabda, S., Dehzangi, I., & Sharma, A. (2024). SleepBoost: A multi-level tree-based ensemble model for sleep stage clas-sification. Medical & Biological Engineering & Computing, 62, 2769–2783. https://doi.org/10.1007/s11517-024-03096-x
    18. Kolhar, M., Alfuraydan, M. M., Alshammary, A., Alharoon, K., Alghamdi, A., Albader, A., Alnawah, A., & Alanazi, A. (2025). Automated sleep stage classification using PSO-optimized LSTM on CAP EEG sequences. Brain Sciences, 15(8), 854. https://doi.org/10.3390/brainsci15080854
    19. Schellenberger, S., Shi, K., Mai, M., Wiedemann, J. P., Steigle-Der, T., Eskofier, B., Weigel, R., & Kölpin, A. (2018). Detecting respiratory effort-related arousals in polysomnographic data using LSTM networks. In 2018 Computing in Cardiology Conference (CINC), 45, 1–4. IEEE. https://doi.org/10.22489/CinC.2018.104
    20. Kumar, M. R., & Rao, Y. S. (2019). Epileptic seizures classification in EEG signal based on semantic features and variational mode decomposition. Cluster Computing, 22(6), 13521–13531. https://doi.org/10.1007/s10586-018-1995-4.
    21. Yu, H., Liu, D., Zhao, J., et al. (2022). A sleep apnea-hypopnea syndrome automatic detection and subtype classification method based on LSTM-CNN. Biomedical Signal Processing and Control, 71, 103240. https://doi.org/10.1016/j.bspc.2021.103240
    22. Lestari, F. P., Haekal, M., Edison, R. E., Fauzy, F. R., Khotimah, S. N., & Haryanto, F. (2020). Epileptic seizure detection in EEGs by using ran-dom tree forest, naïve bayes and KNN classification. Journal of Physics: Conference Series, 1505, 012055. IOP Publishing. https://doi.org/10.1088/1742-6596/1505/1/012055.
    23. Edla, D. R., Mangalorekar, K., Dhavalikar, G., & Dodia, S. (2018). Classification of EEG data for human mental state analysis using random forest classifier. Procedia Computer Science, 132, 1523–1532. https://doi.org/10.1016/j.procs.2018.05.116
    24. Rodrigues, J. D. C., Rebouças Filho, P. P., Peixoto Jr, E., Kumar, A., & De Albuquerque, V. H. C. (2019). Classification of EEG signals to detect alcoholism using machine learning techniques. Pattern Recognition Letters, 125, 140–149. https://doi.org/10.1016/j.patrec.2019.04.019
    25. Kaya, Y., & Ertuğrul, Ö. F. (2018). A stable feature extraction method in classification epileptic EEG signals. Australasian Physical & Engineering Sciences in Medicine, 41, 721–730. https://doi.org/10.1007/s13246-018-0669-0
    26. Lv, X., & Li, J. (2020). A multi-level features fusion network for detecting obstructive sleep apnea hypopnea syndrome. In Proceedings of the 2020 International Conference on Algorithms and Architectures for Parallel Processing (ICA3PP), 509–519. Berlin, Germany. https://doi.org/10.1007/978-3-030-60248-2_34.
    27. Cohen, M. X. (2014). Analyzing neural time series data: theory and practice. MIT Press. https://doi.org/10.7551/mitpress/9609.001.0001
    28. Phan, H., & Mikkelsen, K. (2022). Automatic sleep staging of EEG signals: recent development, challenges, and future directions. Physiological Measurement, 43, 04TR01. https://doi.org/10.1088/1361-6579/ac6049.
    29. Chiranjeevi, R., & Dixit, U. (2017). A note on clamped Simpson’s rule. Global Journal of Pure and Applied Mathematics, 13, 5275–5285.
    30. Shen, Q., Yang, X., Zou, L., Wei, K., Wang, C., & Liu, G. (2022). Multitask residual shrinkage convolutional neural network for sleep-apnea detec-tion based on wearable bracelet photoplethysmography. IEEE Internet of Things Journal, 9, 25207–25222. https://doi.org/10.1109/JIOT.2022.3195777
    31. Haghayegh, S., Hu, K., Stone, K., Redline, S., & Schernhammer, E. (2023). Automated sleep stages classification using convolutional neural net-work from raw and time-frequency electroencephalogram signals: systematic evaluation study. Journal of Medical Internet Research, 25, e40211. https://doi.org/10.2196/40211.
    32. Bhattacharjee, T., Das, D., Alam, S., Rao, A., Ghosh, P. K., Lohani, A. R., Banerjee, R., Choudhury, A. D., & Pal, A. (2018). SleepTight: Identify-ing sleep arousals using inter and intra-relation of multimodal signals. In 2018 Computing in Cardiology Conference (CINC), 45, 1–4. IEEE. https://doi.org/10.22489/CinC.2018.245.
    33. Biswal, S., Sun, H., Goparaju, B., Westover, M. B., Sun, J., & Bianchi, M. T. (2018). Expert-level sleep scoring with deep neural networks. Journal of the American Medical Informatics Association, 25, 1643–1650. https://doi.org/10.1093/jamia/ocy131
    34. Sadr, N., & De Chazal, P. (2018). Automatic scoring of non-apnoea arousals using the polysomnogram. In 2018 Computing in Cardiology Confer-ence (CINC), 45, 1–4. IEEE. https://doi.org/10.22489/CinC.2018.252
    35. Rao, A., Ghosh, P. K., Bhattacharjee, T., & Choudhury, A. D. (2019). Trend statistics network and channel invariant EEG network for sleep arous-al study. In 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 5716–5722. IEEE. https://doi.org/10.1109/EMBC.2019.8857553.
    36. Shoeb, A., & Sridhar, N. (2018). Evaluating convolutional and recurrent neural network architectures for respiratory-effort related arousal detection during sleep. In 2018 Computing in Cardiology Conference (CINC), 45, 1–4. IEEE. https://doi.org/10.22489/CinC.2018.284.

  • Downloads

  • How to Cite

    K, M., & R, A. (2025). Optimization of The Process of Identifying Sleep-Disordered‎Breathing Based on CNN and LSTM Recurrent NeuralNetworks ‎Using PSG EEG Signals. International Journal of Basic and Applied Sciences, 14(8), 174-197. https://doi.org/10.14419/d7tqy474