A Comparative Performance Analysis of CNN, LSTM, and CNNLSTM Models for Classifying Sleep Stages Using Electroencephalography Signals
Abstract
This paper aims to study and analyze the performance of CNN, LSTM and CNN+LSTM deep neural networks individually in the problem of sleep cycle stage classification, by analyzing the recorded EEG signals, and highlight the strengths of each model in this classification problem. The deep learning models selected in this work are reliable models in the world of experiments and medical classification. The data used here is the EEG signal represented by the sleep-edf-expanded-npzs database which carries information about the different sleep stages, which are five stages: wakefulness (W), non-REM stage 1 (N1), non-REM stage 2 (N2), non-REM stage 3 (N3), and rapid eye movement (REM). This data was split by training by 70% and testing by 30%. The models were trained based on cross-entropy loss and Adam optimizer. The results obtained in this study showed that the classification rates are as follows: CNN model accuracy (0.8736%), LSTM model accuracy (0.8306%), and LSTM + CNN hybrid model accuracy (0.8813%). These results indicate the good performance of the CNN model, which can be attributed to its strong ability to extract spatial features from data. The results of the LSTM approach demonstrate its ability to track and interpret the temporal characteristics of the sleep signal. For the CNN-LSTM model, which combines the strengths of temporal LSTM and spatial CNN, the result of combining features in this sequence showed superior results than either CNN or LSTM alone in processing sleep signals. Statistical measures were used to validate the results obtained. The F-statistic was 949.78666666523 and the probability value was 6.119863 e-14, which validate the results obtained for each model.References
Walker, M. P. (2017). Why We Sleep: Unlocking the Power of Sleep and Dreams. Scribner, Publisher: Scribner , Length: 368 pagesISBN13: 9781501144325
Siegel, J. M. (2005). Clues to the functions of mammalian sleep. Nature, 437(7063), 1264–1271. https://doi.org/10.1038/nature04285
Rechtschaffen, A., & Kales, A. (1968). A manual of standardized terminology, techniques and scoring system for sleep stages of human subjects., U.S. Department of Health, Education, and Welfare.
Iber, C., Ancoli-Israel, S., & Chesson, A. (2007). The AASM manual for the scoring of sleep and associated events. Medicine , American Academy.
Sanei, S., & Chambers, J. A. (2013). EEG Signal Processing. John Wiley & Sons, 1118691237, 9781118691236.
Lopes da Silva, F. (2005). "Electroencephalography: Basic principles, clinical applications, and related fields",Lippincott Williams&Wikins,
Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735-1780. http://dx.doi.org/10.1162/neco.1997.9.8.1735.
Chengfan L., Yueyu Q. and Xuehai D. (2022). A "Deep Learning Method Approach for Sleep Stage Classification with EEG Spectrogram", PMCID: PMC9141573 PMID: 35627856. . https://doi.org/10.3390/ijerph19106322
Tsinalis, O., Matthews, P. M., & Guo, Y. (2016). Automatic sleep stage scoring using time-frequency analysis and stacked sparse autoencoders. Annals of Biomedical Engineering. https://doi.org/10.48550/arXiv.1610.01683
Sasai, S., Koike, T., Sugawara, S. K., Okazaki, S., Watanabe, K., Sadato, N., & Iguchi, Y. (2017). "Network-wide reorganization of procedural memory during NREM sleep revealed by fMRI". eLife, 6, e24987. https://doi.org/10.7554/eLife.24987
Nicola M., U.Rajendra A., Filippo M. (2019). Cascaded LSTM recurrent neural network for automated sleep stage classification using single-channel EEG signals. Computers in Biology and MedicineVolume 106,Pages 71-81. https://doi.org/10.1016/j.compbiomed.2019.01.013
Asma Salamatian and Ali Khadem . (2022
).Automatic Sleep Stage Classification Using 1D Convolutional Neural Network. Frontiers in Biomedical Technologies.Vol. 7, No. 3. http://dx.doi.org/10.18502/fbt.v7i3.4616
Huijun Y., Zhuqi C., Wenbin G., Lin S. and Yidan D. (2024). " Research and application of deep learning-based sleep staging: Data, modeling, validation, and clinical practice." Sleep Medicine Reviews.Volume 74, 101897.
https://doi.org/10.1016/j.smrv.2024.101897
Luic A., Takashi A.and Marta Molinas (2023):" EEG-based 5- and 2-class CNN for Sleep Stage Classification." , IFAC-PapersOnLine ,Volume 56, Issue 2, Pages 3211-3216. https://doi.org/10.1016/j.ifacol.2023.10.1458
Enes E., Seral O. (2023). "CoSleepNet: Automated sleep staging using a hybrid CNN-LSTM network on imbalanced EEG-EOG datasets." Biomedical Signal Processing and Control ,Volume 80, Part 1, February, 104299. https://doi.org/10.1016/j.bspc.2022.104299
Kotla R. and Polavarapu N. and Safa P. (2023)." A CNN-LSTM Model for Sleep Stage Scoring Using EEG Signals": 2023 International Conference on Communication, Circuits, and Systems (IC3S). https://doi.org/10.1109/IC3S57698.2023.1016917
Ralf C. Staudemeyer and Eric R. (2019). " Understanding LSTM -- a tutorial into Long Short-Term Memory Recurrent Neural Networks", arXiv:1909.09586v1 [cs.NE] 12 Sep 2019. http://dx.doi.org/10.48550/arXiv.1909.09586
.
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). "Gradient-based learning applied to document recognition." Proceedings of the IEEE.
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). "ImageNet classification with deep convolutional neural networks." Advances in Neural Information Processing Systems.
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press. https://doi.org/10.1007/s10710-017-9314-z
Ghita A. ,Amina A., and Mohammed B. (2022). " EEG signal analysis using deep learning: A systematic literature review." 2021 Fifth International Conference On Intelligent Computing in Data Sciences (ICDS). https://doi.org/10.1109/ICDS53782.2021.9626707
Roy, Y., & Banville, H. (2019). " Deep learning-based electroencephalography analysis: a systematic review" Frontiers in Neuroscience. https://doi.org/10.1088/1741-2552/ab260c
G. Sudhamathy, N. Valliammal, P. Subashini, T. T. Dhivyanrabha and R. G. Sneha, "Hybrid Convolutional Neural Network - Long Short-Term Memory Model for Automated Detection of Sleep Stages," 2023 International Conference on Intelligent Systems for Communication, IoT and Security (ICISCoIS), Coimbatore, India, 2023, pp. 510-515,
https://doi.org/10.1109/ICISCoIS56541.2023.10100489
Phan, H., et al. (2019). "SeqSleepNet: End-to-end hierarchical recurrent neural network for sequence-to-sequence automatic sleep staging." IEEE Transactions on Neural Systems and Rehabilitation Engineering. https://doi.org/10.1109/TNSRE.2019.2896659.
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. IEEE Transactions on Biomedical Engineering, 47(9), 1185–1194. https://doi.org/10.1109/10.867928
Goldberger, A. L., Amaral, L. A. N., Glass, L., et al. (2000). PhysioBank, PhysioToolkit, and PhysioNet: Components of a New Research Resource for Complex Physiologic Signals. Circulation, 101(23), e215-e220. http://dx.doi.org/10.1161/01.CIR.101.23.e215
DOI:
https://doi.org/10.31449/inf.v49i28.8082Downloads
Additional Files
- Performance evaluation study of CNN, LSTM and CNN-LSTM models in the problem of sleep stage classification based on EEG signals
- Performance evaluation study of CNN, LSTM and CNN-LSTM models in the problem of sleep stage classification based on EEG signals
- Performance evaluation study of CNN, LSTM and CNN-LSTM models in the problem of sleep stage classification based on EEG signals
Published
How to Cite
Issue
Section
License
I assign to Informatica, An International Journal of Computing and Informatics ("Journal") the copyright in the manuscript identified above and any additional material (figures, tables, illustrations, software or other information intended for publication) submitted as part of or as a supplement to the manuscript ("Paper") in all forms and media throughout the world, in all languages, for the full term of copyright, effective when and if the article is accepted for publication. This transfer includes the right to reproduce and/or to distribute the Paper to other journals or digital libraries in electronic and online forms and systems.
I understand that I retain the rights to use the pre-prints, off-prints, accepted manuscript and published journal Paper for personal use, scholarly purposes and internal institutional use.
In certain cases, I can ask for retaining the publishing rights of the Paper. The Journal can permit or deny the request for publishing rights, to which I fully agree.
I declare that the submitted Paper is original, has been written by the stated authors and has not been published elsewhere nor is currently being considered for publication by any other journal and will not be submitted for such review while under review by this Journal. The Paper contains no material that violates proprietary rights of any other person or entity. I have obtained written permission from copyright owners for any excerpts from copyrighted works that are included and have credited the sources in my article. I have informed the co-author(s) of the terms of this publishing agreement.
Copyright © Slovenian Society Informatika
