Abstract
The common existing methods for performing the sleep stage classification include the time domain-based approaches, the frequency domain-based approaches and the time frequency domain-based approaches. However, the structures imposed by the transforms sometimes result to the poor classification performances. Recently, the deep learning-based methods such as the convolutional neural network-based methods are proposed. However, the required computational power for performing the training is very high. To address these issues, this paper proposes a dynamic mode decomposition-based (DMD) approach for performing the sleep stage classification. The DMD is a time space analysis-based approach. First, the polysomnograms including a single channel of the electroencephalograms and a single channel of the electrooculograms are acquired. Then, the DMD is applied to the epochs of these signals. Next, the dynamic mode powers of the components decomposed by the DMD are computed and they are employed as the features. After that, the random forest is employed for performing the classification. The computer numerical simulations are conducted using two datasets. They are the sleep EDF dataset and the sleep EDF expanded dataset. Here, the durations of the signals are 30 s. As our proposed method exploits the relationship between the temporal electric field influence and the spatial electric field influence among the channels, our proposed method outperforms the existing methods. In particular, our proposed method yields the classification accuracy and the Cohen’s Kappa coefficient at 99.8748% and 0.9980, respectively, for the six sleep stage classification.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data availability
The data and the other materials will be provided if they are requested.
References
Hartmann, C., Kempf, A.: Mitochondrial control of sleep. Curr. Opin. Neurobiol. 81, 102733 (2023)
A Rechtschaffen, (1968) A manual for standardized terminology, techniques and scoring system for sleep stages in human subjects, Brain information service.
Berry, R.B., Brooks, R., Gamaldo, C.E., Harding, S.M., Marcus, C., Vaughn, B.V., et al.: The aasm manual for the scoring of sleep and associated events. Rules, Terminol. Tech. Specific. Darien, Illinois, American Acad. Sleep Med. 176, 2012 (2012)
Sokolovsky, M., Guerrero, F., Paisarnsrisomsuk, S., Ruiz, C., Alvarez, S.A.: Deep learning for automated feature discovery and classification of sleep stages. IEEE/ACM Trans. Comput. Biol. Bioinf. 17(6), 1835–1845 (2019)
Flexer, A., Gruber, G., Dorffner, G.: A reliable probabilistic sleep stager based on a single eeg signal. Artif. Intell. Med. 33(3), 199–207 (2005)
Zhu, G., Li, Y., Wen, P.: Analysis and classification of sleep stages based on difference visibility graphs from a single-channel eeg signal. IEEE J. Biomed. Health Inform. 18(6), 1813–1821 (2014)
Güneş, S., Polat, K., Yosunkaya, Ş: Efficient sleep stage recognition system based on eeg signal using k-means clustering based feature weighting. Expert Syst. Appl. 37(12), 7922–7928 (2010)
Hassan, A.R., Bashar, S.K., Bhuiyan, M.I.H.: On the classification of sleep states by means of statistical and spectral features from single channel electroencephalogram in International conference on advances in computing, communications and informatics (ICACCI). IEEE 2015, 2238–2243 (2015)
Younes, M., Ostrowski, M., Soiferman, M., Younes, H., Younes, M., Raneri, J., Hanly, P.: Odds ratio product of sleep eeg as a continuous measure of sleep state. Sleep 38(4), 641–654 (2015)
Charbonnier, S., Zoubek, L., Lesecq, S., Chapotot, F.: Self-evaluated automatic classifier as a decision-support tool for sleep/wake staging. Comput. Biol. Med. 41(6), 380–389 (2011)
Furman, L., Duch, W., Minati, L., Tolpa, K.: Short-time fourier transform and embedding method for recurrence quantification analysis of eeg time series. European Phys. J. Spec Top 232(1), 135–149 (2023)
Huang, Z., Ling, B.W.-K.: Sleeping stage classification based on joint quaternion valued singular spectrum analysis and ensemble empirical mode decomposition. Biomed. Signal Process. Control 71, 103086 (2022)
Yücelbaş, C., Yücelbaş, Ş, Özşen, S., Tezel, G., Küççüktürk, S., Yosunkaya, Ş: Automatic detection of sleep spindles with the use of stft, emd and dwt methods. Neural Comput. Appl. 29(8), 17–33 (2018)
Hussein, R.M., George, L.E., Miften, F.S.: Accurate method for sleep stages classification using discriminated features and single eeg channel. Biomed. Signal Process. Control 84, 104688 (2023)
Abdulla, S., Diykh, M., Siuly, S., Ali, M.: An intelligent model involving multi-channels spectrum patterns based features for automatic sleep stage classification. Int. J. Med. Informatics 171, 105001 (2023)
Hassan, A.R., Bhuiyan, M.I.H.: Automatic sleep scoring using statistical features in the emd domain and ensemble methods. Biocybern Biomed Eng 36(1), 248–255 (2016)
Cura, O.K., Ozdemir, M.A., Pehlivan, S., Akan, A.: A dynamic mode decomposition based approach for epileptic eeg classification. In: 28th European Signal Processing Conference (EUSIPCO). IEEE 2021, 1070–1074 (2020)
Kemp, B., Zwinderman, A.H., Tuk, B., Kamphuisen, H.A., Oberye, J.J.: Analysis of a sleep-dependent neuronal feedback loop: the slow-wave microcontinuity of the eeg. IEEE Trans. Biomed. Eng. 47(9), 1185–1194 (2000)
Goldberger, A.L., Amaral, L.A., Glass, L., Hausdorff, J.M., Ivanov, P.C., Mark, R.G., Mietus, J.E., Moody, G.B., Peng, C.-K., Stanley, H.E.: Physiobank, physiotoolkit, and physionet: components of a new research resource for complex physiologic signals. Circulation 101(23), e215–e220 (2000)
Tzimourta, K.D., Tsilimbaris, A., Tzioukalia, K., Tzallas, A.T., Tsipouras, M.G., Astrakas, L.G., Giannakeas, N.: Eeg-based automatic sleep stage classification. Biomed J 1, 6 (2018)
JH Tu, (2013) Dynamic mode decomposition: Theory and applications, Ph.D. dissertation, Princeton University,
Hassan, A.R., Bhuiyan, M.I.H.: Automated identification of sleep states from eeg signals by means of ensemble empirical mode decomposition and random under sampling boosting. Comput. Methods Program Biomed. 140, 201–210 (2017)
Hassan, A.R., Subasi, A.: A decision support system for automated identification of sleep stages from single-channel eeg signals. Knowl.-Based Syst. 128, 115–124 (2017)
Hassan, A.R., Bhuiyan, M.I.H.: Computer-aided sleep staging using complete ensemble empirical mode decomposition with adaptive noise and bootstrap aggregating. Biomed. Signal Process. Control 24, 1–10 (2016)
Zhou, J., Wang, G., Liu, J., Wu, D., Xu, W., Wang, Z., Ye, J., Xia, M., Hu, Y., Tian, Y.: Automatic sleep stage classification with single channel eeg signal based on two-layer stacked ensemble model. IEEE Access 8, 57283–57297 (2020)
Imtiaz, S.A., Rodriguez-Villegas, E.: Automatic sleep staging using state machine-controlled decision trees. In: 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE 2015, 378–381 (2015)
Yildirim, O., Baloglu, U.B., Acharya, U.R.: A deep learning model for automated sleep stages classification using psg signals. Int. J. Environ. Res. Public Health 16(4), 599 (2019)
Kong, G., Li, C., Peng, H., Han, Z., Qiao, H.: Eeg-based sleep stage classification via neural architecture search. IEEE Trans. Neural Syst. Rehabil. Eng. 31, 1075–1085 (2023)
Zaidi, T.F., Farooq, O.: Eeg sub-bands based sleep stages classification using fourier synchrosqueezed transform features. Expert Syst. Appl. 212, 118752 (2023)
Acknowledgements
Not applicable.
Funding
This paper was supported partly by the National Nature Science Foundation of China (no. U1701266, no. 61671163 and no. 62071128), the Team Project of the Education Ministry of the Guangdong Province (no. 2017KCXTD011), the Guangdong Higher Education Engineering Technology Research Center for Big Data on Manufacturing Knowledge Patent (no. 501130144) and the Hong Kong Innovation and Technology Commission, Enterprise Support Scheme (no. S/E/070/17).
Author information
Authors and Affiliations
Contributions
JL is responsible for conducting the simulations and performing the data acquisition, formulating the methodology, implementing the algorithm and writing the draft of the paper. BW-KL is responsible for formulating the methodology, revising the paper, attracting the funding and managing the project. RL, JS, SL, JHC and QL are responsible for validating the results.
Corresponding author
Ethics declarations
Conflict of interest
There is no conflict of interest.
Consent for publication
The submission of this paper is consented by all the authors.
Ethics approval and consent to participate
The ethics approval and the consent to the participates are not required.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Liu, J., Ling, B.WK., Li, R. et al. Sleep stage classification via dynamic mode decomposition approach. SIViP 18, 535–544 (2024). https://doi.org/10.1007/s11760-023-02734-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11760-023-02734-5