Comparison of Time-Frequency Analyzes for a Sleep Staging Application with CNN

Abstract:

Sleep staging is the process of acquiring biological signals during sleep and marking them according to the stages of sleep. The procedure is performed by an experienced physician and takes more time. When this process is automated, the processing load will be reduced and the time required to identify disease will also be reduced. In this paper, 8 different transform methods for automatic sleep-staging based on convolutional neural networks (CNNs) were compared to classify sleep stages using single-channel electroencephalogram (EEG) signals. Five different labels were used to stage the sleep. These are Wake (W), Non Rapid Eye Movement (NonREM)-1 (N1), NonREM-2 (N2), NonREM-3 (N3), and REM (R). The classifications were done end-to-end without any hand-crafted features, ie without requiring any feature engineering. Time-Frequency components obtained by Short Time Fourier Transform, Discrete Wavelet Transform, Discrete Cosine Transform, Hilbert-Huang Transform, Discrete Gabor Transform, Fast Walsh-Hadamard Transform, Choi-Williams Distribution, and Wigner-Willie Distribution were classified with a supervised deep convolutional neural network to perform sleep staging. The discrete Cosine Transform-CNN method (DCT-CNN) showed the highest performance among the methods suggested in this paper with an F1 score of 89% and a value of 0.86 kappa. The findings of this study revealed that the transformation techniques utilized for the most accurate representation of input data are far superior to traditional approaches based on manual feature extraction, which acquires time, frequency, or nonlinear characteristics. The results of this article are expected to be useful to researchers in the development of low-cost, and easily portable devices.

• Periodical: Journal of Biomimetics, Biomaterials and Biomedical Engineering (Volume 55)
• Pages: 109-130
• DOI: https://doi.org/10.4028/p-2j5c10
• Online since: March 2022
• Authors: Enes Efe*, Seral Özşen
• Keywords: Convolutional Neural Networks, Sleep Staging, Time-Frequency Methods

References

[1] Roffwarg, H.P., J.N. Muzio, and W.C. Dement, Ontogenetic development of the human sleep-dream cycle. Science, (1966).

[2] Eaton, D.K., et al., Prevalence of insufficient, borderline, and optimal hours of sleep among high school students–United States, 2007. Journal of Adolescent Health, 2010. 46(4): pp.399-401.

DOI: 10.1016/j.jadohealth.2009.10.011

[3] Benington, J.H. and H.C. Heller, Restoration of brain energy metabolism as the function of sleep. Progress in neurobiology, 1995. 45(4): pp.347-360.

DOI: 10.1016/0301-0082(94)00057-o

[4] Alhassani, A.A. and M.S. Al-Zahrani, Is inadequate sleep a potential risk factor for periodontitis? PLoS One, 2020. 15(6): p. e0234487.

DOI: 10.1371/journal.pone.0234487

[5] Redline, S., et al., The effects of age, sex, ethnicity, and sleep-disordered breathing on sleep architecture. Archives of internal medicine, 2004. 164(4): pp.406-418.

DOI: 10.1001/archinte.164.4.406

[6] Wisana, I., P.C. Nugraha, and D. Estiwidani. The Effectiveness Obstructive Sleep Apnea Monitoring Using Telemedicine Smartphone System (TmSS). in Journal of Biomimetics, Biomaterials and Biomedical Engineering. 2021. Trans Tech Publ.

DOI: 10.4028/www.scientific.net/jbbbe.50.113

[7] da Silva, A.A., et al., Sleep duration and mortality in the elderly: a systematic review with meta-analysis. BMJ open, 2016. 6(2): p. e008119.

[8] Vitiello, M.V., Sleep disorders and aging: understanding the causes. The Journals of Gerontology Series A: Biological Sciences and Medical Sciences, 1997. 52(4): p. M189-M191.

DOI: 10.1093/gerona/52a.4.m189

[9] Sharma, R., R.B. Pachori, and A. Upadhyay, Automatic sleep stages classification based on iterative filtering of electroencephalogram signals. Neural Computing and Applications, 2017. 28(10): pp.2959-2978.

DOI: 10.1007/s00521-017-2919-6

[10] Berry, R., et al., Deliberations of the Sleep Apnea Definitions Task Force of the American Academy of Sleep Medicine. Rules for scoring respiratory events in sleep: update of the 2007 AASM Manual for the Scoring of Sleep and Associated Events. J Clin Sleep Med, 2012. 8(5): pp.597-619.

DOI: 10.5664/jcsm.2172

[11] Rosenberg, R.S. and S. Van Hout, The American Academy of Sleep Medicine inter-scorer reliability program: Respiratory events. Journal of clinical sleep medicine, 2014. 10(4): pp.447-454.

DOI: 10.5664/jcsm.3630

[12] Wolpert, E.A., A Manual of Standardized Terminology, Techniques and Scoring System for Sleep Stages of Human Subjects. Archives of General Psychiatry, 1969. 20(2): pp.246-247.

DOI: 10.1001/archpsyc.1969.01740140118016

[13] Biswal, S., et al., SLEEPNET: automated sleep staging system via deep learning. arXiv preprint arXiv:1707.08262, (2017).

[14] Redmond, S.J. and C. Heneghan, Cardiorespiratory-based sleep staging in subjects with obstructive sleep apnea. IEEE Transactions on Biomedical Engineering, 2006. 53(3): pp.485-496.

DOI: 10.1109/tbme.2005.869773

[15] Krakovská, A. and K. Mezeiová, Automatic sleep scoring: A search for an optimal combination of measures. Artificial intelligence in medicine, 2011. 53(1): pp.25-33.

DOI: 10.1016/j.artmed.2011.06.004

[16] Andreotti, F., H. Phan, and M. De Vos. Visualising convolutional neural network decisions in automatic sleep scoring. in CEUR Workshop Proceedings. 2018. CEUR Workshop Proceedings.

[17] Lajnef, T., et al., Learning machines and sleeping brains: automatic sleep stage classification using decision-tree multi-class support vector machines. Journal of neuroscience methods, 2015. 250: pp.94-105.

DOI: 10.1016/j.jneumeth.2015.01.022

[18] Huang, W., et al., Sleep staging algorithm based on multichannel data adding and multifeature screening. Computer methods and programs in biomedicine, 2020. 187: p.105253.

DOI: 10.1016/j.cmpb.2019.105253

[19] Sors, A., et al., A convolutional neural network for sleep stage scoring from raw single-channel EEG. Biomedical Signal Processing and Control, 2018. 42: pp.107-114.

DOI: 10.1016/j.bspc.2017.12.001

[20] Supratak, A., et al., DeepSleepNet: A model for automatic sleep stage scoring based on raw single-channel EEG. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2017. 25(11): pp.1998-2008.

DOI: 10.1109/tnsre.2017.2721116

[21] Wang, Y., et al., Evaluation of an automated single-channel sleep staging algorithm. Nature and science of sleep, 2015. 7: p.101.

[22] Tsinalis, O., et al., Automatic sleep stage scoring with single-channel EEG using convolutional neural networks. arXiv preprint arXiv:1610.01683, (2016).

[23] Kıymık, M.K., et al., Comparison of STFT and wavelet transform methods in determining epileptic seizure activity in EEG signals for real-time application. Computers in biology and medicine, 2005. 35(7): pp.603-616.

DOI: 10.1016/j.compbiomed.2004.05.001

[24] Radha, M., et al. Comparison of feature and classifier algorithms for online automatic sleep staging based on a single EEG signal. in 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 2014. IEEE.

DOI: 10.1109/embc.2014.6943976

[25] Li, Y., et al. Sleep stage classification based on EEG Hilbert-Huang transform. in 2009 4th IEEE Conference on Industrial Electronics and Applications. 2009. IEEE.

DOI: 10.1109/iciea.2009.5138842

[26] Liu, Y., et al. Automatic sleep stage scoring using Hilbert-Huang transform with BP neural network. in 2010 4th International Conference on Bioinformatics and Biomedical Engineering. 2010. IEEE.

DOI: 10.1109/icbbe.2010.5516372

[27] Guo, C., et al. Sleep EEG staging based on Hilbert-Huang transform and sample Entropy. in 2015 International Conference on Computational Intelligence and Communication Networks (CICN). 2015. IEEE.

DOI: 10.1109/cicn.2015.92

[28] Hassan, A.R. and M.I.H. Bhuiyan, A decision support system for automatic sleep staging from EEG signals using tunable Q-factor wavelet transform and spectral features. Journal of neuroscience methods, 2016. 271: pp.107-118.

DOI: 10.1016/j.jneumeth.2016.07.012

[29] Khalighi, S., et al. Efficient feature selection for sleep staging based on maximal overlap discrete wavelet transform and SVM. in 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 2011. IEEE.

DOI: 10.1109/iembs.2011.6090897

[30] Chriskos, P., et al. Automatic sleep stage classification applying machine learning algorithms on EEG recordings. in 2017 IEEE 30th International Symposium on Computer-Based Medical Systems (CBMS). 2017. IEEE.

DOI: 10.1109/cbms.2017.83

[31] Liao, Y., et al. Tri-FeatureNet: An Adversarial Learning-Based Invariant Feature Extraction for Sleep Staging using Single-Channel EEG. in 2020 IEEE International Symposium on Circuits and Systems (ISCAS). 2020. IEEE.

DOI: 10.1109/iscas45731.2020.9180501

[32] Tabar, Y.R., et al., Investigation of Low Dimensional Feature Spaces for Automatic Sleep Staging. Computer Methods and Programs in Biomedicine, 2021: p.106091.

DOI: 10.1016/j.cmpb.2021.106091

[33] Triwiyanto, T., et al. Electromyography Feature Analysis to Recognize the Hand Motion in a Prosthetic Hand Design. in Journal of Biomimetics, Biomaterials and Biomedical Engineering. 2021. Trans Tech Publ.

DOI: 10.4028/www.scientific.net/jbbbe.50.25

[34] Phan, H., et al., XSleepNet: Multi-view sequential model for automatic sleep staging. IEEE Transactions on Pattern Analysis and Machine Intelligence, (2021).

DOI: 10.1109/tpami.2021.3070057

[35] Nasiri, S. and G.D. Clifford. Attentive Adversarial Network for Large-Scale Sleep Staging. in Machine Learning for Healthcare Conference. 2020. PMLR.

[36] Phan, H., et al., Joint classification and prediction CNN framework for automatic sleep stage classification. IEEE Transactions on Biomedical Engineering, 2018. 66(5): pp.1285-1296.

DOI: 10.1109/tbme.2018.2872652

[37] Mikkelsen, K. and M. De Vos, Personalizing deep learning models for automatic sleep staging. arXiv preprint arXiv:1801.02645, (2018).

[38] Chambon, S., et al., A deep learning architecture for temporal sleep stage classification using multivariate and multimodal time series. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2018. 26(4): pp.758-769.

DOI: 10.1109/tnsre.2018.2813138

[39] Jayathilake, A., A. Perera, and M. Chamikara, Discrete Walsh-Hadamard transform in signal processing. IJRIT Int. J. Res. Inf. Technol, 2013. 1: pp.80-89.

[40] Ahmed, N., T. Natarajan, and K.R. Rao, Discrete cosine transform. IEEE transactions on Computers, 1974. 100(1): pp.90-93.

DOI: 10.1109/t-c.1974.223784

[41] Goldberger, A.L., et al., PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. circulation, 2000. 101(23): p. e215-e220.

DOI: 10.1161/01.cir.101.23.e215

[42] Boostani, R., F. Karimzadeh, and M. Nami, A comparative review on sleep stage classification methods in patients and healthy individuals. Computer methods and programs in biomedicine, 2017. 140: pp.77-91.

DOI: 10.1016/j.cmpb.2016.12.004

[43] Kales, A. and A. Rechtschaffen, A manual of standardized terminology, techniques and scoring system for sleep stages of human subjects. 1968: US Department of Health, Education and Welfare, Public Health Service ….

[44] Fu, M., et al., Deep Learning in Automatic Sleep Staging With a Single Channel Electroencephalography. Frontiers in Physiology, 2021. 12(179).

[45] Phan, H., et al. Automatic sleep stage classification using single-channel eeg: Learning sequential features with attention-based recurrent neural networks. in 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). 2018. IEEE.

DOI: 10.1109/embc.2018.8512480

[46] Shenoi, B.A., Introduction to digital signal: Processing and filter design. 2006: Wiley Online Library.

[47] Qu, N., et al., Fault detection on insulated overhead conductors based on DWT-LSTM and partial discharge. IEEE Access, 2020. 8: pp.87060-87070.

DOI: 10.1109/access.2020.2992790

[48] Mallat, S.G., A theory for multiresolution signal decomposition: the wavelet representation. IEEE transactions on pattern analysis and machine intelligence, 1989. 11(7): pp.674-693.

DOI: 10.1109/34.192463

[49] Salomon, D., Data compression: the complete reference. 2004: Springer Science & Business Media.

[50] Birvinskas, D., et al. EEG dataset reduction and feature extraction using discrete cosine transform. in 2012 Sixth UKSim/AMSS European Symposium on Computer Modeling and Simulation. 2012. IEEE.

DOI: 10.1109/ems.2012.88

[51] Huang, N.E., et al., The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proceedings of the Royal Society of London. Series A: mathematical, physical and engineering sciences, 1998. 454(1971): pp.903-995.

DOI: 10.1098/rspa.1998.0193

[52] Peng, Z., W.T. Peter, and F. Chu, An improved Hilbert–Huang transform and its application in vibration signal analysis. Journal of sound and vibration, 2005. 286(1-2): pp.187-205.

DOI: 10.1016/j.jsv.2004.10.005

[53] Kizhner, S., et al. On the Hilbert-Huang transform data processing system development. in 2004 IEEE Aerospace Conference Proceedings (IEEE Cat. No. 04TH8720). 2004. IEEE.

DOI: 10.1109/aero.2004.1367979

[54] Labate, D., et al., Empirical mode decomposition vs. wavelet decomposition for the extraction of respiratory signal from single-channel ECG: A comparison. IEEE Sensors Journal, 2013. 13(7): pp.2666-2674.

DOI: 10.1109/jsen.2013.2257742

[55] Rilling, G., P. Flandrin, and P. Goncalves. On empirical mode decomposition and its algorithms. in IEEE-EURASIP workshop on nonlinear signal and image processing. 2003. Citeseer.

[56] Cho, S.-H., G. Jang, and S.-H. Kwon, Time-frequency analysis of power-quality disturbances via the Gabor–Wigner transform. IEEE transactions on power delivery, 2009. 25(1): pp.494-499.

DOI: 10.1109/tpwrd.2009.2034832

[57] Qian, S. and D. Chen, Discrete gabor transform. IEEE transactions on signal processing, 1993. 41(7): pp.2429-2438.

DOI: 10.1109/78.224251

[58] Saraiva, A.A., et al., Electroencephalography applied compression algorithms qualitative analysis. Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 2020. 8(4): pp.367-373.

DOI: 10.1080/21681163.2019.1673212

[59] Hlawatsch, F. and G.F. Boudreaux-Bartels, Linear and quadratic time-frequency signal representations. IEEE signal processing magazine, 1992. 9(2): pp.21-67.

DOI: 10.1109/79.127284

[60] Taşpinar, G., et al. Investigation of photic stimulation response with time-frequency based parameters. in 2010 15th National Biomedical Engineering Meeting. 2010. IEEE.

DOI: 10.1109/biyomut.2010.5479845

[61] Choi, H.-I. and W.J. Williams, Improved time-frequency representation of multicomponent signals using exponential kernels. IEEE Transactions on Acoustics, Speech, and Signal Processing, 1989. 37(6): pp.862-871.

DOI: 10.1109/assp.1989.28057

[62] Li, M., W. Zhao, and W. Jia, The Profile of Kernels in Time Frequency Distributions. Journal of Ship Mechanics, 1999. 3(6): p.49.

[63] Lazorenko, O., The use of atomic functions in the Choi-Williams analysis of ultrawideband signals. Radioelectronics and Communications Systems, 2009. 52(8): pp.397-404.

DOI: 10.3103/s0735272709080019

[64] Goodfellow, I., et al., Deep learning. Vol. 1. 2016: MIT press Cambridge.

[65] Haut, J.M., et al., Hyperspectral image classification using random occlusion data augmentation. IEEE Geoscience and Remote Sensing Letters, 2019. 16(11): pp.1751-1755.

DOI: 10.1109/lgrs.2019.2909495

[66] Ioffe, S. and C. Szegedy. Batch normalization: Accelerating deep network training by reducing internal covariate shift. in International conference on machine learning. 2015. PMLR.

[67] Park, H.-J., et al., Automated sleep stage scoring using hybrid rule-and case-based reasoning. Computers and Biomedical Research, 2000. 33(5): pp.330-349.

DOI: 10.1006/cbmr.2000.1549

[68] Cohen, J., A coefficient of agreement for nominal scales. Educational and psychological measurement, 1960. 20(1): pp.37-46.

DOI: 10.1177/001316446002000104

[69] Fleiss, J.L., Measuring nominal scale agreement among many raters. Psychological bulletin, 1971. 76(5): p.378.

DOI: 10.1037/h0031619

[70] Landis, J.R. and G.G. Koch, The measurement of observer agreement for categorical data. biometrics, 1977: pp.159-174.

DOI: 10.2307/2529310

[71] Michielli, N., U.R. Acharya, and F. Molinari, Cascaded LSTM recurrent neural network for automated sleep stage classification using single-channel EEG signals. Computers in biology and medicine, 2019. 106: pp.71-81.

DOI: 10.1016/j.compbiomed.2019.01.013

[72] Wei, L., et al. Time-frequency convolutional neural network for automatic sleep stage classification based on single-channel EEG. in 2017 IEEE 29th International Conference on Tools with Artificial Intelligence (ICTAI). 2017. IEEE.

DOI: 10.1109/ictai.2017.00025