Deep neural network method for classification of sleep stages using spectrogram of signal based on transfer learning with different domain data

Document Type : Article


1 Department of Biomedical Engineering, Kazerun Branch, Islamic Azad University, Kazerun, Iran

2 Department of Electrical Engineering, Kazerun Branch, Islamic Azad University, Kazerun, Iran


Sleep stages Classification is a useful way to diagnose sleep problems. This is based on the processing of bio-signals (ECG, EEG, EOG, PPG). The less complex this signal is, the better the detection and processing. Feature extraction methods using hand are tedious and long lasting.
Extraction of features without hand intervention are deep features, which are usually extracted from images. Analysis of time-frequency characteristics of non-static bio-signals is very important and has useful information.
In this study, time-frequency image was extracted using ECG signal spectrogram and deep features were extracted using convolutional neural network. After extracting deep features, sleep stages were classified using deep transfer learning method. Network training was performed using one of the ECG signal and testing was performed with the other ECG signal channel.
The results show that it is possible to detect sleep stages with acceptable accuracy with different amplitudes of signals. Sleep stages were detected with 98.92% accuracy and 96.52% sensitivity.


1. Emina, A. and Abdulhamit, S. "Ensemble SVM method for automatic sleep stage classification", IEEE Transactions on Instrumentation and Measurement, 67(1), pp. 1-8 (2018).
2. Bela, W., Zsofia, C., Robert, B., et al. "Comparison of fractal and power spectral EEG features: Effects of topography and sleep stages", IBrain Research Bulletin, 84(6), pp. 359-375 (2011).
3. Doroshenkov, L., Konyshev, V., and Selishchev, S. "Comparison of fractal and power spectral EEG features: Effects of topography and sleep stages", Brain Research Bulletin, 84(6), pp. 25-28 (2007).
4. LeCun, Y., Bengio, Y., and Hinton, G. "Deep learning", Nature, 521(7553), pp. 436-437 (2015).
5. Khadempir, H., Afsari, E., and Rashedi, E. "Domain adaptation based on incremental adversarial learning", 8th Iranian Joint Congress on Fuzzy and intelligent Systems, pp. 2-4 (2020).
6. Malon, C. and Cosatto, E. "Classification of mitotic figures with convolutional neural networks and seeded blob features", Pathol. Inform, pp. 4-9 (2013).
7. Cruz-Roa, A., Basavanhally, A., Gonzalez, H., et al. "Automatic detection of invasive ductal carcinoma in whole slide images with convolutional neural networks", International Society for Optics and Photonics, 84(6), pp. 904103 (2014).
8. Ciresan, D., Giusti, A., Gambardella, L., et al. "Deep neural networks segment neuronal membranes in electron microscopy images", Advances in Neural Information Processing Systems, 2(12), pp. 2843-2851 (2012).
9. Esteva, A., Kuprel, B., and Thrun, S., Deep Networks for Early Stage Skin Disease and Skin Cancer Classification, Stanford University (2015).
10. Dhungel, N., Carneiro, G., and Bradley, A. "Deep learning and structured prediction for the segmentation of mass in mammograms", International Conference on Medical Image Computing and Computer- Assisted Intervention, pp. 605-612 (2015).
11. Ullah Khan, S., Naveed Islam, Z., Ikram, U., et al. "A novel deep learning based framework for the detection and classification of breast cancer using transfer learning", Pattern Recognition Letters, 125(1), pp. 1-6 (2019).
12. Donahue, J., Nguyen, D., Jia, Y., et al. "A deep convolutional activation feature for generic visual recognition", Computer Vision and Pattern Recognition, 1310(1) pp. 1-10 (2013).
13. Lin, D., Lin, D., and Cao, J. "Deep cnns for microscopic image classification by exploiting transfer learning and feature concatenation", Circuits and Systems (ISCAS), 1(1), pp. 1-5 (2018).
14. Cheng, J., Huang, W., Cao, S., et al. "Enhanced performance of brain tumor classification via tumor region augmentation and partition", Circuits and Systems (ISCAS), 10(1371), pp. 1-13 (2015).
15. Hossein, K., Aditi, C., Tariqus, S., and Richard, B. "Electronic sleep stage classifiers: A survey and VLSI design methodology", IEEE Transactions on Biomedical Circuits and System, 11(1) pp. 177-188 (2017).
16. Heenam, Y., Su, H., Jae, C., et al. "Slow-wave sleep estimation for healthy subjects and OSA patients using R- intervals", IEEE Journal of Biomedical and Health Informatics, 22(1), pp. 119-128 (2018).
17. Koley, B. and Dey, D. "An ensemble system for automatic sleep stage classification using single-channel EEG signal", Computers in Biology and Medicine, 42(12) pp. 1186-1195 (2012).
18. Varun, B. and Ram, B. "Automatic classification of sleep stages based on the time-frequency image of EEG signals", Computer Methods and Programs in Biomedicine, 112(3) pp. 320-328 (2013).
19. Oliver, F., Yuki, H., Tan, J., et al. "Deep learning for healthcare applications based on physiological signals: A review", Computer Methods and Programs in Biomedicine, 161(1), pp. 1-13 (2018).
20. Oh, S., Hagiwara, Y., Yuvaraj, R., et al. "A deep learning approach for Parkinson's disease diagnosis from EEG signals", Neural Computing and Applications, 32(1) pp. 10927-10933 (2020).
21. Andreas, A., Loukianos, S., Yuvaraj, R., et al. "Deep neural architectures for mapping scalp to intracranial EEG", International Journal of Neural Systems, 28, pp. 1-15 (2018).
22. Moradi, M., Fatehi, M.H., Masoumi, H., et al. "Deep learning method for sleep stages classification by timefrequency image", Signal Processing and Renewable Energy, 1(s1), pp. 67-83 (2021).
23. Moradi, M., Fatehi, M.H., Masoumi, H., et al. "Adaptive neuro-fuzzy method for sleep stages detection by PPG signal", Journal of Advanced Pharmacy Education & Research, 10(s1) pp. 1-7 (2020).
24. Tuncer, T., Dogan, S., Ertam, F. et al. "A novel ensemble local graph structure based feature extraction network for EEG signal analysis", Biomedical Signal Processing and Control, 61(10) pp. 1-11 (2020).
25. De Mooij, S.M.M., Blanken, T.F., Grasman, R.P.P.P., et al. "Dynamics of sleep: Exploring critical transitions and early warning signals", Biomedical Signal Processing and Control, 193(105448) pp. 1-8 (2020).
26. Baygin,, M., Dogan, S., Turker, T. et al. "Automated ASD detection using hybrid deep lightweight features extracted from EEG signals", Computers in Biology and Medicine, 134(2), pp. 1-13 (2021).