Abstract
To achieve accurate sleep stage classification and improve its generalization ability, we presented a features fusion method to classify sleep stage using Electroencephalogram (EEG) and Electromyography (EMG). We regarded EEG and EMG samples from MIT-BIH Polysomnographic database as analysis objects. First of all, we used the Discrete Wavelet Transform (DWT) to filter noise of signals and extract energy ratio of α, β, θ and δ wave from EEG and the high frequency component from EMG, and used Sample Entropy (SampEn) algorithm to extract nonlinear characteristics of EEG. Then, we compared the accuracy difference of sleep stage classification method between using EEG and using EEG and EMG features fusion by inputting these features to Support Vector Machine (SVM) classifier to train and test. Finally, we used cross-validation method to train and test different samples to verify its generalization ability. The experiment of testing accuracy showed a satisfactory result with accuracy of 91.86%, and the average accuracy raised 4.94% compared to the sleep stage classification method using EEG. The cross-validation results indicated that this method has better generalization ability.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Neonates, F.P., Kushida, C.A.: Sleep Deprivation, pp. 121–150. Marcel Dekker, New York (2004)
Liu, Z., Zhang, H., Zhao, H.: Study on sleep staging algorithm based on EEG signals. Chin. J. Biomed. Eng. 34(6), 693–700 (2015)
Xie, H., Shi, X.: Research on sleep staging based on discrete wavelet transform for electroencephalogram. Softw. Algorithms 34(16), 18–20 (2015)
Estrada, E., Nazeran, H., Nava, P., Behbehani, K., Burk, J., Lucas, E.: Itakura distance: a useful similarity measure between EEG and EOG signals in computer-aided classification of sleep stages. In: Proceedings of the 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference, Shanghai, China, pp. 1–4, September 2005
Li, J., Chen, H., Ye, S.: A self-adaptive threshold method for automatic sleep stage classification using EOG and EMG. MATEC Web Conf. 22 (2015). Article no. 05023
Goldberger, A.L., Amaral, L.A.N., Glass, L., Hausdorff, J.M., Ivanov, P.C., et al.: PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation 101(23), e215–e220 (2000)
Lajnef, T., Chaibi, S., Ruby, P., Aguera, P.E., Eichenlaub, J.B.: Learning machines and sleeping brains: automatic sleep stage classification using decision-tree multi-class support vector machines. J. Neurosci. Methods 250, 94–105 (2015)
Constable, R., Thornhill, R.J., Carpenter, D.R.: Time frequency analysis of the surface EMG during maximum height jumps under altered conditions. Biomed. Sci. Instrum. 30, 69–74 (1994)
Wang, H.: The latest interpretation of analytical standard guide on the American Academy of sleep medicine sleep staging. Diagn. Theor. Pract. 8(6), 575–578 (2009)
Weixing, H., Xiaoping, C., Junting, S.: Sleep EEG staging based on sample entropy. J. Jiangsu Univ. 30(5), 501–504 (2009)
Baudat, G., Anouar, F.: Kernel-based methods and function approximation. In: IJCNN 2001 International Joint Conference on proceedings of the Neural Networks, pp. 1244–1249 (2001)
Run, J., Luo, D., Luo, H.: Indoor and outdoor scene recognition algorithm based on support vector machine multi-classifier. J. Comput. Appl. 35(11), 3135–3138 (2015)
Acknowledgment
This work is partially supported by Science and Technology Program of Suzhou-the Medical Devices and New Medicine Program (ZXY201427, ZXY201429).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Lv, T., Wang, X., Yu, Q., Yu, Y. (2017). A Features Fusion Method for Sleep Stage Classification Using EEG and EMG. In: Yuan, H., Geng, J., Bian, F. (eds) Geo-Spatial Knowledge and Intelligence. GRMSE 2016. Communications in Computer and Information Science, vol 698. Springer, Singapore. https://doi.org/10.1007/978-981-10-3966-9_19
Download citation
DOI: https://doi.org/10.1007/978-981-10-3966-9_19
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-3965-2
Online ISBN: 978-981-10-3966-9
eBook Packages: Computer ScienceComputer Science (R0)