Abstract
Human’s sleep is divided into two segments, Rapid Eye Movement (REM) sleep and Non-REM (NREM) sleep. NREM sleep is further divided into 4 stages. Sleep staging attempts to identify these stages based on the signals collected in polysomnogram (PSG). Significant information can be derived from the EEG signals collected during PSG.
In our study we extract spectral features from EEG signals. Genetic Algorithm (GA) is used for selecting best features and then Support Vector Machine (SVM) with different kernels have been applied to differentiate sleep stages. According to chaotic characteristic of EEG signal, we use non-linear features, as well. Nonlinear and spectral features can differentiate stages awake and REM with 98.15% accuracy. Chaotic features improved classification rate as a necessary component. Succinctly, through the feature space constructed by approximate entropy and fractal dimension, different stages of EEG signals can be recognized from each other expressly. That is to say, Pattern varies under the different sleep stages. Therefore Healthy humans with a regular night’s sleep will follow these sleep stages in a particular pattern.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Parrino, L., Ferrillo, F., Smerieri, A., Spaggiari, M.C., Palomba, V., Rossi, M., Terzano, M.G.: Is insomnia a neurophysiological disorder? The role of sleep EEG microstructure. Brain Research Bulletin 63, 377–383 (2004)
Scher, M.S.: Automated EEG-sleep analyses and neonatal neurointensive care. Sleep Medicine 5, 533–540 (2004)
Sleep Computing of the Japanese Society of Sleep Researches(JSSR): Proposed supplements and amendments to ‘A Manual of Standardized Terminology,Techniques and Scoring System for Sleep Stages of Human Subjects’, the Rechtschaffen & Kales (1968) standard. Psychiatry and Clinical Neurosciences 55, 305–310 (2001)
Nayak, A., Roy, R.J.: Time Frequency Spectral Representation of EEG. IEEE, 7–8 (1993)
Van Hese, P., Philips, W., et al.: Automatic Detection of Sleep Stages using the EEG. In: Proc. of the 23rd Ann’l, EMBS Int’l. Conf., Istanbul, Turkey, October 25-28, pp. 1944–1947 (2001)
Scheuer, M.L.: Continuous EEG Monitoring in the Intensive Car Unit. Epilepsia 43(suppl. 3), 114–127 (2002)
Muthuswamy, J., Thakor, N.V.: Spectral analysis methods for neurological signals. Journal of Neuroscience Methods 83, 1–14 (1998)
Laing, R.J.A.: A Sleep Spindle Detection Algorithm. Master Thesis
Shen, J.Y.: Sleep Staging: Study through Spectrograms and Scalograms (2003), http://www.eng.uwaterloo.ca/~y5shen/research/sleepstaging .htm#sleepstage
Shen, J.Y.: Applying Image Processing to Identify Characteristic Waves in EOG (2004), http://www.eng.uwaterloo.ca/~y5shen/research/sleepstaging .htm#sleepstage
Pincus, S.M.: Older males secrete luteinizing hormone and testosterone more irregu-larly and joint more asynchronously, than younger males. Proc. Natl. Acad. Sci. USA 93, 14100–14105 (1996)
Radhakrishnan, N., Gangadhar, E.N.: Estimating regularity in epileptic seizure time-series data. A complexity-measure approach. IEEE Eng. Med. BIOI. 17, 89–94 (1998)
Zhang, X., Roy, R.J.: Derived fuzzy knowledge model for estimating the depth of anesthe-sia. IEEE Trans. Biomed. Eng. 48 (2001)
Solhjoo, S., Motie Nasrabadi, A.: EEG-Based Mental Task Classification in Hypnotized and Normal Subjects. In: Engineering in Medicine and Biology 27th Annual Conference, Shanghai, China, September 1-4 (2005)
Zhou, J., Bai, T.: The SVM Optimized by Culture Genetic Algorithm and Its Application in Forecasting Share Price. In: IEEE International Conference on Granular Computing, pp. 838–843 (2008)
Joachims, T.: Estimating the Generalization Performance of a SVM Efficiently. In: Proceedings of the International Conference on Machine Learning (ICML). Morgan Kaufman, San Francisco (2000)
Huerta, E.B., Duval, B.: A Hybrid GA/SVM Approach for Gene Selection and Classification of Microarray Data, pp. 34–44. Springer, Heidelberg (2006)
Güler, I., Beyli, E.Ü.: Multiclass Support Vector Machines for EEG-Signals Classification. IEEE Transactions on Information Technology in Biomedicine 11(2) (March 2007)
Guyon, J.W., Barnhill, S., Vapnik, V.: Gene selection for cancer classification using support vector machines. Machine Learning 46(1-3), 389–422 (2002)
Mukherjee, S.: Classifying Microarray Data Using Support Vector Machines. Springer, Heidelberg (2003)
Shimada, T., Shiina, T., Saito, Y.: Sleep Stage Diagnosis System with Neural Network Analysis. In: Proc. of the 20th Ann’l. Int’l. Conf. of the IEEE Engineering in Medicine and Biology Society, vol. 20(4), pp. 2074–2077 (1998)
Oropesa, E., Cycon, H.L., Jobert, M.: Sleep Staging Classification using Wavelet Transform and Neural Network. TR-99-008, International Computer Science Institute, Berkeley, California, (March 30, 1999)
Pohl, V., Fahr, E.: Neuro-Fuzzy Recognition of KComplexes in Sleep EEG Signals. IEEE, 789–790 (1997)
Akin, A., Akgul, T.: Detection of Sleep Spindles by Discrete Wavelet Transform. IEEE, 15–17 (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Vatankhah, M., Akbarzadeh Totonchi, M.R., Moghimi, A., Asadpour, V. (2010). GA/SVM for Diagnosis Sleep Stages Using Non-linear and Spectral Features. In: Gao, XZ., Gaspar-Cunha, A., Köppen, M., Schaefer, G., Wang, J. (eds) Soft Computing in Industrial Applications. Advances in Intelligent and Soft Computing, vol 75. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-11282-9_19
Download citation
DOI: https://doi.org/10.1007/978-3-642-11282-9_19
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-11281-2
Online ISBN: 978-3-642-11282-9
eBook Packages: EngineeringEngineering (R0)