Automatic Sleep Stage Classification Based on an Improved K-means Clustering Algorithm_Journal of Biomedical Engineering

Authors：

XIAOShuyuan ¹ ,  WANGBei ¹ , ZHANGJian ¹ , ZHANGQunfeng ² , ZOUJunzhong ¹

1. Department of Automation, School of Information Science and Engineering, East China University of Science and Technology, Shanghai 200237, China;
2. NCC Medical Co., LTD, Shanghai 200245, China;

Corresponding author：

WANGBei, Email: beiwang@ecust.edu.cn

Keywords：

K-means clustering; sleep stage classification; electroencephalography

DOI：

10.7507/1001-5515.20160137

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Sleep stage scoring is a hotspot in the field of medicine and neuroscience. Visual inspection of sleep is laborious and the results may be subjective to different clinicians. Automatic sleep stage classification algorithm can be used to reduce the manual workload. However, there are still limitations when it encounters complicated and changeable clinical cases. The purpose of this paper is to develop an automatic sleep staging algorithm based on the characteristics of actual sleep data. In the proposed improved K-means clustering algorithm, points were selected as the initial centers by using a concept of density to avoid the randomness of the original K-means algorithm. Meanwhile, the cluster centers were updated according to the 'Three-Sigma Rule' during the iteration to abate the influence of the outliers. The proposed method was tested and analyzed on the overnight sleep data of the healthy persons and patients with sleep disorders after continuous positive airway pressure (CPAP) treatment. The automatic sleep stage classification results were compared with the visual inspection by qualified clinicians and the averaged accuracy reached 76%. With the analysis of morphological diversity of sleep data, it was proved that the proposed improved K-means algorithm was feasible and valid for clinical practice.

Citation： XIAO Shuyuan, WANG Bei, ZHANG Jian, ZHANG Qunfeng, ZOU Junzhong. Automatic Sleep Stage Classification Based on an Improved K-means Clustering Algorithm. Journal of Biomedical Engineering, 2016, 33(5): 847-854. doi: 10.7507/1001-5515.20160137 Copy

1.	BRODBECK V, KUHN A, VON WEGNER F, et al. EEG microstates of wakefulness and NREM sleep[J]. Neuroimage, 2012, 62(3):2129-2139.
2.	XIAO Meng, YAN Hong, SONG Jinzhong, et al. Sleep stages classification based on heart rate variability and random forest[J]. Biomed Signal Process Control, 2013, 8(6):624-633.
3.	GÜNEŞ S, POLAT K, YOSUNKAYA Ş. Efficient sleep stage recognition system based on EEG signal using k-means clustering based feature weighting[J]. Expert Syst Appl, 2010, 37(12):7922-7928.
4.	SUSMÁKOVÁ K, KRAKOVSKÁ A. Discrimination ability of individual measures used in sleep stages classification[J]. Artif Intell Med, 2008, 44(3):261-277.
5.	CORSI-CABRERA M, MUÑOZ-TORRES Z, DEL RÍO-PORTILLA Y, et al. Power and coherent oscillations distinguish REM sleep, stage 1 and wakefulness[J]. Int J Psychophysiol, 2006, 60(1):59-66.
6.	王歆媛, 汪丰.基于EEG复杂度和近似熵的睡眠自动分期[J].软件, 2013, 34(2):97-100.
7.	KOLEY B, DEY D. An ensemble system for automatic sleep stage classification using single channel EEG signal[J]. Comput Biol Med, 2012, 42(12):1186-1195.
8.	FELL J, RÖSCHKE J, MANN K, et al. Discrimination of sleep stages:a comparison between spectral and nonlinear EEG measures[J]. Electroencephalogr Clin Neurophysiol, 1996, 98(5):401-410.
9.	RONZHINA M, JANOUŠEK O, KOLÁŘOVÁ J, et al. Sleep scoring using artificial neural networks[J]. Sleep Med Rev, 2012, 16(3):251-263.
10.	焦东来, 冯昊, 姚凤华, 等.基于平均能量耗散的睡眠分期研究[J].北京生物医学工程, 2013, 32(2):134-138.
11.	彭振, 韦明, 郭建平, 等.基于奇异值第一主成分的睡眠脑电分期方法研究[J].现代生物医学进展, 2014, 14(7):1368-1372.
12.	WU H T, TALMON R, LO Y L. Assess sleep stage by modern signal processing techniques[J]. IEEE Trans Biomed Eng, 2015, 62(4):1159-1168.
13.	ZHU Guohun, LI Yan, WEN P P. Analysis and classification of sleep stages based on difference visibility graphs from a single-channel EEG signal[J]. IEEE J Biomed Health Inform, 2014, 18(6):1813-1821.
14.	KRISHNASAMY G, KULKARNI A J, PARAMESRAN R. A hybrid approach for data clustering based on modified cohort intelligence and K-means[J]. Expert Syst Appl, 2014, 41(13):6009-6016.
15.	KOUPPARIS A M, KOKKINOS V, KOSTOPOULOS G K. Semi-automatic sleep EEG scoring based on the hypnospectrogram[J]. J Neurosci Methods, 2014, 221:189-195.
16.	LIMA P, LEITAO J, PAIVA T. Artifact detection in sleep EEG recording[C]//Proceedings of Electrotechnical Conference. Lisbon, 1989:273-277.
17.	ZHANG S Q, TENG J F, GU J H. A new cluster method using rough set theory[C]//International Conference on Machine Learning and Cybernetics. Guilin, 2011:1555-1559.
18.	MITRA S. An evolutionary rough partitive clustering[J]. Pattern Recognit Lett, 2004, 25(12):1439-1449.
19.	张娇, 裘国永, 张奇.基于二分K均值的SVM决策树的高维数据分类方法[J].赤峰学院学报:自然科学版, 2012, 28(4):13-15.
20.	ORHAN U, HEKIM M, OZER M. EEG signals classification using the K-means clustering and a multilayer perceptron neural network model[J]. Expert Syst Appl, 2011, 38(10):13475-13481.
21.	SOUSA T, CRUZ A, KHALIGHI S, et al. A two-step automatic sleep stage classification method with dubious range detection[J]. Comput Biol Med, 2015, 59:42-53.
22.	Ş EN B, PEKER M, ÇAVUŞOĞLU A, et al. A comparative study on classification of sleep stage based on EEG signals using feature selection and classification algorithms[J]. J Med Syst, 2014, 38(3):18-38.
23.	DEVUYST S, DUTOIT T, STENUIT P, et al. Automatic K-complexes detection in sleep EEG recordings using likelihood thresholds[C]//International Conference of the IEEE Engineering in Medicine and Biology. Buenos Aires, 2010:4658-4661.
24.	彭小虎, 王国锋, 陈欢, 等.睡眠K复合波的功能及其模型[J].第二军医大学学报, 2014, 35(1):94-100.
25.	DUMAN F, ERDAMAR A, EROGUL O, et al. Efficient sleep spindle detection algorithm with decision tree[J]. Expert Syst Appl, 2009, 36(6):9980-9985.

1. BRODBECK V, KUHN A, VON WEGNER F, et al. EEG microstates of wakefulness and NREM sleep[J]. Neuroimage, 2012, 62(3):2129-2139.
2. XIAO Meng, YAN Hong, SONG Jinzhong, et al. Sleep stages classification based on heart rate variability and random forest[J]. Biomed Signal Process Control, 2013, 8(6):624-633.
3. GÜNEŞ S, POLAT K, YOSUNKAYA Ş. Efficient sleep stage recognition system based on EEG signal using k-means clustering based feature weighting[J]. Expert Syst Appl, 2010, 37(12):7922-7928.
4. SUSMÁKOVÁ K, KRAKOVSKÁ A. Discrimination ability of individual measures used in sleep stages classification[J]. Artif Intell Med, 2008, 44(3):261-277.
5. CORSI-CABRERA M, MUÑOZ-TORRES Z, DEL RÍO-PORTILLA Y, et al. Power and coherent oscillations distinguish REM sleep, stage 1 and wakefulness[J]. Int J Psychophysiol, 2006, 60(1):59-66.
6. 王歆媛, 汪丰.基于EEG复杂度和近似熵的睡眠自动分期[J].软件, 2013, 34(2):97-100.
7. KOLEY B, DEY D. An ensemble system for automatic sleep stage classification using single channel EEG signal[J]. Comput Biol Med, 2012, 42(12):1186-1195.
8. FELL J, RÖSCHKE J, MANN K, et al. Discrimination of sleep stages:a comparison between spectral and nonlinear EEG measures[J]. Electroencephalogr Clin Neurophysiol, 1996, 98(5):401-410.
9. RONZHINA M, JANOUŠEK O, KOLÁŘOVÁ J, et al. Sleep scoring using artificial neural networks[J]. Sleep Med Rev, 2012, 16(3):251-263.
10. 焦东来, 冯昊, 姚凤华, 等.基于平均能量耗散的睡眠分期研究[J].北京生物医学工程, 2013, 32(2):134-138.
11. 彭振, 韦明, 郭建平, 等.基于奇异值第一主成分的睡眠脑电分期方法研究[J].现代生物医学进展, 2014, 14(7):1368-1372.
12. WU H T, TALMON R, LO Y L. Assess sleep stage by modern signal processing techniques[J]. IEEE Trans Biomed Eng, 2015, 62(4):1159-1168.
13. ZHU Guohun, LI Yan, WEN P P. Analysis and classification of sleep stages based on difference visibility graphs from a single-channel EEG signal[J]. IEEE J Biomed Health Inform, 2014, 18(6):1813-1821.
14. KRISHNASAMY G, KULKARNI A J, PARAMESRAN R. A hybrid approach for data clustering based on modified cohort intelligence and K-means[J]. Expert Syst Appl, 2014, 41(13):6009-6016.
15. KOUPPARIS A M, KOKKINOS V, KOSTOPOULOS G K. Semi-automatic sleep EEG scoring based on the hypnospectrogram[J]. J Neurosci Methods, 2014, 221:189-195.
16. LIMA P, LEITAO J, PAIVA T. Artifact detection in sleep EEG recording[C]//Proceedings of Electrotechnical Conference. Lisbon, 1989:273-277.
17. ZHANG S Q, TENG J F, GU J H. A new cluster method using rough set theory[C]//International Conference on Machine Learning and Cybernetics. Guilin, 2011:1555-1559.
18. MITRA S. An evolutionary rough partitive clustering[J]. Pattern Recognit Lett, 2004, 25(12):1439-1449.
19. 张娇, 裘国永, 张奇.基于二分K均值的SVM决策树的高维数据分类方法[J].赤峰学院学报:自然科学版, 2012, 28(4):13-15.
20. ORHAN U, HEKIM M, OZER M. EEG signals classification using the K-means clustering and a multilayer perceptron neural network model[J]. Expert Syst Appl, 2011, 38(10):13475-13481.
21. SOUSA T, CRUZ A, KHALIGHI S, et al. A two-step automatic sleep stage classification method with dubious range detection[J]. Comput Biol Med, 2015, 59:42-53.
22. Ş EN B, PEKER M, ÇAVUŞOĞLU A, et al. A comparative study on classification of sleep stage based on EEG signals using feature selection and classification algorithms[J]. J Med Syst, 2014, 38(3):18-38.
23. DEVUYST S, DUTOIT T, STENUIT P, et al. Automatic K-complexes detection in sleep EEG recordings using likelihood thresholds[C]//International Conference of the IEEE Engineering in Medicine and Biology. Buenos Aires, 2010:4658-4661.
24. 彭小虎, 王国锋, 陈欢, 等.睡眠K复合波的功能及其模型[J].第二军医大学学报, 2014, 35(1):94-100.
25. DUMAN F, ERDAMAR A, EROGUL O, et al. Efficient sleep spindle detection algorithm with decision tree[J]. Expert Syst Appl, 2009, 36(6):9980-9985.

Journal of Biomedical Engineering

Automatic Sleep Stage Classification Based on an Improved K-means Clustering Algorithm

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content