Sleep EEG Staging Studies Based on Relief Algorithm

  • Huaping Jia
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 163)


Using the approximate entropy method for sleep staging EEG signal, But to the sleep stage III and IV approximate entropy value is very close, So by the approximate entropy cannot be distinguished, the results of stage III and IV EEG signal AR modeling, as the EEG signal characteristic coefficient, use of Probabilistic neural network method and Relief algorithm to distinguished sleep stage III and IV, Relief algorithm achieve a good effect.


Sleep EEG (electroencephalograph) staging Approximate entropy Probabilistic neural network Relief algorithm 



This work was supported by Shaanxi Provincial Department of Education Special research projects (11JK0480), Shaanxi nature science foundation research programs (2011JM1010) and WeiNan Teachers University key research projects (11YKF011).


  1. 1.
    Rechtschaffen A, Kales A (1968) A manual of standardized terminology, techniques and scoring system for sleep stages of human subjects, vol 48. Government Printing Office, Public Health Service, Washington, DC, pp 3–7Google Scholar
  2. 2.
    Liang Xiaohua (2008) Based on EEG ECG data fusion of the sleep stages. Jiangsu University 428:281–291Google Scholar
  3. 3.
    Liu Hui, He Weixing, Chen Xiaoping (2005) Sleep EEG nonlinear dynamics method. J Jiangsu Univ Nat Sci Edn 26(2):174–177Google Scholar
  4. 4.
    Xiao Yuliang, He Weixing, Chen Xiaoping (2009) Based on the sample entropy sleep EEG staging. J Jiangsu Univ Nat Sci Edn 30(5):501–504Google Scholar
  5. 5.
    Ong RJ, Dawley JT, Clem PG (2006) Submitted to Journal of Materials Research (2003) Xiao YL, He WX, Chen XP, et al. Wavelet transform and wavelet entropy in the sleep EEG signal change characteristics of value. Chin J Clin Rehab 10(25):118–120Google Scholar
  6. 6.
    Chen Weiting, Wang Zhizhong, Xie Hongbo et al (2007) Characterization of surface EMG signal based on fuzzy entropy. IEEE Trans Neural Syst Rehab Eng 15(2):267–272Google Scholar
  7. 7.
    Pedro P, Pavel G, Leticia A (2004) Sleep stage classification using fuzzy sets and machine learning techniques. Neurocomputing 58:1137–1143Google Scholar
  8. 8.
    Ventours EM, Monoyiou EA, Ktonas PY et al (2005) Sleep spindle detection using artificial neural networks trained with filtered time-domain EEG: a feasibility study. Comput Methods Programs Biomed 78(3):191–207CrossRefGoogle Scholar
  9. 9.
    Liu Jianping, Zheng Chongxun (1995) Analysis of EEG signals, an exploring brain function state and activity patterns of the way. Foreign Med Sci Biomed Eng Fascicle 18(5):263–270Google Scholar
  10. 10.
    Zhang Jie, Wang Ming (1997) The sleep EEG studies. Foreign Med Sci Biomed Eng 20(2):87–94Google Scholar
  11. 11.
    Fu Xiaohua, Li Hongpei (2003) Sleep and health. China J Med 38(8):34–42Google Scholar
  12. 12.
  13. 13.
    Kira K, Rendell L (1992) A practical approach to feature selection. In: Proceedings of the 9th international workshop on machine learning. Morgan Kaufmann, San Francisco 34:249–256Google Scholar
  14. 14.
    Kononenkl I (1994) Estimation attributes: analysis and extensions of RELIEF. European conference on machine learning, vol 42. Springer Verlag, Catania, pp 171–182Google Scholar

Copyright information

© Springer Science+Business Media New York 2014

Authors and Affiliations

  1. 1.College of Mathematics and Information ScienceWeinan Teachers’ UniversityWeinanPeople’s Republic of China
  2. 2.Center of Network Engineering TechnologyWeinan Teachers’ UniversityWeinanPeople’s Republic of China

Personalised recommendations