Advertisement

A Comparison of Performance of Sleep Spindle Classification Methods Using Wavelets

  • Elena Hernandez-PereiraEmail author
  • Isaac Fernandez-Varela
  • Vicente Moret-Bonillo
Conference paper
Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 60)

Abstract

Sleep spindles are transient waveforms and one of the key features that contributes to sleep stages assessment. Due to the large number of sleep spindles appearing on an overnight sleep, automating the detection of this waveforms is desirable. This paper presents a comparative study over the sleep spindle classification task involving the discrete wavelet decomposition of the EEG signal, and seven different classification algorithms. The main goal was to find a classifier that achieves the best performance. The results reported that Random Forest stands out over the rest of models, achieving an accuracy value of \(94.08 \pm 2.8\) and \(94.08 \pm 2.4\,\%\) with the symlet and biorthogonal wavelet families.

Keywords

Sleep spindles Wavelets Machine learning 

Notes

Acknowledgments

This research was partially funded by the Xunta de Galicia (Grant code GRC2014/035) and by the Spanish Ministerio de Economa y Competitividad, MINECO, under research project TIN2013-40686P both partially supported by the European Union ERDF.

References

  1. 1.
    Acir, N., Güzelis, C.: Automatic recognition of sleep spindles in EEG by using artificial neural networks. Expert Syst. Appl. 27(3), 451–458 (2004)CrossRefGoogle Scholar
  2. 2.
    Ahmed, B., Redissi, A., Tafreshi, R.: An automatic sleep spindle detector based on wavelets and the teager energy operator. In: Proceedings of Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 2596–2599 (2009)Google Scholar
  3. 3.
    Berry, R.B., et al.: The AASM Manual for Scoring of Sleep and Associated Events: Rules, Terminology and Technical Specifications. American Academy of Sleep Medicine, Darien, Illinois (2015)Google Scholar
  4. 4.
    Bishop, C.M.: Neural Networks for Pattern Recognition. Oxford University Press, New York (1995)zbMATHGoogle Scholar
  5. 5.
    Breiman, L., Friedman, J., Olshen, R., Stone, C.: Classification and Regression Trees. Chapman & Hall, New York (1984)zbMATHGoogle Scholar
  6. 6.
    Breiman, L.: Bagging predictors. Mach. Learn. 24(2), 123–140 (1996)zbMATHGoogle Scholar
  7. 7.
    Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)CrossRefzbMATHGoogle Scholar
  8. 8.
    Castillo, E., Fontenla-Romero, O., Alonso-Betanzos, A., Guijarro-Berdiñas, B.: A global optimum approach for one-layer neural networks. Neural Comput. 14(6), 1429–1449 (2002)CrossRefzbMATHGoogle Scholar
  9. 9.
    Daubechies, I.: Ten lectures on wavelets. In: Regional Conference Series in Applied Mathematics. Society for Industrial and Applied Mathematics (1992)Google Scholar
  10. 10.
    Devuyst, S., Dutoit, T., Stenuit, P., Kerkhofs, M.: Automatic sleep spindles detection. Overview and development of a standard proposal assessment method. In: 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC (2011)Google Scholar
  11. 11.
    Duman, F., Erdamar, A., Erogul, O., Telatar, Z., Yetkin, S.: Efficient sleep spindle detection algorithm with decision tree. Expert Syst. Appl. 36(6), 9980–9985 (2009)CrossRefGoogle Scholar
  12. 12.
    Efron, B.: Bootstrap methods: another look at the jackknife. Ann. Stat. 7, 1–26 (1979)MathSciNetCrossRefzbMATHGoogle Scholar
  13. 13.
    Fish, D., Allen, P., Blackie, J.: A new method for the quantitative analysis of sleep spindles during continuous overnight eeg recordings. Electroencephalogr. Clin. Neurophysiol. 70(3), 273–277 (1988)CrossRefGoogle Scholar
  14. 14.
    Fontenla-Romero, O., Guijarro-Berdiñas, B., Pérez-Sánchez, B., Alonso-Betanzos, B.: A new convex objective function for the supervised learning of single-layer neural networks. Pattern Recognit. 43(5), 1984–1992 (2010)CrossRefzbMATHGoogle Scholar
  15. 15.
    Fung, G., Mangasarian, O.: Proximal support vector machine classifiers. In: Provost, F., Srikant, R. et al. (eds.) Proceedings KDD-2001: Knowledge Discovery and Data Mining. pp. 77–86. San Francisco, CA, Asscociation for Computing Machinery, New York (2001)Google Scholar
  16. 16.
    Gennaro, L.D., Ferrara, M.: Sleep spindles: an overview. Sleep Med. Rev. 7(5), 423–440 (2003)CrossRefGoogle Scholar
  17. 17.
    Görür, D.: Automated Detection of Sleep Spindles. MSc thesis (2003)Google Scholar
  18. 18.
    Güneş, S., Dursun, M., Polat, K., Yosunkaya, C.: Sleep spindles recognition system based on time and frequency domain features. Expert Syst. Appl. 38(3), 2455–2461 (2011)CrossRefGoogle Scholar
  19. 19.
    Imtiaz, S.A., Saremi-Yarahmadi, S., Rodriguez-Villegas, E.: Automatic detection of sleep spindles using teager energy and spectral edge frequency. In: Biomedical Circuits and Systems Conference (BioCAS), 2013 IEEE, pp. 262–265 (2013)Google Scholar
  20. 20.
    Kumar, A., Hofman, W., Campbell, K.: An automatic spindle analysis and detection system based on the evaluation of human ratings of the spindle quality. Waking Sleep. 325–333 (1979)Google Scholar
  21. 21.
    Mashao, D.: Comparing SVM and GMM on parametric feature-sets. In: Proceedings of the 15th Annual Symposium of the Pattern Recognition Association of South Africa (2004)Google Scholar
  22. 22.
    MATLAB: version 8.4.0.150421 (R2014b). The MathWorks Inc., Natick, Massachusetts (2014)Google Scholar
  23. 23.
    Mitchell, T.: Machine Learning. McGraw Hill (1997)Google Scholar
  24. 24.
    Nonclercq, A., Urbain, C., Verheulpen, D., Decaestecker, C., Bogaert, P.V., Peigneux, P.: Sleep spindle detection through amplitude? Frequency normal modelling. J. Neurosci. Methods 214(2), 192–203 (2013)CrossRefGoogle Scholar
  25. 25.
    Quinlan, J.R.: Induction of decision trees. Mach. Learn. 1, 81–106 (1986)Google Scholar
  26. 26.
    Rao, R.M., Bopardikar, A.S.: Wavelet Transformations. Introduction to Theory and Applications (1998)Google Scholar
  27. 27.
    Ray, L.B., Fogel, S.M., Smith, C.T., Peters, K.R.: Validating an automated sleep spindle detection algorithm using an individualized approach. J. Sleep Res. 19(2), 374–378 (2010)CrossRefGoogle Scholar
  28. 28.
    Vapnik, V.: Statistical learning theory. Adaptive and learning systems for signal processing, communications, and control (1998)Google Scholar
  29. 29.
    Ventouras, E.M., Monoyiou, E.A., Ktonas, P.Y., Paparrigopoulos, T., Dikeos, D.G., Uzunoglu, N.K., Soldatos, C.R.: Sleep spindle detection using artificial neural networks trained with filtered time-domain EEG: a feasibility study. Comput. Methods Progr. Biomed. 78(3), 191–207 (2005)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Elena Hernandez-Pereira
    • 1
    Email author
  • Isaac Fernandez-Varela
    • 1
  • Vicente Moret-Bonillo
    • 1
  1. 1.Faculty of Informatics, Department of Computer ScienceUniversity of A CoruñaA CoruñaSpain

Personalised recommendations