Journal of the Korea Convergence Society (한국융합학회논문지)

Korea Convergence Society (한국융합학회)
권호 표지
DOI QR코드

DOI QR Code

Performance evaluation of sleep stage classifier for the sleep-inducing portable neurofeedback system

포터블 수면유도 뉴로피드백 시스템 구현을 위한 수면뇌파 상태 분류기 성능 평가

  • Lee, Taek (Department of Convergence Security Engineering, Sungshin Women's University)
  • 이택 (성신여자대학교 융합보안공학과)
  • Received : 2018.09.16
  • Accepted : 2018.11.20
  • Published : 2018.11.28
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, many people have suffered from insomnia, labor loss, cognitive decline, and mental illness. The solution to this problem is almost entirely cognitive therapy or medication, but it is not recommended in the long term due to side effects and dependency problems. Therefore, in this paper, we propose a neuro feedback system based on portable EEG that helps induce sleeping. We design and evaluate the EEG classifier, which is the most important function to implement the system, and propose an optimized classifier modeling method for various factors that can affect performance. When using the proposed classifier, we could distinguish 97.9% of awakening and sleep phase in portable EEG.

최근 많은 사람들이 불면증으로 인한 노동력저하, 인지기능저하, 정신질환 증가 등의 불편을 겪고 있다. 이에 대한 해결책은 인지치료나 약물치료가 거의 전부인 수준이나 부작용과 의존성 문제로 인해 장기적으로는 권장되지 않는 방법이다. 따라서 본 논문에서는 수면 유도에 도움이 되는 포터블 뇌파 측정기 기반 뉴로피드백 시스템을 제안한다. 그리고 시스템을 구현하는 데 가장 핵심적인 기능인 뇌파 상태 분류기를 설계하고 평가하며 성능에 영향을 미칠 수 있는 여러 요인들에 대해 최적화된 분류기 모델링 방법을 제시한다. 제안한 분류기를 이용할 시 포터블 뇌파 측정기에서 각성과 수면 단계를 97.9% 정확하게 구분할 수 있었다.

Keywords

OHHGBW_2018_v9n11_83_f0001.png 이미지

Fig. 1. Class labeling of NeuroSky EEG data by referring to the expert labels

OHHGBW_2018_v9n11_83_f0002.png 이미지

Fig. 2. Performance comparison of the tested learning algorithms

OHHGBW_2018_v9n11_83_f0003.png 이미지

Fig. 3. Contribution of features in classification

OHHGBW_2018_v9n11_83_f0004.png 이미지

Fig. 4. Performance comparison of the different labeling approaches

OHHGBW_2018_v9n11_83_f0005.png 이미지

Fig. 5. Performance in the different window size

OHHGBW_2018_v9n11_83_f0006.png 이미지

Fig. 6. Performance comparison between Embletta and NeuroSky (6 states, 5s window size)

OHHGBW_2018_v9n11_83_f0007.png 이미지

Fig. 7. Performance comparison between Embletta and NeuroSky (2 states, 30s window size)

Table 1. The proposed features for classification

OHHGBW_2018_v9n11_83_t0001.png 이미지

References

  1. Yonhapnews. (2017. 7. 12). 'Stress republic' ... "540,000 people are insomnia". www.yonhapnews.co.kr/bulletin/2017/07/11/0200000000AKR20170711142900017.HTML
  2. Embla Systems, Inc. (2010). EmblettaX100.carestreammedical.com/wp-content/uploads/Carestream-Embla-Embletta-X100.pdf
  3. NeuroSky (2018). NeuroSky Mindwave. www.neurosky.com
  4. Welch. P. (1967). The use of Fast Fourier Transform for the estimation of power spectra: A method based on time averaging over short, modified periodograms. IEEE Transactions on Audio and Electroacoustics, AU-15 (2):70-73
  5. Wolpert. E. (1969). A manual of standardized terminology, techniques and scoring system for sleep stages of human subjects. Archives of General Psychiatry, 20(2), 246.
  6. R. Agarwal & G. Jean. (2001). Computer-assisted sleep staging. IEEE Transactions on Biomedical Engineering, 48(12), 1412-1423. https://doi.org/10.1109/10.966600
  7. Weka 3 (2018). Data mining software in Java. www.cs.waikato.ac.nz/ml/weka/
  8. E. Alpaydin. (2010). Introduction to Machine Learning, 2nd ed. Cambridge, MA, USA: The MIT Press.
  9. A. Rechtschaffen & A. Kales. (1968). A manual of standardized terminology, techniques and scoring system of sleep stages in human subjects. Los Angeles: Brain Information Service/Brain Research Institute, University of California.
  10. J. H. Jang, S. Y. Cho & B. Y. Kim. (2002). Automatic sleep stage scoring using single-channel EEG signal. Korean Journal of Brain Science and Technology, 2(2), 129-135.
  11. J. E. Lee & S. K. Yoo. (2013). The design of feature selecting algorithm for sleep stage analysis. Journal of The Institute of Electronics Engineers of Korea, 50(10).
  12. H. S. Han & U. P. Chong. (2012). Electroencephalogrambased driver drowsiness detection system using AR coefficients and SVM. Journal of Korean Institute of Intelligence Systems, 22(6).
  13. J. E. Jeon & S. W. Choi. (2017). Insomnia treatment using neurofeedback: EEG beta decrease protocol. Korean Journal of Clinical Psychology, 36(3), 351-368. https://doi.org/10.15842/kjcp.2017.36.3.006
  14. Y. H. Joo, J. K. Kim & I. H. Ra. (2008). Intelligent drowsiness drive warning system. Journal of Korean Institute of Intelligent Systems, 18(2), 223-229. https://doi.org/10.5391/JKIIS.2008.18.2.223
  15. H. Kataoka, H. Yoshida, A. Saijo, M. Yasuda & M. Osumi. (1998). Development of a skin temperature measuring system for non-contact stress evaluation. Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2, 940-943.
  16. A. Bunde, S. Havlin, J. Kantelhardt, T. Penzel, J. Peter & K. Voigt. (2000). Correlated and uncorrelated regions in heart-rate fluctuations during sleep. Phys. Rev. Lett, 8(85), 3736-3739.
  17. Y. B. Lee & M. H. Lee. (2007). Automobile system for drowsiness accident detection using EDA signal analysis. The Transactions of KIEE, 56(2), 227-450.