한국통신학회논문지 (The Journal of Korean Institute of Communications and Information Sciences)

한국통신학회 (The Korean Institute of Commucations and Information Sciences)
권호 표지
DOI QR코드

DOI QR Code

EIV와 MLP를 이용한 뇌파 기반 운전자의 졸음 감지 시스템

Electroencephalogram-Based Driver Drowsiness Detection System Using Errors-In-Variables(EIV) and Multilayer Perceptron(MLP)

  • 투고 : 2014.08.11
  • 심사 : 2014.09.19
  • 발행 : 2014.10.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

졸음운전은 전체 교통사고 원인 중 큰 비중을 차지하며 그 위험성이 음주운전보다도 크다고 알려져 있다. 따라서 운전자의 졸음을 판단하고 경고하는 시스템 개발에 대한 관심이 높아지고 있으며, 뇌파를 분석하는 것이 운전자의 피로와 졸음을 감지하는데 효과적이라는 연구결과들이 발표되었다. 본 논문은 짧은 시간에 높은 해상도를 가지는 auto-regressive 모델 기법 중 잡음에 강인한 errors-in-variables(EIV) 방법을 이용하여 특징벡터를 추출하고, 다층신경망(multilayer perceptron; MLP)에 적용하여 운전자의 상태를 각성, 천이, 졸음의 세 가지 상태로 분류하는 졸음 감지 시스템을 제안한다. 생체신호의 측정 환경에 따른 성능을 평가하기 위해 높은 진단률을 갖도록 하는 EIV차수를 결정하고, 잡음에 대한 강인성을 확인하기 위해 신호대 잡음비(signal-to-noise ratio; SNR)에 따른 성능을 선형 예측 부호화(linear predictive coding; LPC) 방법과 비교하였다. 이 결과로부터 제안한 EIV와 MLP를 결합한 졸음 감지 시스템은 기존의 LPC와 MLP를 이용한 시스템에 대해 우수한 성능을 얻을 수 있음을 확인하였다.

Drowsy driving is a large proportion of the total car accidents. For this reason, drowsiness detection and warning system for drivers has recently become a very important issue. Monitoring physiological signals provides the possibility of detecting features of drowsiness and fatigue of drivers. Many researches have been published that to measure electroencephalogram(EEG) signals is the effective way in order to be aware of fatigue and drowsiness of drivers. The aim of this study is to extract drowsiness-related features from a set of EEG signals and to classify the features into three states: alertness, transition, and drowsiness. This paper proposes a drowsiness detection system using errors-in-variables(EIV) for extraction of feature vectors and multilayer perceptron (MLP) for classification. The proposed method evaluates robustness for noise and compares to the previous one using linear predictive coding (LPC) combined with MLP. From evaluation results, we conclude that the proposed scheme outperforms the previous one in the low signal-to-noise ratio regime.

키워드

참고문헌

  1. Q. Ji, Z. Zhu, and P. Lan, "Real-time nonintrusive monitoring and prediction of driver fatigue," IEEE Trans. Veh. Technol., vol. 53, no. 4, pp. 1052-1068, 2004. https://doi.org/10.1109/TVT.2004.830974
  2. J. D. Slater, "A definition of drowsiness: One purpose for sleep?," Med. Hypotheses, vol. 71, pp. 641-644, 2008. https://doi.org/10.1016/j.mehy.2008.05.035
  3. J.-M. Choi, H. Song, S. H. Park, and C.-D. Lee, "Implementation of driver fatigue monitoring system," J. KICS, vol. 37, no. 8, pp. 711-720, 2012. https://doi.org/10.7840/kics.2012.37C.8.711
  4. Y. H. Joo, J. K. Kim, and I. H. Ra, "Intelligent drowsiness drive warning system," J. KIIS, vol. 18 no. 2, pp. 223-229, 2008. https://doi.org/10.5391/JKIIS.2008.18.2.223
  5. H. Kataoka, H. Yoshida, A. Saijo, M. Yasuda, and M. Osumi, "Development of a skin temperature measuring system for non-contact stress evaluation," in Proc. 20th Annual Int. Conf. IEEE Eng. Medicine Biology Soc., vol. 2, pp. 940-943, 1998.
  6. A. Bunde, S. Havlin, J. W. Kantelhardt, T. Penzel, J.-H. Peter, and K. Voigt, "Correlated and uncorrelated regions in heart-rate fluctuations during sleep," Phys. Rev. Lett., vol. 85, pp. 3736-3739, 2000. https://doi.org/10.1103/PhysRevLett.85.3736
  7. Y.-B. Lee and M.-H. Lee, "Automobile system for drowsiness accident detection using EDA signal analysis," Trans. KIEE, vol. 56. no. 2, pp. 227-450, 2007.
  8. M. V. M. Yeo, X. Li, K. Shen, and E. P. V. Wilder-Smith. "Can SVM be used for automatic EEG detection of drowsiness during car driving?," Safety Science, vol. 47 pp. 115-116, 2009. https://doi.org/10.1016/j.ssci.2008.01.007
  9. M. Steriade, "Brain electrical activity and sensory processing during waking and sleep states," In: Kryger, M.H., Roth, T., Dement, W. C. (Eds.), Principles and Practice of Sleep Medicine. Saunders, Philadelphia, pp. 93-111, 2000.
  10. S. K. L. Lal and A. Craig, "A critical review of the psychophysiology of driver fatigue," Biological Psychology, vol. 55, pp. 173-94, 2001. https://doi.org/10.1016/S0301-0511(00)00085-5
  11. M. V. M. Yeo, X. Li, and E. P. V. Wilder-Smith, "Characteristic EEG differences between voluntary recumbent sleep onset in bed and involuntary sleep onset in a driving simulator," Clinical Neurophysiology, vol. 118, pp. 1315-1323, 2007. https://doi.org/10.1016/j.clinph.2007.02.001
  12. H. J. Moller, L. Kayumov, E. L. Bulmash, J. Nhan, and C. M. Shapiro, "Simulator performance, microsleep episodes, and subjective sleepiness: normative data using convergent methodologies to assess driver drowsiness," J. Psychosomatic Research, vol. 61, pp. 335-342, 2006. https://doi.org/10.1016/j.jpsychores.2006.04.007
  13. H. Han, D. Kim, D. An, G. B. Hong, and U. Chong, "Driver drowsiness and alertness detection method using linear predictive coding and electroencephalographic change," in Proc. KISPS Falls Conf. 2011, pp. 237-239, Dec. 2011.
  14. R. Diversi, U. Soverini, and R. Guidorzi, "A new estimation approach for AR models in presence of noise," in Proc. Preprints 16th IFAC World Congr., pp. 290-294, 2005.
  15. Y.-S. Kang and C.-S. Bae, "License plates detection using a Gaussian windows," J. KICS, vol. 37, no. 9, pp. 780-785, 2012. https://doi.org/10.7840/kics.2012.37A.9.780
  16. C. J. Lee, B. Son, and H. S. Hong, "Improvement of pattern recognition capacity of the fuzzy ART with the variable learning," J. KICS, vol. 38. no. 15, pp. 954-961, 2013. https://doi.org/10.7840/kics.2013.38B.12.954
  17. B. T. Jap, S. Lal, P. Fischer, and E. Bekiaris, "Using EEG spectral components to assess algorithms for detecting fatigue," Expert Syst. Appl., vol. 36. no. 2, pp. 2352-2359, 2009. https://doi.org/10.1016/j.eswa.2007.12.043