Learning Characteristic Driving Operations in Curve Sections that Reflect Drivers’ Skill Levels

  • Shuguang Li
  • Shigeyuki Yamabe
  • Yoichi Sato
  • Yoshihiro Suda
  • Naiwala P. Chandrasiri
  • Kazunari Nawa


Our main objective was to develop a new driving assistance system that could help less experienced drivers improve their driving skills. We describe a statistical method we developed to extract distinctions between experienced and less experienced drivers. This paper makes three key contributions. The first involves a technology for feature extraction based on AdaBoost, which selects a small number of features critical for operation between experienced and less experienced drivers. The second involves a simple definition for experienced and less experienced drivers. The third involves the introduction of wavelet transforms that were used to analyze the frequency characteristics of driver operations. We performed a series of experiments using a driving simulator on a specially designed course that included several curves and then used the proposed method to extract features of driving operations that demonstrated the differences between the two groups.


Driver behavior Driving simulator Driving skill Features extraction Curve sections 


  1. 1.
    Kato, H., Kobayashi, S.: Factors contributing to improved fuel economy in eco-drive. J. Soc. Automot. Eng. Jpn. 62(11), 79–84 (2008) (in Japanes-e)Google Scholar
  2. 2.
    Murphey Y L., Milton R., Kiliaris L.: Driver’s style classification using jerk analysis. Computational intelligence in vehicles and vehicular systems, CIVVS ‘09. IEEE workshop, pp. 23–28 (2009)Google Scholar
  3. 3.
    Chandrasiri N.P., Nawa K., Ishii A., Li S., Yamabe S., Sato Y., Hirasawa T., Suda Y., Matsumura T., Taguchi K.: Driver skill analysis using machine learning: the full curve and curve segmented cases, The 12th International Conference on ITS Telecommunications, pp. 542–547 (2012)Google Scholar
  4. 4.
    Odenheimer, G.L., Beaudet, M., Jette, A.M., Albert, M.S., Grande, L., Minaker, K.L.: Performance-based driving evaluation of the elderly driver: safety, reliability, and validity. J. Gerontol. Med. Sci. 49(4), 153–159 (1994)CrossRefGoogle Scholar
  5. 5.
    Ferguson, S.A.: Other high-risk factors for young drivers. J. Saf. Res. 34, 71–77 (2003)CrossRefGoogle Scholar
  6. 6.
    Tada, M., Ohmura, R., Futoshi Naya, Noma, H., Toriyama, T.: Analysis of steering control behavior using 3D-accelerometers [in Japanese]. CVIM 93, 233–240 (2006)Google Scholar
  7. 7.
    Yamada M., Yamashita K., Yamasaki H., Kawasumi M., Yamada M., Yamamoto S., Nakano T.: Study on measurement and evaluation of novice driving ability, 10th Symposium on ITS peer-review proceedings, 1-D-4, pp. 1–6 (2011)Google Scholar
  8. 8.
    Tokunaga, R.A., Asano, M., Munehiro, K., Hagiwara, T., Kunugiza, K., Kagaya, S.: Effects of curve designs and road conditions on driver’s curve sharpness judgment and driving behavior. J. East. Asia Soc. Transp. Stud. 6, 3536–3550 (2005)Google Scholar
  9. 9.
    Li S., Yamaguchi D., Sato Y., Suda Y., Hirasawa T., Takeuchi S., Yoshioka S.: Differentiating skilled and unskilled drivers by using an Adaboost classifier for driver’s operations. 18th World Congress on Intel-ligent Transport Systems, TS92-3044, pp. 1–11 (2011)Google Scholar
  10. 10.
    Zhang, Y., Lin, W.C., Chin, Y.-K.S.: A pattern-recognition approach for driving skill characterization. IEEE Trans. Intell. Transp. Syst. 11(4), 905–916 (2010)CrossRefGoogle Scholar
  11. 11.
    Viola, P., et al.: Robust real-time object detection. Int. J. Comput. Vis. 57(2), 137–154 (2001)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Tamura, A., Morooka, K., Kurazume, R., Iwashita, Y., Uchida, S., Hara, K., Nakanishi, Y., Hashizume, M., Hasegawa, T.: Trachea and esophagus classification by AdaBoost. IEICE Trans. Inf. Syst. (Japan. Ed.) J92-D(12), 2249–2260 (2009)Google Scholar
  13. 13.
    Mao, J., Jain, A.K.: Artificial neural networks for feature extraction and multivariate data projection. IEEE Trans. Neural Netw. 6(2), 296–317 (1995)CrossRefGoogle Scholar
  14. 14.
    Watanabe S., Furuhashi T., Obata K., Uchikawa Y.: A study on feature extraction using a fuzzy net for off-line signature recognition. Neural Networks, 1993. IJCNN ‘93-Nagoya. Proceedings of 1993 International Joint Conference, vol. 3, pp. 2857–2860 (1993)Google Scholar
  15. 15.
    Lerner B., Guterman H., Aladjem M., Dinstein I.: Feature extraction by neural network nonlinear mapping for pattern classification. The 13th International Conference on Pattern Recognition, ICPR13, vol. 4, pp. 320–324 (1996)Google Scholar
  16. 16.
    Kar, C., Mohanty, A.R.: Monitoring gear vibrations through motor current signature analysis and wavelet transform. Mech. Syst. Signal Process. 20, 158–187 (2006)CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2014

Authors and Affiliations

  • Shuguang Li
    • 1
  • Shigeyuki Yamabe
    • 2
  • Yoichi Sato
    • 1
  • Yoshihiro Suda
    • 1
  • Naiwala P. Chandrasiri
    • 3
  • Kazunari Nawa
    • 3
  1. 1.Institute of Industrial ScienceThe University of TokyoTokyoJapan
  2. 2.Tohoku University, New Industry Creation Hatchery CenterSendaiJapan
  3. 3.Toyota Info Technology Center Co. LTDTokyoJapan

Personalised recommendations