Advertisement

Safety Prognostic Analysis in Traffic System

  • Yong Qin
  • Limin Jia
Chapter
Part of the Advances in High-speed Rail Technology book series (ADVHIGHSPEED)

Abstract

In this chapter, the safety region based theory is extended to the traffic system. The theory applicability will be testified and we will discuss the safety prognostic analysis in traffic system.

The first part of the work is to research the traffic operation risk analysis model based on safety region. Firstly, we propose the state feature extraction algorithm based on SFS-PCA. Secondly, based on the extracted state features, we use LSSVM to assess safety region margin of traffic operation and distinguish traffic operation state. Finally, we test proposed algorithm on case of the American Alameda I-880 highway.

The second part is to research on the traffic crash risk evaluation model based on reliability theory. Firstly, we select state variables applying CART. Secondly, we fit the distribution function of each variable based on reliability and calculate the joint distribution function of variables. Thirdly, we apply SVM approximately to estimate limit state function (LSF), and assess traffic operation risk using LSF. Finally, we also test proposed algorithm on case of the American Alameda I-880 highway.

References

  1. 1.
    J. Pohjalainen, O. Rӓsӓnen, S. Kadioglu, Feature selection methods and their combinations in high-dimensional classification of speaker likability, intelligibility and personality traits. Comput. Speech Lang. 29, 145–171 (2015)CrossRefGoogle Scholar
  2. 2.
    K. Pearson, On lines and planes of closest fit to systems in space. Phios. Mag. 2, 559–573 (1901)CrossRefGoogle Scholar
  3. 3.
    C. Xu, P. Liu, W. Wang, Z. Li, Evaluation of the impacts of traffic states on crash risk on freeways. Accid. Anal. Prev. 47, 162–171 (2012)CrossRefGoogle Scholar
  4. 4.
    R. Yu, M. Abdel-Aty, Utilizing support vector machine in real-time crash risk evaluation. Accid. Anal. Prev. 51, 252–259 (2013)CrossRefGoogle Scholar
  5. 5.
    K. Polat, S. Güneş, A novel approach to estimation of E. coli promoter gene sequences: Combining feature selection and least square support vector machine (FS_LSSVM). Appl. Math. Comput. 190, 1574–1582 (2007)MathSciNetzbMATHGoogle Scholar
  6. 6.
    H.B. Basaga, A. Bayraktar, I. Kaymaz, An improved response surface method for reliability analysis of structures. Struct. Eng. Mech. 42(2), 175–189 (2012)CrossRefGoogle Scholar
  7. 7.
    A.M. Hasofer, N.C. Lind, Exact and invariant second-moment code format. J. Eng. Mech. 100(1), 111–121 (1974)Google Scholar
  8. 8.
    A.D. Kiureghian, H.Z. Lin, S.J. Hwang, Second-order reliability approximations. J. Eng. Mech. 113(8), 1208–1225 (1987)CrossRefGoogle Scholar
  9. 9.
    B.K. Low, W.H. Tang, Reliability analysis using object-oriented constrained optimization. Struct. Saf. 26, 69–89 (2004)CrossRefGoogle Scholar
  10. 10.
    R. Yu, Q. Shi, M. Abdel-Aty. Feasibility of incorporating reliability analysis in traffic safety investigation, Transportation Research Record: Journal of Transportation Research Board, No. 2386, Transportation Research Board of the National Academies, Washington, DC., (2013), pp. 35–41Google Scholar
  11. 11.
    H. William, A.S.A. Teukolsky, W.T. Vetterling, B.P. Flannery, Numerical Recipes in C: The Art of Scientific Computing (Cambridge University England EPress, New Delhi, 1992)zbMATHGoogle Scholar
  12. 12.
    U. Alibrandi, A.M. Alani, G. Ricciardi, A new sampling strategy for SVM-based response surface for structural reliability analysis. Probab. Eng. Mech. 41, 1–12 (2015)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Yong Qin
    • 1
  • Limin Jia
    • 1
  1. 1.Beijing Jiaotong UniversityBeijingChina

Personalised recommendations