Incident Duration Prediction with Hybrid Tree-based Quantile Regression

  • Qing He
  • Yiannis Kamarianakis
  • Klayut Jintanakul
  • Laura Wynter
Chapter
First Online:
Part of the Complex Networks and Dynamic Systems book series (CNDS, volume 2)

Abstract

Accurate prediction of incident duration is critical for efficient incident management which aims to minimize the impact of non-recurrent congestion. In this chapter, a hybrid tree-based quantile regression method is proposed for incident duration prediction and quantification of the effects of various incident and traffic characteristics that determine duration. Hybrid tree-based quantile regression incorporates the merits of both quantile regression modeling and tree-structured modeling: robustness to outliers, simple interpretation, flexibility in combining categorical covariates, and capturing nonlinear associations. The predictive models presented here are based on variables associated with incident characteristics as well as the traffic conditions before and after incident occurrence. Compared to previous approaches, the hybrid tree-based quantile regression offers higher predictive accuracy.

Keywords

Quantile Regression Traffic Data Quantile Regression Model Incident Duration Incident Characteristic 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in to check access.

References

  1. Breiman L, et al. Classification and regression trees. New York: Chapman & Hall; 1984.Google Scholar
  2. Chassiakos AP, Stephanedes YJ. Smoothing algorithms for incident detection. Transport Res Rec J Tranport Res Board 1993;1394:8–16.Google Scholar
  3. Chin SM, et al. Temporary loss of highway capacity and impacts on performance: phase 2. Oak Ridge, Tennessee: Oak Ridge National Laboratory; 2004.CrossRefGoogle Scholar
  4. Choe T, Skabardonis A, Varaiya P. Freeway performance measurement system: operational analysis tool. Transport Res Rec J Transport Res Board c;1811:67–75.Google Scholar
  5. CHP. 2011. CHP traffic incident information page. Available at: http://cad.chp.ca.gov/[AccessedApril27,2011].Google Scholar
  6. Chung Y. Development of an accident duration prediction model on the Korean Freeway Systems. Accid Anal Prev. 2010;42:282–289.CrossRefGoogle Scholar
  7. Chung Y, Walubita LF, Choi K. Modeling accident duration and its mitigation strategies on South Korean Freeway Systems. Transport Res Rec J Transport Res Board 2010;2178:49–57.CrossRefGoogle Scholar
  8. Demiroluk S, Ozbay K. Structure learning for the estimation of non-parametric incident duration prediction models. In: Proceedings 90th Annual Meeting of TRB (CD-ROM). Washington D.C.: 2011.Google Scholar
  9. Garib A, Radwan AE, Al-Deek H. Estimating magnitude and durationof incident delays. J Transport Eng. 1997;123(6):459–466.CrossRefGoogle Scholar
  10. Giuliano G. Incident characteristics, frequency, and duration on a high volume urban freeway. Transport Res. 1989;23A:387–396.Google Scholar
  11. Golob TF, Recker WW, Leonard ID. An analysis of truck involved freeway accidents. Accid Anal Prev. 1987;19:375–395.CrossRefGoogle Scholar
  12. Hothorn T, et al. 2011. CRAN - Package party. party: A Laboratory for Recursive Partytioning. Available at: http://cran.r-project.org/web/packages/party/[AccessedMay3,2011].Google Scholar
  13. Hothorn T, Hornik K, Zeileis A. Unbiased recursive partitioning: a conditional inference framework. J Comput Graph Stat. 2006;15:651–674.CrossRefGoogle Scholar
  14. Jones B, Jassen L, Mannering FL. Analysis of the frequency and duration of freeway accidents in Seattle. Accid Anal Prev. 1991;23:239–255.CrossRefGoogle Scholar
  15. Khattak AJ, Schofer JL, Wang M-H. A simple time sequential procedure for predicting freeway incident duration. IVHS J 1994;1:1–26.Google Scholar
  16. Kim W, Natarajan S, Chang G. Empirical analysis and modeling of freeway incident duration. In: Proceedings of the 11th International IEEE Conference on Intelligent Transportation Systems. Beijing, China:2008.Google Scholar
  17. Koenker R. Quantile regression. Cambridge: Cambridge University Press; 2005.CrossRefGoogle Scholar
  18. Lee D-H, Jeng S, Ng M. Defining the incident impact area for traffic diversion: knowledge discovery via a data mining approach. In: Proceedings 82th Annual Meeting of TRB (CD-ROM). Washington D.C. 2003.Google Scholar
  19. Lee Y, Wei C-H. A computerized feature selection method using genetic algorithms to forecast freeway accident duration times. Comput Aided Civ Infrastruct Eng. 2010;25(2):132–148.CrossRefGoogle Scholar
  20. Loh W-Y. Classification and regression tree methods. In: Ruggeri F, Kenett R, Faltin FW, editors. Encyclopedia of statistics in quality and reliability. Chichester: Wiley; 2008. p. 315–323.Google Scholar
  21. Murthy SK. Automatic construction of decision trees from data: a multi-disciplinary survey. Data Min Knowl Discov. 1998;2:345–389.CrossRefGoogle Scholar
  22. Nam D, Mannering FL. An exploratory hazard-based analysis of highway incident duration. Transport Res A 2000;34:85–102.Google Scholar
  23. Oh J, Jayakrishnan R. Temporal control of variable message signs toward achieving dynamic system optimum. In: Proceedings 79th Annual Meeting of TRB (CD-ROM) 2000.Google Scholar
  24. Ozbay K, Kachroo P. Incident management in intelligent transportation systems. Boston: Artech House; 1999.Google Scholar
  25. Payne HJ, Tignor SC. Freeway incident-detection algorithmsbased on decision trees with states. Transport Res Rec J Tranport Res Board 1978;682:30–37.Google Scholar
  26. Qi Y, Smith BL. Identifying nearest neighbors in a large-scale incident data archive. Transport Res Rec J Transport Res Board 2004;1879:89–98.Google Scholar
  27. Qi Y, Teng H. An information-based time sequential approach to online incident duration prediction. J Intell Transport Syst. 2008;12(1):1–12.CrossRefGoogle Scholar
  28. R Development Core Team, R: a language and environment for statistical computing. Vienna, Austria: R Foundation for Statistical Computing; 2009.Google Scholar
  29. Smith KW, Smith BL. Forecasting the clearance time of freeway accidents. Charlottesville, VA: Center for Transportation Studies, University of Virginia; 2001.Google Scholar
  30. Srinivasan K, Krishnamurthy A. Roles of spatial and temporal factors in variable message sign effectiveness under nonrecurrent congestion. Transport Res Rec J Tranport Res Board 2003;1854:124–134.Google Scholar
  31. Therneau TM, Atkinson B. 2011. CRAN - Package rpart. rpart: Recursive Partitioning. Available at: http://cran.r-project.org/web/packages/rpart/index.html[AccessedMay4,2011].Google Scholar
  32. Wei CH, Lee Y. Sequential forecast of incidentduration using artificial neural network models. Accid Anal Prev. 2007;39(5):944–54.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  • Qing He
    • 1
  • Yiannis Kamarianakis
    • 1
  • Klayut Jintanakul
    • 1
  • Laura Wynter
    • 1
  1. 1.IBM T. J. Watson Research CenterYorktown HeightsUSA

Personalised recommendations