Skip to main content
SpringerLink
Log in

Predicting Freeway Incident Duration Using Machine Learning

  • Published:
International Journal of Intelligent Transportation Systems Research Aims and scope Submit manuscript

Abstract

Traffic incident duration provides valuable information for traffic management officials and road users alike. Conventional mathematical models may not necessarily capture the complex interaction between the many variables affecting incident duration. This paper summarizes the application of five state-of-the-art machine learning (ML) models for predicting traffic incident duration. More than 110,000 incident records with over 52 variables were retrieved from Houston TranStar data archive. The attempted ML techniques include: regression decision tree, support vector machine (SVM), ensemble tree (bagged and boosted), Gaussian process regression (GPR), and artificial neural networks (ANN). These methods are known to effectively handle extensive and complex datasets. Towards achieving the best modeling accuracy, the parameters of each of these models were fine-tuned. The results showed that the SVM and GPR models outperformed other techniques in terms of the mean absolute error (MAE) with the best model scoring an MAE of 14.34 min. On the other hand, the simple regression tree was the worst overall model with an MAE of 16.74 min. In terms of training time, a considerable difference was found between two groups of models: regression decision tree, ensemble tree, and ANN on one hand and SVM and GPR on the other. The former required shorter training time (less than one hour each) whereas the latter had training times ranging between 5 to 34 hours per model.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

References

  1. Baker, L., Ellison, D.: The wisdom of crowds - ensembles and modules in environmental modelling. Geoderma. 147(1–2), 1–7 (2008). https://doi.org/10.1016/j.geoderma.2008.07.003

    Article  Google Scholar 

  2. Blockeel, H., De Raedt, L.: Top-down induction of first-order logical decision trees. Artif. Intell. 101(1–2), 285–297 (1998). https://doi.org/10.1016/S0004-3702(98)00034-4

    Article  MathSciNet  MATH  Google Scholar 

  3. Breiman, L.: Classification and Regression Trees. Routledge, New York (1984)

    MATH  Google Scholar 

  4. Breiman, L.: Bagging predictors. Mach. Learn. 24(2), 123–140 (1996). https://doi.org/10.1007/BF00058655

    Article  MATH  Google Scholar 

  5. Briggs, V., & Jasper, K. (2001). Organizing for Regional Transportation Operations: Houston TranStar

    Google Scholar 

  6. Chung, Y.: Development of an accident duration prediction model on the Korean freeway systems. Accid. Anal. Prev. 42(1), 282–289 (2010). https://doi.org/10.1016/j.aap.2009.08.005

    Article  Google Scholar 

  7. Cortes, C., Vapnik, V.: Support vector networks. Mach. Learn. 20(3), 273–297 (1995). https://doi.org/10.1007/BF00994018

    Article  MATH  Google Scholar 

  8. El-Basyouny, K., Sayed, T., Trb: Comparison of Two Negative Binomial Regression Techniques in Developing Accident Prediction Models. Statistical Methods and Crash Prediction Modeling. 1950(January 2006), 9–16 (2006). https://doi.org/10.3141/1950-02

    Article  Google Scholar 

  9. Friedman, J.H.: Greedy function approximation: a gradient boosting machine. Ann. Stat. (2001)

  10. J. Friedman, T. Hastie, R. Tibshirani (1998). A\dditive logistic regression: a statistical view of boosting

  11. Garib, A., Radwan, A.E., Al-Deek, H.: Estimating Magnitude and Duration of Incident Delays. Journal of Transportation Engineering. 123(DECEMBER), 459–466 (1997). https://doi.org/10.1061/(ASCE)0733-947X(1997)123:6(459

    Article  Google Scholar 

  12. Giam, X., Olden, J.D.: A new R2-based metric to shed greater insight on variable importance in artificial neural networks. Ecol. Model. 313, 307–313 (2015). https://doi.org/10.1016/j.ecolmodel.2015.06.034

    Article  Google Scholar 

  13. Givargis, S., Karimi, H.: A basic neural traffic noise prediction model for Tehran’s roads. J. Environ. Manag. 91(12), 2529–2534 (2010). https://doi.org/10.1016/j.jenvman.2010.07.011

    Article  Google Scholar 

  14. Hastie, T., Tibshirani, R., Friedman, J.: The Elements of Statistical Learning Data Mining, Inference, and Prediction (Second Edi). Springer (2009)

  15. Hu, J., Krishnan, R., & Bell, M. G. H. (2011). Incident duration prediction for in-vehicle navigation system. In Transportation Research Board 90th Annual Meeting. Washington D.C.: T

  16. Izenman, A.: Modern Multivariate Statistical Techniques. Springer, New York (2008)

    Book  Google Scholar 

  17. Junhua, W., Haozhe, C., Shi, Q.: Estimating freeway incident duration using accelerated failure time modeling. Saf. Sci. 54, 43–50 (2013). https://doi.org/10.1016/j.ssci.2012.11.009

    Article  Google Scholar 

  18. Kavousi-Fard, A., Samet, H., Marzbani, F.: A new hybrid modified firefly algorithm and support vector regression model for accurate short term load forecasting. Expert Syst. Appl. 41(13), 6047–6056 (2014). https://doi.org/10.1016/j.eswa.2014.03.053

    Article  Google Scholar 

  19. Khattak, A.J., Liu, J., Wali, B., Li, X., Ng, M.: Modeling traffic incident duration using quantile regression. Transportation Research Record: Journal of the Transportation Research Board. 2554(1), 139–148 (2016). https://doi.org/10.3141/2554-15

    Article  Google Scholar 

  20. Kim, H.J., Choi, H.-K.: A comparative analysis of incident service time on urban freeways. IATSS Research. 25(1), 62–72 (2001). https://doi.org/10.1016/S0386-1112(14)60007-8

    Article  Google Scholar 

  21. Kumar, P., Nigam, S.P., Kumar, N.: Vehicular traffic noise modeling using artificial neural network approach. Transportation Research Part C: Emerging Technologies. 40, 111–122 (2014). https://doi.org/10.1016/j.trc.2014.01.006

    Article  Google Scholar 

  22. Lee, Y., Wei, C.H.: A computerized feature selection method using genetic algorithms to forecast freeway accident duration times. Computer-Aided Civil and Infrastructure Engineering. 25(2), 132–148 (2010). https://doi.org/10.1111/j.1467-8667.2009.00626.x

    Article  Google Scholar 

  23. Li, R., Pereira, F.C., Ben-Akiva, M.E.: Competing risks mixture model for traffic incident duration prediction. Accid. Anal. Prev. 75, 192–201 (2015). https://doi.org/10.1016/j.aap.2014.11.023

    Article  Google Scholar 

  24. Li, Z., Zhang, Q., Zhao, X.: Performance analysis of K-nearest neighbor, support vector machine, and artificial neural network classifiers for driver drowsiness detection with different road geometries. International Journal of Distributed Sensor Networks. 13(9), 155014771773339 (2017). https://doi.org/10.1177/1550147717733391

    Article  Google Scholar 

  25. Rasmussen, C., Williams, C.: Gaussian Processes for Machine Learning. MIT press, Cambridge (2006)

    MATH  Google Scholar 

  26. Stewart, J.: Applications of classification and regression tree methods in roadway safety studies. Transportation Research Record: Journal of the Transportation Research Board. 1542(1), 1–5 (1996)

    Article  Google Scholar 

  27. Sun, B., Park, B.B.: Route choice modeling with support vector machine. Transportation Research Procedia. 25, 1811–1819 (2017). https://doi.org/10.1016/j.trpro.2017.05.151

    Article  Google Scholar 

  28. Tavassoli Hojati, A., Ferreira, L., Washington, S., Charles, P.: Hazard based models for freeway traffic incident duration. Accid. Anal. Prev. 52, 171–181 (2013). https://doi.org/10.1016/j.aap.2012.12.037

    Article  Google Scholar 

  29. Tso, G.K.F., Yau, K.K.W.: Predicting electricity energy consumption: a comparison of regression analysis, decision tree and neural networks. Energy. 32(9), 1761–1768 (2007). https://doi.org/10.1016/j.energy.2006.11.010

    Article  Google Scholar 

  30. Valenti, G., Lelli, M., Cucina, D.: A comparative study of models for the incident duration prediction. Eur. Transp. Res. Rev. 2(2), 103–111 (2010). https://doi.org/10.1007/s12544-010-0031-4

    Article  Google Scholar 

  31. Vlahogianni, E.I., Karlaftis, M.G.: Fuzzy-entropy neural network freeway incident duration modeling with single and competing uncertainties. Computer-Aided Civil and Infrastructure Engineering. 28(6), 420–433 (2013). https://doi.org/10.1111/mice.12010

    Article  Google Scholar 

  32. Wei, C.H., Lee, Y.: Sequential forecast of incident duration using artificial neural network models. Accid. Anal. Prev. 39(5), 944–954 (2007). https://doi.org/10.1016/j.aap.2006.12.017

    Article  Google Scholar 

  33. Wu, W., Chen, S., & Zheng, C. (2011). Traffic incident duration prediction based on support vector regression. In 11th International Conference of Chinese Transportation Professionals (ICCTP) (pp. 2412–2421)

  34. Yin, T., Zhong, G., Zhang, J., He, S., Ran, B.: A prediction model of bus arrival time at stops with multi-routes. Transportation Research Procedia. 25, 4627–4640 (2017). https://doi.org/10.1016/j.trpro.2017.05.381

    Article  Google Scholar 

  35. Zhang, H., Khattak, A.: What is the role of multiple secondary incidents in traffic operations? J. Transp. Eng. 136(November), 986–997 (2010). https://doi.org/10.1061/(ASCE)TE.1943-5436.0000164

    Article  Google Scholar 

  36. Ziari, H., Maghrebi, M., Ayoubinejad, J., Waller, S.T.: Prediction of pavement performance. Transportation Research Record: Journal of the Transportation Research Board. 2589(2589), 135–145 (2016). https://doi.org/10.3141/2589-15

    Article  Google Scholar 

Download references

Acknowledgements

The authors would like to acknowledge the help received from Houston TranStar and Texas A&M Transportation Institute, especially in providing us with the data used to complete this research study.

Author information

Authors and Affiliations

  1. Department of Civil and Environmental Engineering, Sustainable Civil Infrastructure Systems Research Group, Research Institute of Sciences & Engineering, University of Sharjah, Sharjah, United Arab Emirates

    Khaled Hamad

  2. Sustainable Civil Infrastructure Systems Research Group, Research Institute of Sciences & Engineering, University of Sharjah, Sharjah, United Arab Emirates

    Mohamad Ali Khalil

  3. Department of Civil and Environmental Engineering, University of Sharjah, Sharjah, United Arab Emirates

    Abdul Razak Alozi

Authors
  1. Khaled Hamad
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mohamad Ali Khalil
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Abdul Razak Alozi
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Khaled Hamad.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hamad, K., Khalil, M.A. & Alozi, A.R. Predicting Freeway Incident Duration Using Machine Learning. Int. J. ITS Res. 18, 367–380 (2020). https://doi.org/10.1007/s13177-019-00205-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13177-019-00205-1

Keywords

Search

Navigation