Predicting Highway–Rail Grade Crossing Collision Risk by Neural Network Systems
Publication: Journal of Transportation Engineering, Part A: Systems
Volume 145, Issue 8
Abstract
In this paper, train-vehicle crash risk at highway–rail grade crossings (HRGCs) is analyzed with a neural network (NN) model to return meaningful rankings of crash-contributory-variable importance based on different criteria, but also to produce dependent nonlinear contributor-crash curves with all other contributors considered for a specific contributor variable. Historical crash data for North Dakota public HRGCs from 1996 to 2014 were used for the study. Several principal findings were observed: (1) 22 input variables describing traffic characteristics and crossing characteristics are related to crashes at public HRGCs; (2) a mean-square error–based NN model and a connection weights–based NN model represent two relative contributory-variable importance lists for different application purposes; (3) the effect of different variables on crash likelihood is different when all other contributors are set at different levels, and the relationship between contributors and crash likelihood is dynamic nonlinear; and (4) in predictive and explanatory power, the neural network model outperforms the decision tree approach for the considered case study.
Get full access to this article
View all available purchase options and get full access to this article.
Acknowledgments
This work was partially supported by the US Department of Transportation under Agreement DTRT13-G-UTC38 through Mountain Plains Consortium Transportation Center No. MPC-476 and NDSU development Foundation Project No. FAR0024887. The authors deeply appreciate this funding support.
References
Austin, R., and J. Carson. 2002. “An alternative accident prediction model for highway-rail interfaces.” Accid. Anal. Prev. 34 (1): 31–42. https://doi.org/10.1016/S0001-4575(00)00100-7.
Chadwick, S., N. Y. Zhou, and M. R. Saat. 2014. “Highway-rail grade crossing safety challenges for shared operations of high-speed passenger and heavy freight rail in the US.” Saf. Sci. 28 (Oct): 128–137. https://doi.org/10.1016/j.ssci.2014.03.003.
Chang, L. 2005. “Analysis of freeway accident frequencies: Negative binomial regression versus artificial neural network.” Saf. Sci. 43 (8): 541–557. https://doi.org/10.1016/j.ssci.2005.04.004.
Chang, L., and H. Wang. 2006. “Analysis of traffic injury severity: An application of non-parametric classification tree techniques.” Accid. Anal. Prev. 38 (5): 1019–1027. https://doi.org/10.1016/j.aap.2006.04.009.
Chang, L. Y., and W. C. Chen. 2005. “Data mining of tree-based models to analyze freeway accident frequency.” J. Saf. Res. 36 (4): 365–375. https://doi.org/10.1016/j.jsr.2005.06.013.
Chiou, Y. 2006. “An artificial neural network-based expert system for the appraisal of two-car crash accidents.” Accid. Anal. Prev. 38 (4): 777–785. https://doi.org/10.1016/j.aap.2006.02.006.
Codur, M. Y., and A. Tortum. 2015. “An artificial neural network model for highway accident prediction: A case study of Erzurum, Turkey.” Traffic Transp. 27 (3): 217–225. https://doi.org/10.7307/ptt.v27i3.1551.
Delen, D., R. Sharda, and M. Bessonov. 2006. “Identifying significant predictors of injury severity in traffic accident using a series of artificial neural networks.” Accid. Anal. Prev. 38 (3): 434–444. https://doi.org/10.1016/j.aap.2005.06.024.
Everitt, B. S. 1993. Cluster analysis. 3rd ed. New York: Wiley.
Federal Railroad Administration. 2017. “USDOT launches new railroad crossing safety ad.” Accessed July 1, 2017. https://www.fra.dot.gov/eLib/details/L18522.
Fish, K. E., and J. G. Blodgett. 2003. “A visual method for determining variable importance in an artificial neural network model: An empirical benchmark study.” J. Targeting Meas. Anal. Marketing 11 (3): 244–254. https://doi.org/10.1057/palgrave.jt.5740081.
Garson, G. D. 1991. “Interpreting neural network connection weights.” Artif. Intell. Expert 6 (4): 46–51.
Gevrey, M., I. Dimopoulos, and S. Lek. 2003. “Review and comparison of methods to study the contribution of variables in artificial neural network models.” Ecol. Model. 160 (3): 249–264. https://doi.org/10.1016/S0304-3800(02)00257-0.
Hu, S., C. Li, and C. Lee. 2012. “Model crash frequency at highway-rail grade crossings using negative binomial regression.” J. Chin. Inst. Eng. 35 (7): 841–852. https://doi.org/10.1080/02533839.2012.708527.
Kashani, A. T., R. Rabieyan, and M. M. Besharati. 2014. “A data mining approach to investigate the factors influencing the crash severity of motorcycle pillion passengers.” J. Saf. Res. 51 (Dec): 93–98. https://doi.org/10.1016/j.jsr.2014.09.004.
Li, X., Y. Zhang, and Y. Xie. 2008. “Predicting motor vehicle crashes using support vector machines models.” Accid. Anal. Prev. 40 (4): 1611–1618. https://doi.org/10.1016/j.aap.2008.04.010.
Lu, P., and D. Tolliver. 2016. “Accident prediction model for public highway-rail grade crossings.” Accid. Anal. Prev. 90 (May): 73–81. https://doi.org/10.1016/j.aap.2016.02.012.
McCollister, G., and C. Pflaum. 2007. “A model to predict the probability of highway rail crossing accidents.” Inst. Mech. Eng. 221 (3): 321–329. https://doi.org/10.1243/09544097JRRT84.
McCulloch, W., and W. Pitts. 1943. “A logical calculus of the ideas immanent in nervous activity.” Bull. Math. Biophys. 5 (4): 115–133. https://doi.org/10.1007/BF02478259.
Millegan, H., X. Yan, S. Richards, and L. Han. 2009. “Evaluation of effectiveness of stop sign treatments at highway rail grade crossings.” Transp. Res. Rec. 2122 (1): 78–85. https://doi.org/10.3141/2122-10.
Mussone, L., M. Bassani, and P. Masci. 2017. “Analysis of factors affecting the severity of crashes in urban road intersections.” Accid. Anal. Prev. 103 (Jun): 112–122. https://doi.org/10.1016/j.aap.2017.04.007.
Nielsen, M. A. 2015. “Neural networks and deep learning.” Accessed October 2, 2018. http://static.latexstudio.net/article/2018/0912/neuralnetworksanddeeplearning.pdf.
Oh, A., S. P. Washington, and D. Nam. 2006. “Accident prediction model for railway-highway interfaces.” Accid. Anal. Prev. 38 (2): 346–356. https://doi.org/10.1016/j.aap.2005.10.004.
Olden, J. D., and D. A. Jackson. 2002. “Illuminating the ‘black box’: A randomization approach for understanding variable contributions in artificial neural networks.” Ecol. Model. 154 (1–2): 135–150. https://doi.org/10.1016/S0304-3800(02)00064-9.
Prati, G., L. Pietrantoni, and F. Fraboni. 2017. “Using data mining techniques to predict the severity of bicycle crashes.” Accid. Anal. Prev. 101 (Apr): 44–54. https://doi.org/10.1016/j.aap.2017.01.008.
PSECS (Penn State Eberly College of Science). 2017. “Regression methods.” Accessed June 10, 2017. https://onlinecourses.science.psu.edu/stat501/node/275.
Raub, R. A. 2009. “Examination of highway–rail grade crossing collisions nationally from 1998 to 2007.” Transp. Res. Rec. 2122 (1): 63–71. https://doi.org/10.3141/2122-08.
SAS Institute. 2015a. “Decision tree node.” SAS enterprise miner 14.1 reference help. Accessed June 10, 2017. https://support.sas.com/documentation/cdl/en/emgsj/67981/PDF/default/emgsj.pdf.
SAS Institute. 2015b. “The HPSPLIT procedure.” SAS user’s guide: High-performance procedures. Accessed June 10, 2017. http://support.sas.com/documentation/cdl/en/stathpug/66410/HTML/default/viewer.htm#stathpug_hpsplit_details32.htm.
Xie, Y., D. Lord, and Y. Zhang. 2007. “Predicting motor vehicle collision using Bayesian neural network models: An empirical analysis.” Accid. Anal. Prev. 39 (5): 922–933. https://doi.org/10.1016/j.aap.2006.12.014.
Yan, X., S. Richards, and X. Su. 2010. “Using hierarchical tree-based regression model to predict train-vehicle crashes at passive highway-rail grade crossings.” Accid. Anal. Prev. 42 (1): 64–74. https://doi.org/10.1016/j.aap.2009.07.003.
Ye, Z., Y. Xu, D. Veneziano, and X. Shi. 2014. “Evaluation of winter maintenance chemicals and crashes with an artificial neural network.” Transp. Res. Rec. 2440 (1): 43–50. https://doi.org/10.3141/2440-06.
Zeng, Q., and H. Huang. 2014. “A stable and optimized neural network model for crash injury severity prediction.” Accid. Anal. Prev. 73 (Dec): 351–358. https://doi.org/10.1016/j.aap.2014.09.006.
Zhang, L., and X. Meng. 2011. “An approach to predict road accident frequencies: Application of fuzzy neural network.” Accessed July 2, 2017. http://onlinepubs.trb.org/onlinepubs/conferences/2011/RSS/2/Zheng,L.pdf.
Zhang, Y., Y. Xie, and L. Li. 2012. “Crash frequency analysis of different types of urban roadway segments using generalized additive model.” J. Saf. Res. 43 (2): 107–114. https://doi.org/10.1016/j.jsr.2012.01.003.
Zhao, S., and A. Khattak. 2015. “Motor vehicle drivers’ injuries in train-motor vehicle crashes.” Accid. Anal. Prev. 74 (Jan): 162–168. https://doi.org/10.1016/j.aap.2014.10.022.
Zheng, Z., P. Lu, and D. Tolliver. 2016. “Accident prediction for highway-rail grade crossings using decision tree approach: An empirical analysis.” Transp. Res. Rec. 2545: 115–122. https://doi.org/10.3141/2545-12.
Information & Authors
Information
Published In
Journal of Transportation Engineering, Part A: Systems
Volume 145 • Issue 8 • August 2019
Copyright
©2019 American Society of Civil Engineers.
History
Received: Aug 7, 2018
Accepted: Jan 11, 2019
Published online: May 31, 2019
Published in print: Aug 1, 2019
Discussion open until: Oct 31, 2019
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.