Informing the Work Zone Safety Policy Analysis: Reconciling Multivariate Prediction and Artificial Neural Network Modeling
Publication: Journal of Transportation Engineering, Part A: Systems
Volume 150, Issue 2
Abstract
Work zone safety, as an issue requiring complex solutions and tech-driven investment, has been a major concern for transportation agencies and policymakers. To help decision-makers prioritize investments, there is a need for tools enabling them to assess policies designed to reduce the cost and count of work zone crashes at the same time. Traditional statistical methods, however, are unable to consider two or more target variables when they are intrinsically different (e.g., when a mixture of continuous and dichotomous/discrete variables is of interest). As a result, the dependencies among the outputs of interest may be neglected, which potentially causes biased decision-making. In this study, we used two machine learning models, i.e., group method of data handling (GMDH) and multilayer perceptron (MLP), to simultaneously predict count and cost of work zone crashes in the state of Tennessee in the United States. We further used these tools to assess four policies that could help improve work zone safety. We compared predictability of these models in individual prediction of cost and count with the three statistical models of Poisson regression, negative binomial regression, and multivariate regression. Also, we compared the importance of different variables to evaluate the role that each input variable plays in prediction and recognized the most effective factors. Our results indicated that reduction of annual average daily traffic (AADT) and speed limit are the most effective policies to simultaneously lower work zone crash count and costs, ensued by reducing the percentage of trucks and prohibiting commercial vehicles on segments. We observed that MLP and GMDH perform almost equally in the simultaneous prediction, while these models provide significantly greater degrees of accuracy in crash count and cost prediction, compared with statistical models. The results depicted that the major predictors of cost and count prediction of work zone crashes are speed limit, illumination, involving commercial vehicles, AADT, type of road segment, and percentage of trucks.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code that support the findings of this study are available from the corresponding author upon reasonable request.
Acknowledgments
The authors would like to thank two anonymous reviewers for their constructive comments, which helped us make significant improvements to the paper.
References
Abduljabbar, R., H. Dia, S. Liyanage, and S. A. Bagloee. 2019. “Applications of artificial intelligence in transport: An overview.” Sustainability 11 (1): 189. https://doi.org/10.3390/su11010189.
Aguero-Valverde, J., and P. P. Jovanis. 2008. “Analysis of road crash frequency with spatial models.” Transp. Res. Rec. 2061 (1): 55–63. https://doi.org/10.3141/2061-07.
Al-Bdairi, N. S. S. 2020. “Does time of day matter at highway work zone crashes?” J. Saf. Res. 73 (Jun): 47–56. https://doi.org/10.1016/j.jsr.2020.02.013.
Alruwaished, A. F. 2014. “Characteristics of drivers who cause run-off-road-crashes on Ohio roadways.” Doctoral dissertation, Dept. of Civil and Environmental Engineering and Engineering Mechanics, Univ. of Dayton.
Amiri, A. M., A. Sadri, N. Nadimi, and M. Shams. 2020. “A comparison between artificial neural network and hybrid intelligent genetic algorithm in predicting the severity of fixed object crashes among elderly drivers.” Accid. Anal. Prev. 138 (Jun): 105468. https://doi.org/10.1016/j.aap.2020.105468.
Bhattarai, S., M. M. Golias, S. Mishra, and A. Talebian. 2020. “Multidimensional resource allocation for freight transportation project planning and decision making.” Transp. Res. Part A Policy Pract. 137 (May): 95–110. https://doi.org/10.1016/j.tra.2020.04.017.
Bhowmik, T., S. Yasmin, and N. Eluru. 2018. “A joint econometric approach for modeling crash counts by collision type.” Anal. Methods Accid. Res. 19 (Sep): 16–32. https://doi.org/10.1016/j.amar.2018.06.001.
Bullough, J. D., E. T. Donnell, and M. S. Rea. 2013. “To illuminate or not to illuminate: Roadway lighting as it affects traffic safety at intersections.” Accid. Anal. Prev. 53 (Apr): 65–77. https://doi.org/10.1016/j.aap.2012.12.029.
Caliendo, C., M. L. De Guglielmo, and M. Guida. 2013. “A crash-prediction model for road tunnels.” Accid. Anal. Prev. 55 (Jun): 107–115. https://doi.org/10.1016/j.aap.2013.02.024.
Caliendo, C., M. Guida, and A. Parisi. 2007. “A crash-prediction model for multilane roads.” Accid. Anal. Prev. 39 (4): 657–670. https://doi.org/10.1016/j.aap.2006.10.012.
Cantor, D. E., T. M. Corsi, C. M. Grimm, and K. Özpolat. 2010. “A driver focused truck crash prediction model.” Transp. Res. Part E Logist. Transp. Rev. 46 (5): 683–692. https://doi.org/10.1016/j.tre.2009.08.011.
Carson, J., and F. Mannering. 2001. “The effect of ice warning signs on ice-accident frequencies and severities.” Accid. Anal. Prev. 33 (1): 99–109. https://doi.org/10.1016/S0001-4575(00)00020-8.
Chakraborty, A., D. Mukherjee, and S. Mitra. 2019. “Development of pedestrian crash prediction model for a developing country using artificial neural network.” Int. J. Inj. Control Saf. Promot. 26 (3): 283–293. https://doi.org/10.1080/17457300.2019.1627463.
Chang, L.-Y. 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.
Chen, C., and Y. Xie. 2016. “Modeling the effects of AADT on predicting multiple-vehicle crashes at urban and suburban signalized intersections.” Accid. Anal. Prev. 91 (May): 72–83. https://doi.org/10.1016/j.aap.2016.02.016.
Chen, E., and A. P. Tarko. 2014. “Modeling safety of highway work zones with random parameters and random effects models.” Anal. Methods Accid. Res. 1 (Jan): 86–95. https://doi.org/10.1016/j.amar.2013.10.003.
Das, A., M. Abdel-Aty, and A. Pande. 2009. “Using conditional inference forests to identify the factors affecting crash severity on arterial corridors.” J. Saf. Res. 40 (4): 317–327. https://doi.org/10.1016/j.jsr.2009.05.003.
Dattalo, P. 2013. Analysis of multiple dependent variables. Oxford, UK: Oxford University Press.
Dogru, N., and A. Subasi. 2018. “Traffic accident detection using random forest classifier.” In Proc., 2018 15th Learning and Technology Conference (L&T), 40–45, New York: IEEE.
Dong, N., H. Huang, and L. Zheng. 2015. “Support vector machine in crash prediction at the level of traffic analysis zones: Assessing the spatial proximity effects.” Accid. Anal. Prev. 82 (Sep): 192–198. https://doi.org/10.1016/j.aap.2015.05.018.
Enders, C. K. 2003. “Performing multivariate group comparisons following a statistically significant MANOVA.” Meas. Eval. Couns. Dev. 36 (1): 40–56. https://doi.org/10.1080/07481756.2003.12069079.
Ghasemzadeh, A., and M. M. Ahmed. 2019. “Complementary parametric probit regression and nonparametric classification tree modeling approaches to analyze factors affecting severity of work zone weather-related crashes.” J. Mod. Transp. 27 (2): 129–140. https://doi.org/10.1007/s40534-018-0178-6.
Gu, X., T. Li, Y. Wang, L. Zhang, Y. Wang, and J. Yao. 2018. “Traffic fatalities prediction using support vector machine with hybrid particle swarm optimization.” J. Algorithms Comput. Technol. 12 (1): 20–29. https://doi.org/10.1177/1748301817729953.
Guido, G., S. S. Haghshenas, S. S. Haghshenas, A. Vitale, V. Gallelli, and V. Astarita. 2020. “Development of a binary classification model to assess safety in transportation systems using GMDH-type neural network algorithm.” Sustainability 12 (17): 6735. https://doi.org/10.3390/su12176735.
Halim, Z., R. Kalsoom, S. Bashir, and G. Abbas. 2016. “Artificial intelligence techniques for driving safety and vehicle crash prediction.” Artif. Intell. Rev. 46 (3): 351–387. https://doi.org/10.1007/s10462-016-9467-9.
Hartung, J., and G. Knapp. 2005. “Multivariate multiple regression.” In Encyclopedia of statistics in behavioral science. Chichester, UK: John Wiley & Sons, Ltd. https://doi.org/10.1002/0470013192.bsa432.
Harwood, D., K. Bauer, K. Richard, D. Gilmore, J. Graham, I. Potts, D. Torbic, and E. Hauer. 2007. National cooperative highway research program document 129, phases I and II: Methodology to predict the safety performance of urban and suburban arterials. Washington, DC: Transportation Research Board.
Iranitalab, A., and A. Khattak. 2017. “Comparison of four statistical and machine learning methods for crash severity prediction.” Accid. Anal. Prev. 108 (Nov): 27–36. https://doi.org/10.1016/j.aap.2017.08.008.
Islam, M., N. Alnawmasi, and F. Mannering. 2020. “Unobserved heterogeneity and temporal instability in the analysis of work-zone crash-injury severities.” Anal. Methods Accid. Res. 28 (Nov): 100130. https://doi.org/10.1016/j.amar.2020.100130.
Jonsson, T., J. N. Ivan, and C. Zhang. 2007. “Crash prediction models for intersections on rural multilane highways: Differences by collision type.” Transp. Res. Rec. 2019 (1): 91–98. https://doi.org/10.3141/2019-12.
Kamla, J., T. Parry, and A. Dawson. 2019. “Analysing truck harsh braking incidents to study roundabout accident risk.” Accid. Anal. Prev. 122 (Mar): 365–377. https://doi.org/10.1016/j.aap.2018.04.031.
Kinderytė-Poškienė, J., and E. Sokolovskij. 2008. “Traffic control elements influence on accidents, mobility and the environment.” Transport 23 (1): 55–58. https://doi.org/10.3846/1648-4142.2008.23.55-58.
Kweon, Y.-J. 2011. “Development of crash prediction models with individual vehicular data.” Transp. Res. Part C Emerging Technol. 19 (6): 1353–1363. https://doi.org/10.1016/j.trc.2011.03.002.
Lyu, P., Y. Lin, L. Wang, and X. Yang. 2017. “Variable speed limit control for delay and crash reductions at freeway work zone area.” J. Transp. Eng. Part A. Syst. 143 (12): 04017062. https://doi.org/10.1061/JTEPBS.0000099.
Madhiarasan, M., and S. Deepa. 2017. “Comparative analysis on hidden neurons estimation in multi layer perceptron neural networks for wind speed forecasting.” Artif. Intell. Rev. 48 (4): 449–471. https://doi.org/10.1007/s10462-016-9506-6.
Malyshkina, N. V., and F. Mannering. 2008. “Effect of increases in speed limits on severities of injuries in accidents.” Transp. Res. Rec. 2083 (1): 122–127. https://doi.org/10.3141/2083-14.
Meng, Q., and J. Weng. 2011. “A genetic algorithm approach to assessing work zone casualty risk.” Saf. Sci. 49 (8–9): 1283–1288. https://doi.org/10.1016/j.ssci.2011.05.001.
Meng, Q., J. Weng, and X. Qu. 2010. “A probabilistic quantitative risk assessment model for the long-term work zone crashes.” Accid. Anal. Prev. 42 (6): 1866–1877. https://doi.org/10.1016/j.aap.2010.05.007.
Milton, J., and F. Mannering. 1998. “The relationship among highway geometrics, traffic-related elements and motor-vehicle accident frequencies.” Transportation 25 (4): 395–413. https://doi.org/10.1023/A:1005095725001.
Mishra, S., M. M. Golias, S. Sharma, and S. D. Boyles. 2015. “Optimal funding allocation strategies for safety improvements on urban intersections.” Transp. Res. Part A Policy Pract. 75 (May): 113–133. https://doi.org/10.1016/j.tra.2015.03.001.
Mishra, S., S. Sharma, S. Khasnabis, and T. V. Mathew. 2013. “Preserving an aging transit fleet: An optimal resource allocation perspective based on service life and constrained budget.” Transp. Res. Part A Policy Pract. 47 (Jan): 111–123. https://doi.org/10.1016/j.tra.2012.10.029.
Mokhtarimousavi, S., J. C. Anderson, A. Azizinamini, and M. Hadi. 2019. “Improved support vector machine models for work zone crash injury severity prediction and analysis.” Transp. Res. Rec. 2673 (11): 680–692. https://doi.org/10.1177/0361198119845899.
Mokhtarimousavi, S., A. Azizinamini, and M. Hadi. 2020. “Severity of worker-involved work zone crashes: A study of contributing factors.” In Proc., Int. Conf. on Transportation and Development 2020. Reston, VA: ASCE.
Mrowicki, A., M. Krukowski, F. Turoboś, and P. Kubiak. 2020. “Determining vehicle pre-crash speed in frontal barrier crashes using artificial neural network for intermediate car class.” Forensic Sci. Int. 308 (Mar): 110179. https://doi.org/10.1016/j.forsciint.2020.110179.
National Work Zone Safety. 2021. “National estimates of total and injury work zone crashes.” Accessed November 30, 2021. https://workzonesafety.org/work-zone-data/work-zone-traffic-crash-trends-and-statistics/.
Nelles, O. 2020. Nonlinear system identification: From classical approaches to neural networks, fuzzy models, and Gaussian processes. New York: Springer.
NHTSA (National Highway Traffic Safety Administration). 2005. NHTSA’s national center for statistics and analysis. Washington, DC: NHTSA.
Olden, J. D., M. K. Joy, and R. G. Death. 2004. “An accurate comparison of methods for quantifying variable importance in artificial neural networks using simulated data.” Ecol. Modell. 178 (3–4): 389–397. https://doi.org/10.1016/j.ecolmodel.2004.03.013.
Orme, J. G., and T. Combs-Orme. 2009. Multiple regression with discrete dependent variables. Oxford, UK: Oxford University Press.
Osman, M., R. Paleti, and S. Mishra. 2018. “Analysis of passenger-car crash injury severity in different work zone configurations.” Accid. Anal. Prev. 111 (Feb): 161–172. https://doi.org/10.1016/j.aap.2017.11.026.
Osman, M., R. Paleti, S. Mishra, and M. M. Golias. 2016. “Analysis of injury severity of large truck crashes in work zones.” Accid. Anal. Prev. 97 (Dec): 261–273. https://doi.org/10.1016/j.aap.2016.10.020.
Ozturk, O., K. Ozbay, H. Yang, and B. Bartin. 2013. “Crash frequency modeling for highway construction zones.” In Proc., Transportation Research Board 92nd Annual Meeting. Washington, DC: Transportation Research Board.
Poch, M., and F. Mannering. 1996. “Negative binomial analysis of intersection-accident frequencies.” J. Transp. Eng. 122 (2): 105–113. https://doi.org/10.1061/(ASCE)0733-947X(1996)122:2(105).
Pradhan, B., and M. I. Sameen. 2020. “Review of traffic accident predictions with neural networks.” In Laser scanning systems in highway and safety assessment, 97–109. New York: Springer.
Qi, Y., R. Srinivasan, H. Teng, and R. Baker. 2013. “Analysis of the frequency and severity of rear-end crashes in work zones.” Traffic Inj. Prev. 14 (1): 61–72. https://doi.org/10.1080/15389588.2012.675109.
Qu, X., Y. Yang, Z. Liu, S. Jin, and J. Weng. 2014. “Potential crash risks of expressway on-ramps and off-ramps: A case study in Beijing, China.” Saf. Sci. 70 (Dec): 58–62. https://doi.org/10.1016/j.ssci.2014.04.016.
Santos, B., V. Trindade, C. Polónia, and L. Picado-Santos. 2021. “Detecting risk factors of road work zone crashes from the information provided in police crash reports: The case study of Portugal.” Safety 7 (1): 12. https://doi.org/10.3390/safety7010012.
Shaghaghi, S., H. Bonakdari, A. Gholami, I. Ebtehaj, and M. Zeinolabedini. 2017. “Comparative analysis of GMDH neural network based on genetic algorithm and particle swarm optimization in stable channel design.” Appl. Math. Comput. 313 (Nov): 271–286. https://doi.org/10.1016/j.amc.2017.06.012.
Shankar, V., F. Mannering, and W. Barfield. 1995. “Effect of roadway geometrics and environmental factors on rural freeway accident frequencies.” Accid. Anal. Prev. 27 (3): 371–389. https://doi.org/10.1016/0001-4575(94)00078-Z.
Singh, G., M. Pal, Y. Yadav, and T. Singla. 2020. “Deep neural network-based predictive modeling of road accidents.” Neural Comput. Appl. 32 (Jan): 12417–12426. https://doi.org/10.1007/s00521-019-04695-8.
Sultana, Z., S. Mishra, C. R. Cherry, M. M. Golias, and S. T. Jeffers. 2018. “Modeling frequency of rural demand response transit trips.” Transp. Res. Part A Policy Pract. 118 (Apr): 494–505. https://doi.org/10.1016/j.tra.2018.10.006.
Sze, N. N., and Z. Song. 2019. “Factors contributing to injury severity in work zone related crashes in New Zealand.” Int. J. Sustainable Transp. 13 (2): 148–154. https://doi.org/10.1080/15568318.2018.1452083.
Theofilatos, A., A. Ziakopoulos, E. Papadimitriou, G. Yannis, and K. Diamandouros. 2017. “Meta-analysis of the effect of road work zones on crash occurrence.” Accid. Anal. Prev. 108 (Apr): 1–8. https://doi.org/10.1016/j.aap.2017.07.024.
Wang, J., Y. Kong, and T. Fu. 2019. “Expressway crash risk prediction using back propagation neural network: A brief investigation on safety resilience.” Accid. Anal. Prev. 124 (Mar): 180–192. https://doi.org/10.1016/j.aap.2019.01.007.
Wegman, F. 2014. “Analyzing road design risk factors for run-off-road crashes in the Netherlands with crash prediction models.” J. Saf. Res. 49 (Jun): 121.e1–127. https://doi.org/10.1016/j.jsr.2014.03.003.
Wei, X., X. Shu, B. Huang, E. L. Taylor, and H. Chen. 2017. “Analyzing traffic crash severity in work zones under different light conditions.” J. Adv. Transp. 2017 (Jan): 1–10. https://doi.org/10.1155/2017/5783696.
Xiaodong, D., C. Wang, X. Liu, and N. Wang. 2005. “A hybrid algorithm based on particle swarm optimization.” Int. J. Inf. Syst. Sci. 1 (3–4): 275–282.
Yang, H., K. Ozbay, O. Ozturk, and M. Yildirimoglu. 2013. “Modeling work zone crash frequency by quantifying measurement errors in work zone length.” Accid. Anal. Prev. 55 (Jun): 192–201. https://doi.org/10.1016/j.aap.2013.02.031.
Yu, M., C. Zheng, and C. Ma. 2020. “Analysis of injury severity of rear-end crashes in work zones: A random parameters approach with heterogeneity in means and variances.” Anal. Methods Accid. Res. 27 (Sep): 100126. https://doi.org/10.1016/j.amar.2020.100126.
Zeng, Q., H. Huang, X. Pei, and S. Wong. 2016. “Modeling nonlinear relationship between crash frequency by severity and contributing factors by neural networks.” Anal. Methods Accid. Res. 10 (Jun): 12–25. https://doi.org/10.1016/j.amar.2016.03.002.
Zhang, H., S. Li, C. Wu, Q. Zhang, and Y. Wang. 2020. “Predicting crash frequency for urban expressway considering collision types using real-time traffic data.” J. Adv. Transp. 2020 (Mar): 1–8. https://doi.org/10.1155/2020/8523818.
Zhang, K., and M. Hassan. 2019. “Identifying the factors contributing to injury severity in work zone rear-end crashes.” J. Adv. Transp. 2019 (May): 1–9. https://doi.org/10.1155/2019/4126102.
Zhang, K., M. Hassan, M. Yahaya, and S. Yang. 2018. “Analysis of work-zone crashes using the ordered Probit model with factor analysis in Egypt.” Accid. Anal. Prev. 2018 (Oct): 1–10. https://doi.org/10.1155/2018/8570207.
Zhang, Z., B. Akinci, and S. Qian. 2022. “Inferring heterogeneous treatment effects of work zones on crashes.” Accid. Anal. Prev. 177 (Nov): 106811. https://doi.org/10.1016/j.aap.2022.106811.
Zou, Y., and A. P. Tarko. 2018. “Barrier-relevant crash modification factors and average costs of crashes on arterial roads in Indiana.” Accid. Anal. Prev. 111 (Feb): 71–85. https://doi.org/10.1016/j.aap.2017.11.020.
Information & Authors
Information
Published In
Journal of Transportation Engineering, Part A: Systems
Volume 150 • Issue 2 • February 2024
Copyright
© 2023 American Society of Civil Engineers.
History
Received: Oct 5, 2022
Accepted: Sep 19, 2023
Published online: Nov 25, 2023
Published in print: Feb 1, 2024
Discussion open until: Apr 25, 2024
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.
Cited by
- Nenad Marković, Tijana Ivanišević, Svetlana Čičević, Aleksandar Trifunović, Fuzzy Logic Model for Assessing Accident Proneness Based on Passenger Vehicle Speed in Real and Virtual Traffic Conditions, Mathematics, 10.3390/math12030421, 12, 3, (421), (2024).
- Diwas Thapa, Sabyasachee Mishra, Asad Khattak, Muhammad Adeel, Assessing driver behavior in work zones: A discretized duration approach to predict speeding, Accident Analysis & Prevention, 10.1016/j.aap.2023.107427, 196, (107427), (2024).