Predicting Injury Severity of Angle Crashes Involving Two Vehicles at Unsignalized Intersections Using Artificial Neural Networks
In 2015, about 20% of the 52,231 fatal crashes that occurred in the United States occurred at unsignalized intersections. The economic cost of these fatalities have been estimated to be in the millions of dollars. In order to mitigate the occurrence of theses crashes, it is necessary to investigate their predictability based on the pertinent factors and circumstances that might have contributed to their occurrence. This study focuses on the development of models to predict injury severity of angle crashes at unsignalized intersections using artificial neural networks (ANNs). The models were developed based on 3,307 crashes that occurred from 2008 to 2015. Twenty-five different ANN models were developed. The most accurate model predicted the severity of an injury sustained in a crash with an accuracy of 85.62%. This model has 3 hidden layers with 5, 10, and 5 neurons, respectively. The activation functions in the hidden and output layers are the rectilinear unit function and sigmoid function, respectively.
Keywords:crashes, unsignalized intersection, artificial neural network, injury severity
T. R. Neuman, R. Pfefer, K. L. Slack, K. K. Hardy, D. W. Harwood, I. B. Potts, D. J. Torbic, E. R. K. Rabbani, National Cooperative Highway Research Program: Guidance for Implementation of the AASHTO Strategic Highway Safety Plan, Transportation Research Board, 2003
World Health Organization, Global Status Report on Toad Safety 2015, WHO, 2015
National Highway Traffic Safety Administration, “USDOT Releases 2016 Fatal Traffic Crash Data”, available at: https://www.nhtsa.gov/
National Highway Traffic Safety Administration, Traffic Safety Facts 2015, US Department of Transportation-National Highway Traffic Safety Administration, 2015
B. J. Russo, P. T. Savolainen, W. H. Schneider, P. C. Anastasopoulos, “Comparison of factors affecting injury severity in angle collisions by fault status using a random parameter bivariate ordered probit model”, Analytic Methods in Accident Research, Vol. 2, pp. 21-29, 2014 DOI: https://doi.org/10.1016/j.amar.2014.03.001
R. Garrido, A. Bastos, A. de Almeida, J. P. Elvas, “Prediction of Road Accident Severity Using the Ordered Probit Model”, Transport Research. Procedia, Vol. 3, pp. 214-223, 2014 DOI: https://doi.org/10.1016/j.trpro.2014.10.107
T. Sayed, F. Rodriguez, “Accident Prediction Models for Urban Unsignalized Intersections in British Columbia”, Transportation Research Record Journal of the Transportation Research Board, Vol. 1665, No. 1, pp. 93-99, 1999 DOI: https://doi.org/10.3141/1665-13
W. Ackaah, M. Salifu, “Crash prediction model for two-lane rural highways in the Ashanti region of Ghana”, International Association of Traffic and Safety Sciences Research, Vol. 35, No. 1, pp. 34-40, 2011 DOI: https://doi.org/10.1016/j.iatssr.2011.02.001
M. Y. Lau, A. D. May, Accident Prediction Model Development: Signalized Intersections, Institute of Transportation Studies, University of California-Berkeley, 1988
A. Kamer-Ainur, M. Marioara, “Errors And Limitations Associated With Regression And Correlation Analysis”, Statistics and Economic Informatics, pp. 710-712, 2007
P. Chengye, P. Ranjitkar, “Modelling Motorway Accidents using Negative Binomial Regression”, Journal of the Eastern Asia Society for Transportation Studies, Vol. 10, pp. 1946-1963, 2013
Z. Yang, L. Zhibin, L. Pan, Z. Liteng, “Exploring contributing factors to crash injury severity at freeway diverge areas using ordered probit model”, Procedia Engineering, Vol. 21, pp. 178-185, 2011 DOI: https://doi.org/10.1016/j.proeng.2011.11.2002
Federal Highway Administration, “Highway Safety Improvement Program Manual–Safety”, available at: https://safety.fhwa.dot.gov/
G. Dutta, P. Jha, A. K. Laha, N. Mohan, “Artificial Neural Network Models for Forecasting Stock Price Index in the Bombay Stock Exchange”, Journal of Emerging Market Finance, Vol. 5, No. 3, pp. 283-295, 2006 DOI: https://doi.org/10.1177/097265270600500305
M. H. Hassoun, Fundamentals of Artificial Neural Networks, MIT Press, 1995
S. Sharma, “Activation Functions in Neural Networks”, available at: https://towardsdatascience.com/activation-functions-neural-networks-1cbd9f8d91d6, 2017
F. R. Moghaddam, S. Afandizadeh, M. Ziyadi, “Prediction of accident severity using artificial neural networks”, International Journal of Civil Engineering, Vol. 9, No. 1, pp. 41-49, 2011
K. S. Jadaan, M. Al-Fayyad, H. F. Gammoh, “Prediction of Road Traffic Accidents in Jordan using Artificial Neural Network (ANN)”, Journal of Traffic Logistics Engineering, Vol. 2, No. 2, pp. 92-94, 2014 DOI: https://doi.org/10.12720/jtle.2.2.92-94
Office of the State Superintendent of Education, “New U.S. Census Bureau Numbers Officially Put DC’s Population Over 700,000”, available at: https://osse.dc.gov/release/new-us-census-bureau-numbers-officially-put-dc%E2%80%99s-population-over-700000, 2018
T. Winship, “The 10 US cities with the worst traffic”, available at: https://www.businessinsider.com/the-10-us-cities-with-the-worst-traffic-2018-2, 2018
District Department of Transportation, “DDOT by the Numbers”, available at: https://ddot.dc.gov/page/ddot-numbers
American Society of Civil Engineers, Repord Card for D.C.’s Infrastructure, ASCE, 2016
How to Cite
MetricsAbstract Views: 711
PDF Downloads: 508
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.