Journal of Transportation Research

Journal of Transportation Research

An integrated data mining model for analyzing the pedestrian crash patterns in Iran

Document Type : Original Article

Authors
Ali Tavakoli Kashani 1
Mohammad Mehdi Besharati 2
1 Associate Professor, School of Civil Engineering, Iran University of Science and Technology, Tehran, Iran and Road Safety Research Center, Iran University of Science and Technology, Tehran, Iran.
2 Assistant Professor, Department of Transportation Engineering, Isfahan University of Technology, Isfahan, Iran.
10.22034/tri.2024.470638.3265
Abstract
Pedestrians as one of the main groups of vulnerable road users account for a significant share of traffic crash fatalities. The purpose of this study is to investigate the pedestrian crash patterns and identify the set of factors that contribute to increase the fatality risk of pedestrians. To this end, pedestrian crash data in Iran during 2016 to 2022 was analyzed in a combined data mining framework. In the first step, crash data was divided into homogeneous groups using the clustering method. Then, the association rules discovery method was applied to identify the set of factors that contribute to increase the fatality risk of pedestrians as well as the probability of the pedestrians being at-fault in the crash. Results indicated that the interaction effects of factors such as darkness, pedestrian wearing dark clothes, being male and above 65-years old, crash being occurred on rural freeways and highways, collision with heavy vehicles, and crossing the road in unpermitted locations contribute to increase the fatality risk of pedestrians. Therefore, obstruction of the crossing passage of pedestrians and providing overpass/underpass might have a significant effect on reducing pedestrian fatal crashes. Moreover, providing illuminated crossings and encouraging the pedestrians to use these crossing might reduce the risk of occurrence and severity of such crashes.
Keywords
Fatal Crashes
Pedestrian
Clustering
Association Rules
Subjects
-کی منش، محمود رضا و ذبیحیان، رسول (1402). ارزیابی عوامل موثر بر تصادفات عابرین پیاده در خیابان­­­های شهری و ارائه مدلی برای پیش بینی این تصادفات (مطالعه موردی شهر زنجان). پژوهشنامه حمل و نقل، 20(3)، 190-171. doi.org/10.22034/tri.2022.286782.2913
-مسلمی مهنی، صادق، نادران، علی و ناصر علوی، سید صابر (1403). مقایسه الگوریتم‌های یادگیری ماشین در انتخاب ویژگی و طبقه‌بندی شدت تصادفات عابر پیاده (مطالعه موردی: شهر قم). پژوهشنامه حمل و نقل.  (پذیرفته شده برای چاپ). doi.org/10.22034/tri.2024.443127.3227
-ندیمی، نوید، ناصرعلوی، سید صابر، خلیفه، وحید و امینیان، مهدی (1403). تحلیل و ارزیابی عوامل موثر بر تصادفات کاربران آسیب‎پذیر در معابر شهری با استفاده از استخراج قواعد انجمنی. پژوهشنامه حمل و نقل، 22(1)، 82-65.  doi.org/10.22034/tri.2024.430837.3216
-Alikhani, M., Nedaie, A., and Ahmadvand, A. (2013). Presentation of clustering-classification heuristic method for improvement accuracy in classification of severity of road accidents in Iran. Safety science, 60, 142-150.
-Ankunda, A., Ali, Y., and Mohanty, M. (2024). Pedestrian crash risk analysis using extreme value models: new insights and evidence. Accident Analysis and Prevention, 203, 107633.
-Aziz, H., Ukkusuri, S. V., and Hasan, S. (2013). Exploring the determinants of pedestrian–vehicle crash severity in New York City. Accident Analysis and Prevention, 50, 1298-1309.
-Dai, D. (2012). Identifying clusters and risk factors of injuries in pedestrian–vehicle crashes in a GIS environment. Journal of transport geography, 24, 206-214.
-de Oña, J., López, G., Mujalli, R., and Calvo, F. J. (2013). Analysis of traffic accidents on rural highways using Latent Class Clustering and Bayesian Networks. Accident Analysis and Prevention, 51, 1-10.
-Depaire, B., Wets, G., and Vanhoof, K. (2008). Traffic accident segmentation by means of latent class clustering. Accident Analysis and Prevention, 40(4), 1257-1266.
-Hossain, M. M., Zhou, H., Sun, X., Hossain, A., and Das, S. (2024). Crashes involving distracted pedestrians: Identifying risk factors and their relationships to pedestrian severity levels and distraction modes. Accident Analysis and Prevention, 194, 107359.
-Iranitalab, A., and Khattak, A. (2017). Comparison of four statistical and machine learning methods for crash severity prediction. Accident Analysis and Prevention, 108, 27-36.
-Kaufman, L., and Rousseeuw, P. J. (2009). Finding Groups in Data: an Introduction to cluster Analysis. John Wiley and Sons.
-Kim, J.-K., Ulfarsson, G. F., Shankar, V. N., and Kim, S. (2008). Age and pedestrian injury severity in motor-vehicle crashes: A heteroskedastic logit analysis. Accident Analysis and Prevention, 40(5), 1695-1702.
-Kim, J.-K., Ulfarsson, G. F., Shankar, V. N., and Mannering, F. L. (2010). A note on modeling pedestrian-injury severity in
motor-vehicle crashes with the mixed logit model. Accident Analysis and Prevention, 42(6), 1751-1758.
-Kim, S. H. (2023). How heterogeneity has been examined in transportation safety analysis: A review of latent class modeling applications. Analytic methods in accident research, 100292.
-Lee, C., and Abdel-Aty, M. (2005). Comprehensive analysis of vehicle–pedestrian crashes at intersections in Florida. Accident Analysis and Prevention, 37(4), 775-786.
-Ma, Z., Mei, G., and Cuomo, S. (2021). An analytic framework using deep learning for prediction of traffic accident injury severity based on contributing factors. Accident Analysis and Prevention, 160, 106322.
-Mohamed, M. G., Saunier, N., Miranda-Moreno, L. F., and Ukkusuri, S. V. (2013). A clustering regression approach: A comprehensive injury severity analysis of pedestrian–vehicle crashes in New York, US and Montreal, Canada. Safety science, 54, 27-37.
-Montella, A., Aria, M., D’Ambrosio, A., and Mauriello, F. (2012). Analysis of powered two-wheeler crashes in Italy by classification trees and rules discovery. Accident Analysis and Prevention, 49, 58-72.
-Moudon, A. V., Lin, L., Jiao, J., Hurvitz, P., and Reeves, P. (2011). The risk of pedestrian injury and fatality in collisions with motor vehicles, a social ecological study of state routes and city streets in King County, Washington. Accident Analysis and Prevention, 43(1), 11-24.
-Raihan, M. A., Hossain, M., and Hasan, T. (2018). Data mining in road crash analysis: the context of developing countries. International Journal of Injury Control and Safety Promotion, 25(1), 41-45.
-Salehian, A., Aghabayk, K., Seyfi, M., and Shiwakoti, N. (2023). Comparative analysis of pedestrian crash severity at United Kingdom rural road intersections and Non-Intersections using latent class clustering and ordered probit model. Accident Analysis and Prevention, 192, 107231.
-Santos, K., Dias, J. P., and Amado, C. (2022). A literature review of machine learning algorithms for crash injury severity prediction. Journal of safety research, 80, 254-269.
-Zajac, S. S., and Ivan, J. N. (2003). Factors influencing injury severity of motor vehicle–crossing pedestrian crashes in rural Connecticut. Accident Analysis and Prevention, 35(3), 369-379.