Predicting injury severity in vehicle-to-pedestrian collisions: evidence from Madhya Pradesh state, India
DOI:
https://doi.org/10.55329/xnew4225Keywords:
collision, Latent Class Analysis, Random Forest, vehicle-pedestrianAbstract
The present research examines characteristics of vehicle-to-pedestrian collisions and assesses the factors affecting such crashes in Madhya Pradesh using accident record data from Madhya Pradesh Road Development Corporation and Accident Response System, encompassing 6104 accident entries across 16 variables. To address data heterogeneity, Latent Class Clustering was employed, and a Random Forest Algorithm was used for predictive modelling to accurately classify injury severity based on various predictors. The latent clustering identified three distinct classes: Class 1 (27.7%) associated with fewer severe injuries, attributed to effective traffic controls; Class 2 (8.7%), characterized by reduced injury rates, linked to well-organized traffic systems; and Class 3 (63.5%), which showed a higher incidence of severe injuries, primarily due to narrow, poorly designed, or infrastructure-deficient roads and excessive speeding. The Random Forest Classifier effectively used predictors such as age, gender, violation type, traffic control, and vehicle type, achieving 97.2% precision and 89.2% recall, and an overall accuracy of 88.8%. The Decision Tree model further highlighted the relative importance of each variable in predicting injury severity. The model’s performance was benchmarked against baseline classifiers including logistic regression, Support Vector Machine, and Decision Tree, confirming the superior accuracy and robustness of the Random Forest approach. This study emphasizes the need for proactive road safety measures and provides a robust analytical framework for injury severity classification, supporting the development of targeted interventions to improve pedestrian safety in India.
Downloads
Author Biographies
Chinmay Gayan, Maulana Azad National Institute of Technology, India
Mr. Chinmay Gayan completed his Master's Degree from Maulana Azad National Institute of Technology (MANIT), Bhopal, Madhya Pradesh, India. His research interests lie at the intersection of traffic safety and urban planning, with a focus on developing strategies to improve road safety in urban environments.
CRediT contribution: Conceptualization, Funding acquisition, Methodology, Writing—original draft, Writing—review & editing.
Bivina G. R., Maulana Azad National Institute of Technology, India
Dr. Bivina G. R. is an Assistant Professor in the Department of Civil Engineering at Maulana Azad National Institute of Technology (MANIT), Bhopal, Madhya Pradesh, India. She specializes in pedestrian safety, human factors in transportation, and transportation planning. Her research focuses on understanding pedestrian behavior, safety perceptions, and designing data-driven strategies to improve urban mobility. Dr. Bivina has contributed significantly to the field through her publications in reputed journals and active participation in international conferences. She is also involved in mentoring postgraduate students and coordinating research projects in transportation engineering. Her work aims to develop sustainable and inclusive transportation systems that prioritize safety and efficiency.
CRediT contribution: Methodology, Supervision, Validation, Writing—review & editing.
Yogeshwar V. Navandar, National Institute of Technology Calicut, India
Dr. Yogeshwar V. Navandar currently working as Assistant Professor in Department of Civil Engineering at the National Institute of Technology Calicut, India. He worked on “Traffic flow operational analysis at manually operated toll plazas under mixed traffic conditions in India” for his PhD. The thesis is relevant in terms of qualitative and quantitative evaluation for the user’s perception and traffic flow operational characteristics respectively. The concept of Tollbooth Equivalency Factor (TEF) has been proposed by him which is one of the novel approaches to convert mixed traffic into equivalent flow at toll plaza instead of PCU. He has developed a road user’s perceived Level of Service model using Structural Equation Modelling (SEM) and Ordered Probit Model (OPM). He has a good hands-on experience in data collection, data management, advanced modelling (such as SEM and OPM), and analytical capability. His area of research expertise includes traffic flow analysis, road safety, pedestrian safety, infrastructure management, inland waterways and users perceptions related studies.
CRediT contribution: Supervision, Validation, Writing—review & editing.
References
Bullard, C., Adanu, E. K., Liu, J., Agyemang, W., & Jones, S. (2024) Segmenting and investigating pedestrian-vehicle crashes in Ghana: A latent class clustering approach, African Transport Studies, 2, 100010 DOI: https://doi.org/10.1016/j.aftran.2024.100010
Chang, F., Xu, P., Zhou, H., Chan, A. H., & Huang, H. (2019) Investigating injury severities of motorcycle riders: A two-step method integrating latent class cluster analysis and random parameters logit model, Accident Analysis & Prevention, 131 316-326. DOI: https://doi.org/10.1016/j.aap.2019.07.012
Chen, Y., Luo, R., Yang, H., King, M., & Shi, Q. (2020) Applying latent class analysis to investigate rural highway single-vehicle fatal crashes in China, Accident Analysis & Prevention, 148, 105840 DOI: https://doi.org/10.1016/j.aap.2020.105840
Chen, Z., & Fan, W. (2019) Modeling pedestrian injury severity in pedestrian-vehicle crashes in rural and urban areas: mixed logit model approach, Transportation research record, 2673(4), 1023-1034. DOI: https://doi.org/10.1177/0361198119842825
Eluru, N., Bhat, C. R., & Hensher, D. A. (2008) A mixed generalized ordered response model for examining pedestrian and bicyclist injury severity level in traffic crashes, Accident Analysis & Prevention, 40(3), 1033-1054. DOI: https://doi.org/10.1016/j.aap.2007.11.010
Jamal, A., Zahid, M., Tauhidur Rahman, M., Al-Ahmadi, H. M., Almoshaogeh, M., Farooq, D., & Ahmad, M. (2021) Injury severity prediction of traffic crashes with ensemble machine learning techniques: A comparative study, International journal of injury control and safety promotion, 28(4), 408-427. DOI: https://doi.org/10.1080/17457300.2021.1928233
Li, Y., & Fan, W. D. (2019) Modelling severity of pedestrian-injury in pedestrian-vehicle crashes with latent class clustering and partial proportional odds model: A case study of North Carolina, Accident Analysis & Prevention, 131, 284-296. DOI: https://doi.org/10.1016/j.aap.2019.07.008
Lin, Z., & Fan, W. D. (2021) Exploring bicyclist injury severity in bicycle-vehicle crashes using latent class clustering analysis and partial proportional odds models, Journal of safety research, 76, 101-117. DOI: https://doi.org/10.1016/j.jsr.2020.11.012
Ministry of Road Transport and Highways (2020) , MoRTH Report, 2020,
Muslim, H., & Antona-Makoshi, J. (2022) A review of vehicle-to-vulnerable road user collisions on limited-access highways to support the development of automated vehicle safety assessments, Safety, 8(2), 26 DOI: https://doi.org/10.3390/safety8020026
Rankavat, S., & Tiwari, G. (2015) Association between built environment and pedestrian fatal crash risk in Delhi, India, Transportation Research Record, 2519(1), 61-66. DOI: https://doi.org/10.3141/2519-07
Rifat, M. A. K., Kabir, A., & Huq, A. (2024) An Explainable Machine Learning Approach to Traffic Accident Fatality Prediction, Procedia Computer Science, 246 1905-1914. DOI: https://doi.org/10.1016/j.procs.2024.09.704
Salehian, A., Aghabayk, K., Seyfi, M., & 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 & Prevention, 192 107231 DOI: https://doi.org/10.1016/j.aap.2023.107231
Samerei, S. A., & Aghabayk, K. (2024) Analyzing the transition from two-vehicle collisions to chain reaction crashes: A hybrid approach using random parameters logit model, interpretable machine learning, and clustering, Accident Analysis & Prevention, 202 107603 DOI: https://doi.org/10.1016/j.aap.2024.107603
Sasidharan, L., Wu, K. F., & Menendez, M. (2015) Exploring the application of latent class cluster analysis for investigating pedestrian crash injury severities in Switzerland, Accident Analysis & Prevention, 85, 219-228. DOI: https://doi.org/10.1016/j.aap.2015.09.020
Sivasankaran, S. K., & Balasubramanian, V. (2020) Exploring the severity of bicycle–vehicle crashes using latent class clustering approach in India, Journal of safety research, 72, 127-138. DOI: https://doi.org/10.1016/j.jsr.2019.12.012
Sun, M., Sun, X., & Shan, D. (2019) Pedestrian crash analysis with latent class clustering method, Accident Analysis & Prevention, 124 50-57. DOI: https://doi.org/10.1016/j.aap.2018.12.016
Tom, A., & Granié, M. A. (2011) Gender differences in pedestrian rule compliance and visual search at signalized and unsignalized crossroads, Accident Analysis & Prevention, 43(5), 1794-1801. DOI: https://doi.org/10.1016/j.aap.2011.04.012
WHO (2023) Global Status Report on Road Safety, World Health Organization,
Yao, S., Wang, J., Fang, L., & Wu, J. (2018) Identification of vehicle-pedestrian collision hotspots at the micro-level using network kernel density estimation and random forests: A case study in Shanghai, China, Sustainability, 10(12), 4762 DOI: https://doi.org/10.3390/su10124762
Zhu, C., Brown, C. T., Dadashova, B., Ye, X., Sohrabi, S., & Potts, I. (2023) Investigation on the driver-victim pairs in pedestrian and bicyclist crashes by latent class clustering and random forest algorithm, Accident Analysis & Prevention, 182, 106964 DOI: https://doi.org/10.1016/j.aap.2023.106964
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Chinmay Gayan, Bivina G. R., Yogeshwar V. Navandar
This work is licensed under a Creative Commons Attribution 4.0 International License.
