Journal of Transportation Research

Journal of Transportation Research

Comparison of Machine Learning Algorithms in Feature Selection and Classification of Pedestrian Accidents Severity (Case Study: Qom City)

Document Type : Original Article

Authors
Sadegh Moslemi mehni 1
Ali Naderan 2
Seyed Saber Naseralavi 3
1 Ph.D., Candidate, Department of Civil Engineering, SR.C., Islamic Azad University, Tehran, Iran.
2 Assistant Professor, Department of Civil Engineering, SR.C., Islamic Azad University, Tehran, Iran.
3 Assistant Professor, Civil Engineering Department, Shahid Bahonar University of Kerman, Kerman, Iran.
10.22034/tri.2024.443127.3227
Abstract
This article investigates the performance of machine learning algorithms in classifying the severity of pedestrian accidents, taking into account various factors such as weather conditions, environment, time periods, and accident types. Initially, feature combinations were optimized using real-world data from Qom City to improve classification accuracy. The algorithms were trained on 70% of the data and tested on the remaining 30% to evaluate their effectiveness. The performance of three popular classification algorithms, including k-Nearest Neighbor, Decision Tree, and Random Forest, was compared using all features and subsets of features. The results revealed that the Decision Tree algorithm with all features achieved the highest performance in classifying the severity of pedestrian accidents. Future studies should examine the impact of various factors, such as traffic conditions and road features, along with weather conditions, on pedestrian accidents to enhance the performance of classification algorithms in this area. The research results enable the traffic department to formulate pertinent accident control measures and promote the traffic safety on urban roads
Keywords
Feature Selection
Classification
Confusion Matrix
Machine Learning
Subjects
-Ali, N. M., Farouk, A. I. B., Haruna, S. I., Alanazi, H., Adamu, M., & Ibrahim, Y. E. (2022). Feature selection approach for failure mode detection of reinforced concrete bridge columns. Case Studies in Construction Materials, 17, e01383.
-AlMamlook, R. E., Kwayu, K. M., Alkasisbeh, M. R., & Frefer, A. A. (2019). Comparison of machine learning algorithms for predicting traffic accident severity.
-Chotchantarakun, K., & Sornil, O. (2021). An Adaptive Multilevels Sequential Feature Selection. International Journal of Computer Information Systems and Industrial Management Applications, 13, 010-019.  
-Danaei Mehr, H., & Polat, H. (2022). Diagnosis of polycystic ovary syndrome through different machine learning and feature selection techniques. Health and Technology, 12(1), 137-150.
-Fiorentini, N., & Losa, M. (2020). Handling imbalanced data in road crash severity prediction by machine learning algorithms. Infrastructures, 5(7), 61.
-Got, A., Moussaoui, A., & Zouache, D. (2021). Hybrid filter-wrapper feature selection using whale optimization algorithm.
A multi-objective approach. Expert Systems with Applications, 183, 115312.
-Komol, M. M. R., Hasan, M. M., Elhenawy, M., Yasmin, S., Masoud, M., & Rakotonirainy, A. (2021). Crash severity analysis of vulnerable road users using machine learning. PLoS one, 16(8), e0255828.
-Kunhare, N., Tiwari, R., & Dhar, J. (2020). Particle swarm optimization and feature selection for intrusion detection system. Sādhanā, 45, 1-14.
-Liu, X., Tang, J., Gao, F., & Ding, X. (2023). Time and Distance Gaps of Primary-Secondary Crashes Prediction and Analysis Using Random Forests and SHAP Model. Journal of Advanced Transportation.
-Nguyen, C., Wang, Y., & Nguyen, H. N. (2013). Random forest classifier combined with feature selection for breast cancer diagnosis and prognostic.
-Niyogisubizo, J., Liao, L., Sun, Q., Nziyumva, E., Wang, Y., Luo, L., . . . Murwanashyaka, E. (2023). Predicting Crash Injury Severity in Smart Cities: a Novel Computational Approach with Wide and Deep Learning Model. International Journal of Intelligent Transportation Systems Research, 21(1), 240-258.
-Shiran, G., Imaninasab, R., & Khayamim, R. (2021). Crash severity analysis of highways based on multinomial logistic regression model, decision tree techniques, and artificial neural network: a Modeling comparison. Sustainability, 13(10), 5670.
-Singh, S., & Haider, T. U. (2022, 2022). Selection of best feature reduction method for module-based software defect prediction.
-Tsai, C.-F., & Chen, Y.-C. (2019). The optimal combination of feature selection and data discretization: An empirical study. Information Sciences, 505, 282-293.
-Vandana, C. P., & Chikkamannur, A. A. (2021). Feature selection: An empirical study. International Journal of Engineering Trends and Technology, 69(2), 165-170.
-Yang, H., Huang, S., Guo, S., & Sun, G. (2022). Multi-Classifier Fusion Based on MI–SFFS for Cross-Subject Emotion Recognition. Entropy, 24(5), 705.
-Zhou, H., Zhang, J., Zhou, Y., Guo, X., & Ma, Y. (2021). A feature selection algorithm of decision tree based on feature weight. Expert Systems with Applications, 164, 113842.