ENHANCING ROAD CRASH PREDICTION: A COMPARATIVE STUDY OF MACHINE LEARNING ALGORITHMS AND SAFETY PERFORMANCE FUNCTIONS ON THE LAGOS-IBADAN EXPRESSWAY

Opeyemi Bayode; Oluwatobi Aiyelokun; Oluwatoyin Osanyinlokun; Ariyo Adanikin

doi:10.4314/njt.v44i2.5

Authors

O. Bayode Department of Civil and Environmental Engineering, Bells University of Technology, Ota, Ogun State, Nigeria
O. Aiyelokun Department of Civil and Environmental Engineering, Bells University of Technology, Ota, Ogun State, Nigeria and Department of Civil Engineering, University of Ibadan, Oyo State, Nigeria
O. Osanyinlokun Department of Civil Engineering, Bamidele Olumilua University of Education, Science and Technology, Ikere-Ekiti, Ekiti State, Nigeria
A. Adanikin Harry Building Concept, Okota-Isolo, Lagos State, Nigeria

DOI:

https://doi.org/10.4314/njt.v44i2.5

Keywords:

Road Traffic Crash Prediction, Safety Performance Function, Machine Learning, SVM, RF, XGBoost

Abstract

Road traffic crash prediction (RTCP) is a critical aspect of transportation safety, enabling the identification of high-risk locations and informing the implementation of proactive measures. This study explores the comparative performance of Machine Learning (ML) algorithms and traditional Safety Performance Functions (SPFs) to predict road traffic crashes along the Lagos-Ibadan Expressway, a major highway in Nigeria known for its high crash rates. To achieve the objective, SPFs estimated using Negative Binomial Regression (NBR) and ML regression models mainly Support Vector Machine (SVM), Random Forest (RF) and Extreme Gradient Boosting (XGBoost) were developed using historical crash data collected from Federal Road Safety Commission (FRSC) of Nigeria for 10years duration between 2014 and 2023, traffic components and geometric design features as input variables. The study's findings indicate that ML algorithms outperform SPFs in terms of predictive accuracy and sensitivity to complex, non-linear relationships among crash-contributing factors with R² of 0.99, 097 and 0.84 for training and 0.93,0.9 and 0.76 for testing dataset in the three ML models. However, SPFs remain advantageous in interpretation and ease of implementation. The analysis also highlights the importance of feature selection, with variables such as traffic volume, traffic speed, road curvature and pavement width emerging as significant predictors. Furthermore, this study offers insights for policymakers, traffic engineers, and researchers seeking to improve road safety outcomes through data-driven crash prediction methods. The results emphasize the potential of integrating ML techniques with traditional methods to develop hybrid frameworks for enhanced crash prediction and prevention strategies on high-risk roadways.

References

[1] Popoola, M. O., Abiola, O. S. and Odunfa, S. O. "Effect of Traffic and Geometric Characteristics of Rural Two Lane Roads on Traffic Safety: a case study of Ilesha-Akure-Owo road, South-West, Nigeria," FUOYE Journal of Engineering and Technology, vol. 3, no. 2, pp. 125-130, 2018. doi.org/10.46792/ fuoyejet.v3i2.256.

[2] Bayode, O., Aderinola, O. S., Oluyemi-Ayibiowu, B. D., Okungade, O and Opeyemi, D. "Impact of Geometric Properties of Two Lane Highway on Traffic operation and Safety," UI Journal of Civil Engineering and Technology, vol. 6, no. 1, pp. 15-25, 2024.

[3] Li, X., Lord,D., Zhang, Y. and Xie, Y. "Predicting motor vehicle crashes using Support Vector Machine models.," Accident Analysis and Prevention, vol. 40, pp. 1611-1618, 2008. doi:10.1016/j.aap.2008.04.010

[4] Dong, N., Huang, H. and Zheng, I. "Support vector machine in crash prediction at the level of traffic analysis zones: Assessing the spatial proximity effects.," Accident Analysis and Prevention, vol. 82, pp. 192-198, 2015. doi.org/ 10.1016/j.aap.2015.05.018.

[5] Highway Safety Manual (HSM). American Association of State Highway and Transportation Officials, Washington, D.C., 2010.

[6] Lord, D. and Mannering, F. "The statistical analysis of crash-frequency data: A review and assessment of methodological alternatives.," Transportation research part A: policy and practice, vol. 44, no. 5, pp. 291-305, 2010.

[7] Tayebikhorami, S., and Sacchi, E. "Validation of Machine Learning Algorithms as Predictive Tool in the Road Safety Management Process: Case of Network Screening," Journal of Transportation Engineering: Part A, vol. 148, no. 9, pp. 1-30, 2022. doi/pdf/10.1061/JTEP BS.0000719.

[8] Chang, L. Y. "Analysis of freeway accident frequencies: Negative binomial 465 regression versus artificial neural network.," Safety Science, vol. 43, p. 541–557, 2005.

[9] Xie, Y., Lord, D., and Zhang, Y. "Predicting motor vehicle collisions using Bayesian neural network models: An empirical analysis.," Accident Analysis and Prevention, vol. 39, no. 2, pp. 922-933, 2007.

[10] Rezapour, M., Molan, A. M., and Ksaibati, K. "Analyzing Injury Severity of Motorcycle At-Fault Crashes Using Machine Learning Techniques, Decision Tree and Logistic Regression Models.," International Journal of Transportation Science and Technology, vol. 9, no. 2, pp. 89-99, 2020.

[11] Vitianingsih, A. V., Suryana, N., and Othman, Z. "Spatial Analysis Model for Traffic Accident-Prone Roads Classification: A Proposed Framework.," IAES International Journal of Artificial Intelligence, vol. 10, no. 2, pp. 365-370, 2021.

[12] Pan, C. and Prakash, R. "Modeling Motorway Accidents using Negative Binomial Regression," in Proceedings of the Eastern Asia Society for transportation Studies, 2013.

[13] Omari-Sasu, O., and Adejei, O. "Statistical Models for Count Data with Applications to Road Accidents in Ghana.," International Journal of Statistics and Applications, vol. 6, no. 3, pp. 123-137, 2016.

[14] Shaik, M. E., Islam, M. M., and Hossain, Q. S. "A review on neural network techniques for the prediction of road traffic accident severity," Asian Transport Studies, vol. 7, no. 10, p. 1000040, 2021.

[15] Singh, G., Sachdeva, S. N., and Pal, M. "Support vector machine model for prediction of accidents on non-urban sections of highways.," in Proceedings of the Institution of Civil Engineers Transport, 2018.

[16] Abdel-Aty, M., and Haleem, K. "Analysing angle crashes at unsignalised intersections using machine learning techniques," Accident Analysis and Prevention, vol. 43, no. 1, pp. 461-470, 2011.

[17] Yang, Y., Wang, K., Yuan, Z., and Liu, D. "Predicting Freeway Traffic Crash Severity Using XGBoost-Bayesian Network Model with Consideration of Features Interaction," Journal of Advanced Transportation, pp. 1-16, 2022. doi: 10.1155/2022/4257865.

[18] Aderinola, O. S., and Laoye, A. A "Traffic Crashes Prediction of States in Nigeria using time series Analysis," Global Journal of Engineering and Technology Advances, vol. 3, no. 1, pp. 15-26, 2020.

[19] Oyedepo, O. J., and Makinde, O. O. "Accident Prediction Models for Akure-Ondo Carriageway, Ondo State Southwest Nigeria: Using Multiple Linear Regression," African Research Review, vol. 4, no. 2, pp. 30-49, 2010.

[20] Aderinlewo, O. O., and Afolayan, A. "Development of Road Accident Prediction Models for Akure-Owo Highway, Ondo State," Journal of Enginearing Science, vol. 15, no. 2, pp. 53-70, 2019.

[21] Silva, P. B., Andrade, M., and Ferreira, S. "Machine Learning Applied to Road Safety Modelling: A Systematic Literature Review," Journal of Traffic and Transportation Engineering, vol. 7, no. 6, pp. 775-790, 2020.

[22] Vanitha, R and Swedha, M. "Prediction of Road Accident using Machine Learning Algorithms," Middle-East Journal of Applied Science and Technology, vol. 6, no. 2, pp. 64-75, 2023.

[23] Chen, T. and Guestrin, C. "XGBoost: A Scalable Tree Boosting System," San Francisco, CA, USA,, 2016.

[24] Li, L., Prato, C. G., and Wang, Y. "Ranking contributors to traffic crashes on mountainous freeways from an incomplete dataset: A sequential approach of multivariate imputation by chained equations and random forest classifier," Accident Analysis and Prevention, vol. 146, no. 1, p. 330–345, 2020.

[25] Alvarez, P., Fernandez, M. A., Gordaliza, A., Mansilla, A. and Molinero, A. "Geometric road design factors affecting the risk of urban run-off crashes," A case-control study: PLoS One, vol. 15, no. 6, p. e0234564, 2020.

[26] Madushani, J. S., Sandamal, R. K., Meddage, D. P., Pasindu, H. R., and Gomes, P. A. "Evaluating expressway traffic crash severity using logistic regression and explainable and supervised machine learning classifiers," Transportation Engineering, vol. 13, no. 1, pp. 13-20, 2023.

[27] Mohammadnazar, A., Mahdinia, I., Ahmad, N., Khattak, A. J., and Liu, J. "Understanding how relationships between crash frequency and correlates vary for multi-lane rural highways: Estimating geographically and temporally weighted regression models," Accident Analysis and Prevention, vol. 157, no. 1, p. 106146, 2021.

[28] Berhanu, Y., Schroder, D., Wodajo, B. T., and Aliimayehu, E. "Machine learning for predictions of road traffic accidents and spatial network analysis for safe routing on accident and congestion-prone road networks," Result in Engineering, vol. 23, no. 102737, pp. 1-22, 2024. doi: 10.1016/j.rineng.2024.102737.

[29] Bayode, O., Aderinola, O. S., and Oluyemi-Ayibiowu, B. D. "Application of Machine Learning for Road Safety Modeling of Selected South-West Highway in Nigeria," European Journal of Applied Science, Engineering and Technology, vol. 3, no. 3, pp. 202-213, 2025. doi: 10.59324/ejaset.2025.3(3).13

[30] Zhang, X., Waller, S. T., and Jiang, P. "An Ensemble Machine Learning‐Based Modeling Framework for Analysis of Traffic Crash Frequency.," Computer‐Aided Civil and Infrastructure Engineering, vol. 35, no. 3, pp. 258-276, 2020.

[31] Onuwurah, U. O., Ihueze, C. C., and Nwankwo, C. O. "Modelling Road Traffic Crash Variables in Anambra State, Nigeria: An Application of Negative Binomial Regression," Journal of Multidisciplinary Engineering Science Studies, vol. 7, no. 6, pp. 3942-3950, 2022.