Abstract

Traffic accidents pose a significant global threat to public safety, with the World Health Organization (WHO) estimating that they claim the lives of approximately 1.25 million individuals each year. Without intervention, traffic accidents are projected to become the leading cause of death by 2030. Predicting accident severity and understanding their underlying causes represent crucial steps in developing effective strategies to prevent accidents and enhance overall traffic safety. This paper presented an in-depth analysis of accident severity prediction, considering a wide range of factors, including the vehicle, driver, environmental conditions, and more. The study aims to predict the extent of the severity of traffic accidents using a comprehensive dataset comprising over 4 million incidents that occurred across 49 states in the United States of America (USA) between February 2016 and December 2020. Various machine learning models, including logistic regression (LR), support vector machine (SVM), decision tree (DT), and random forest (RF), were implemented and rigorously evaluated against multiple performance metrics. The achieved results reveal that the RF model stands out with the highest accuracy of 91% in predicting accident severity. Additionally, this model demonstrates excellent performance across additional evaluation metrics, including a precision rate of 89%, a recall rate of 91%, a root mean square error (RMSE) of 18%, and an F1 score of 89%. These findings emphasize the exceptional predictive power and robustness of the RF model, making it a highly promising approach for real-world traffic accident scenarios. This research provides valuable insights into predicting accident severity, which is crucial for the development of effective accident prevention strategies and improvements in traffic safety.

Keyword

Accident, Severity prediction, Machine learning, RMSE.

Cite this article

Houssam M, Abdellah A, Monir A

Refference

[1][1]Moosavi S, Samavatian MH, Parthasarathy S, Teodorescu R, Ramnath R. Accident risk prediction based on heterogeneous sparse data: new dataset and insights. In proceedings of the 27th SIGSPATIAL international conference on advances in geographic information systems 2019 (pp. 33-42). ACM.

[2][2]Mills BN, Andrey J, Hambly D. Analysis of precipitation-related motor vehicle collision and injury risk using insurance and police record information for Winnipeg, Canada. Journal of Safety Research. 2011; 42(5):383-90.

[3][3]Thompson JP, Baldock MR, Dutschke JK. Trends in the crash involvement of older drivers in Australia. Accident Analysis & Prevention. 2018; 117:262-9.

[4][4]Hao W, Kamga C, Daniel J. The effect of age and gender on motor vehicle driver injury severity at highway-rail grade crossings in the United States. Journal of Safety Research. 2015; 55:105-13.

[5][5]Zhao L, Wang C, Yang H, Wu X, Zhu T, Wang J. Exploring injury severity of non-motor vehicle riders involving in traffic accidents using the generalized ordered logit model. Ain Shams Engineering Journal. 2023; 14(5):101962.

[6][6]Pereira V, Bamel U, Paul H, Varma A. Personality and safety behavior: an analysis of worldwide research on road and traffic safety leading to organizational and policy implications. Journal of Business Research. 2022; 151:185-96.

[7][7]Wu J, Lu Y, Shi S, Zhou R, Liu Y. Research on the prediction model of hazardous chemical road transportation accidents. Journal of Loss Prevention in the Process Industries. 2023:105103.

[8][8]Alkheder S, AlRukaibi F, Aiash A. Risk analysis of traffic accidents’ severities: An application of three data mining models. ISA Transactions. 2020; 106:213-20.

[9][9]Ji A, Levinson D. Injury severity prediction from two-vehicle crash mechanisms with machine learning and ensemble models. IEEE Open Journal of Intelligent Transportation Systems. 2020; 1:217-26.

[10][10]Lane MN. Pricing risk transfer transactions1. ASTIN Bulletin: The Journal of the IAA. 2000; 30(2):259-93.

[11][11]Miyajima C, Nishiwaki Y, Ozawa K, Wakita T, Itou K, Takeda K, et al. Driver modeling based on driving behavior and its evaluation in driver identification. Proceedings of the IEEE. 2007; 95(2):427-37.

[12][12]Chang LY. Analysis of freeway accident frequencies: negative binomial regression versus artificial neural network. Safety Science. 2005; 43(8):541-57.

[13][13]Kumar S, Toshniwal D. A data mining framework to analyze road accident data. Journal of Big Data. 2015; 2(1):1-8.

[14][14]Wenqi L, Dongyu L, Menghua Y. A model of traffic accident prediction based on convolutional neural network. In 2nd international conference on intelligent transportation engineering 2017 (pp. 198-202). IEEE.

[15][15]Yu L, Du B, Hu X, Sun L, Han L, Lv W. Deep spatio-temporal graph convolutional network for traffic accident prediction. Neurocomputing. 2021; 423:135-47.

[16][16]Yuan Z, Zhou X, Yang T. Hetero-convlstm: a deep learning approach to traffic accident prediction on heterogeneous spatio-temporal data. In proceedings of the 24th international conference on knowledge discovery & data mining 2018 (pp. 984-92). ACM.

[17][17]Wahab L, Jiang H. A comparative study on machine learning based algorithms for prediction of motorcycle crash severity. PLoS one. 2019; 14(4):1-17.

[18][18]Zhu L, Lu L, Zhang W, Zhao Y, Song M. Analysis of accident severity for curved roadways based on bayesian networks. Sustainability. 2019; 11(8):1-17.

[19][19]Kopelias P, Papadimitriou F, Papandreou K, Prevedouros P. Urban freeway crash analysis: geometric, operational, and weather effects on crash number and severity. Transportation Research Record. 2007; 2015(1):123-31.

[20][20]Soderstrom CA, Dischinger PC, Kufera JA, Ho SM, Shepard A. Crash culpability relative to age and sex for injured drivers using alcohol, marijuana or cocaine. In annual proceedings/association for the advancement of automotive medicine 2005 (pp. 327-31). Association for the Advancement of Automotive Medicine.

[21][21]Zajac SS, Ivan JN. Factors influencing injury severity of motor vehicle–crossing pedestrian crashes in rural connecticut. Accident Analysis & Prevention. 2003; 35(3):369-79.

[22][22]Beirness DJ, Simpson HM, Williams AF. Role of cannabis and benzodiazepines in motor vehicle crashes. Drugs and Traffic. 2005:12-21.

[23][23]Zhang G, Yau KK, Chen G. Risk factors associated with traffic violations and accident severity in China. Accident Analysis & Prevention. 2013; 59:18-25.

[24][24]Islam M. Multi-vehicle crashes involving large trucks: a random parameter discrete outcome modeling approach. Journal of the Transportation Research Forum. 2015; 54(1):77-104.

[25][25]Rifaat SM, Tay R, De BA. Effect of street pattern on the severity of crashes involving vulnerable road users. Accident Analysis & Prevention. 2011; 43(1):276-83.

[26][26]Christie SM, Lyons RA, Dunstan FD, Jones SJ. Are mobile speed cameras effective? a controlled before and after study. Injury Prevention. 2003; 9(4):302-6.

[27][27]Moore DN, Schneider IVWH, Savolainen PT, Farzaneh M. Mixed logit analysis of bicyclist injury severity resulting from motor vehicle crashes at intersection and non-intersection locations. Accident Analysis & Prevention. 2011; 43(3):621-30.

[28][28]Al-ghamdi AS. Experimental evaluation of fog warning system. Accident Analysis & Prevention. 2007; 39(6):1065-72.

[29][29]Edwards JB. The relationship between road accident severity and recorded weather. Journal of Safety Research. 1998; 29(4):249-62.

[30][30]Behnood A, Al-bdairi NS. Determinant of injury severities in large truck crashes: a weekly instability analysis. Safety Science. 2020; 131:104911.

[31][31]Moosavi S, Samavatian MH, Parthasarathy S, Ramnath R. A countrywide traffic accident dataset. ArXiv Preprint Server. 2019:1-6.

[32][32]http://data-seattlecitygis.opendata.arcgis.com/datasets/5b5c745e0f1f48e7a53acec63a0022ab_0. Accessed 24 October 2023.

[33][33]https://data.brla.gov/Transportation-and-Infrastructure/Baton-Rouge-Traffic-Incidents/2tu5-7kif. Accessed 24 October 2023.

[34][34]Zong F, Xu H, Zhang H. Prediction for traffic accident severity: comparing the Bayesian network and regression models. Mathematical Problems in Engineering. 2013; 2013:1-10.

[35][35]Satri J, El MC, Hachimi H. Artificial intelligence and machine learning for a better decision making in the public sector. In 8th international conference on optimization and applications 2022 (pp. 1-5). IEEE.

[36][36]Hidayat TH, Ruldeviyani Y, Aditama AR, Madya GR, Nugraha AW, Adisaputra MW. Sentiment analysis of twitter data related to Rinca Island development using Doc2Vec and SVM and logistic regression as classifier. Procedia Computer Science. 2022; 197:660-7.

[37][37]Güven I, Şimşir F. Demand forecasting with color parameter in retail apparel industry using artificial neural networks (ANN) and support vector machines (SVM) methods. Computers & Industrial Engineering. 2020; 147:106678.

[38][38]Boser BE, Guyon IM, Vapnik VN. A training algorithm for optimal margin classifiers. In proceedings of the fifth annual workshop on computational learning theory. 1992 (pp. 144-52). ACM.

[39][39]Cortes C, Vapnik V. Support-vector networks. Machine Learning. 1995; 20:273-97.

[40][40]Vapnik VN. An overview of statistical learning theory. IEEE Transactions on Neural Networks. 1999; 10(5):988-99.

[41][41]Li K, Zhou G, Yang Y, Li F, Jiao Z. A novel prediction method for favorable reservoir of oil field based on grey wolf optimizer and twin support vector machine. Journal of Petroleum Science and Engineering. 2020; 189:1-11.

[42][42]Sahana M, Rehman S, Sajjad H, Hong H. Exploring effectiveness of frequency ratio and support vector machine models in storm surge flood susceptibility assessment: a study of Sundarban Biosphere Reserve, India. Catena. 2020; 189:104450.

[43][43]Yu Y, Shao M, Jiang L, Ke Y, Wei D, Zhang D, et al. Quantitative analysis of multiple components based on support vector machine (SVM). Optik. 2021; 237:166759.

[44][44]Hunt EB, Marin J, Stone PJ. Experiments in induction. Academic Press. 1996.

[45][45]Jin C, Li F, Ma S, Wang Y. Sampling scheme-based classification rule mining method using decision tree in big data environment. Knowledge-Based Systems. 2022; 244:108522.

[46][46]Chang MY, Chiang RD, Wu SJ, Chan CH. Mining unexpected patterns using decision trees and interestingness measures: a case study of endometriosis. Soft Computing. 2016; 20:3991-4003.

[47][47]Clarke DD, Forsyth R, Wright R. Machine learning in road accident research: decision trees describing road accidents during cross-flow turns. Ergonomics. 1998; 41(7):1060-79.

[48][48]https://www.analyticsvidhya.com/blog/2021/04/beginners-guide-to-decision-tree-classification-using-python/. Accessed 24 October 2023.

[49][49]Shorabeh SN, Samany NN, Minaei F, Firozjaei HK, Homaee M, Boloorani AD. A decision model based on decision tree and particle swarm optimization algorithms to identify optimal locations for solar power plants construction in Iran. Renewable Energy. 2022; 187:56-67.

[50][50]Maimon OZ, Rokach L. Data mining with decision trees: theory and applications. World Scientific; 2014.

[51][51]Breiman L. Random forests. Machine Learning. 2001; 45:5-32.

[52][52]Dietterich TG. An experimental comparison of three methods for constructing ensembles of decision trees: bagging, boosting, and randomization. Machine Learning. 2000; 40:139-57.

[53][53]Ho TK. The random subspace method for constructing decision forests. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1998; 20(8):832-44.

[54][54]Hosseinpour M, Ghaemi S, Khanmohammadi S, Daneshvar S. A hybrid high‐order type‐2 FCM improved random forest classification method for breast cancer risk assessment. Applied Mathematics and Computation. 2022; 424:127038.

[55][55]Chaudhary A, Kolhe S, Kamal R. An improved random forest classifier for multi-class classification. Information Processing in Agriculture. 2016; 3(4):215-22.

[56][56]Kim Y, Kim Y. Explainable heat-related mortality with random forest and SHapley Additive exPlanations (SHAP) models. Sustainable Cities and Society. 2022; 79:103677.

[57][57]Egwim CN, Alaka H, Toriola-coker LO, Balogun H, Sunmola F. Applied artificial intelligence for predicting construction projects delay. Machine Learning with Applications. 2021; 6:1-15.

[58][58]Mensouri D, Azmani A. A new marketing recommendation system using a hybrid approach to generate smart offers. Applied Computer Systems. 2022; 27(2):149-58.

[59][59]Alkheder S, Taamneh M, Taamneh S. Severity prediction of traffic accident using an artificial neural network. Journal of Forecasting. 2017; 36(1):100-8.

[60][60]Shaik ME, Islam MM, Hossain QS. A review on neural network techniques for the prediction of road traffic accident severity. Asian Transport Studies. 2021; 7:1-11.