A STUDY ON TRAFFIC CRASH SEVERITY PREDICTION USING MACHINE LEARNING ALGORITHMS

Abstract

Severity of traffic accidents holds significant importance in terms of affecting human life. Predicting the severity of traffic accidents is crucial for accident prevention and ensuring safe driving. The success of predictive methods enables the identification of relevant risk factors and the implementation of countermeasures. The causes of traffic accidents can be attributed to a wide range of variables. In particular, factors such as road disturbances, weather conditions, vehicle speed as visible causes cause traffic accidents. Obtaining real-time information about the immediate situation of an accident is challenging. However, by calculating the severity of a potential accident based on its causes, it is possible to mitigate future accidents. In this study, machine learning algorithms were tested on a dataset of traffic accidents collected in the US states between 2016 and 2023 to predict accident severity. Comparative performance analysis was conducted using machine learning techniques such as Decision Tree, Random Forest (RF), Logistic Regression (LR), Support Vector Machine (SVM), K-Nearest Neighbors (K-NN), and Naive Bayes (NB) to identify contributing factors to accidents. The results were evaluated according to Precision, Recall, and F1-Score metrics. It has been determined that the accuracy of the accident severity classification accuracy of the Decision Tree algorithm provides the best performance among others with an accuracy of 99.6%. This outcome signifies the potential of advanced predictive methods in significantly reducing the occurrence of traffic accidents through targeted interventions based on identified risk factors. This study's findings underscore the pivotal role of machine learning algorithms in enhancing the accuracy of traffic accident severity prediction.

Keywords

• Classification
• crash severity
• machine learning
• traffic accident

MAKİNE ÖĞRENMESİ ALGORİTMALARI KULLANILARAK TRAFİK KAZASI ŞİDDETİNİN TAHMİNİ ÜZERİNE BİR ÇALIŞMA

Abstract

Trafik kazalarının şiddeti insan hayatını etkilemesi açısından büyük önem arz etmektedir. Trafik kazası şiddetinin tahmin edilmesi, trafik kazalarının önlenmesi ve güvenli bir sürüş sağlanması için önemlidir. Tahmin yöntemlerinin başarısı sayesinde ilgili risk faktörleri çıkarılmakta ve karşı önlemler alınabilmektedir. Trafik kazalarının sebepleri çok fazla değişkene bağlı olabilmektedir. Özellikle görünür sebepler olarak yol bozuklukları, hava şartları, araç hızı gibi faktörler trafik kazalarına neden olmaktadır. Oluşan bir kazada kazanın anlık durumunun ne olduğu bilgisini almak oldukça güçtür. Ancak sebeplerden kaynaklanan bir olası kazanın şiddeti hesaplanarak gelecek zamanda oluşacak kazaların önüne geçilmesi mümkündür. Bu çalışmada kaza şiddeti tahmini için ABD eyaletlerinde 2016-2023 yılları arasında toplanan trafik kaza veri seti üzerinde makine öğrenmesi algoritmaları test edilerek kaza şiddeti tahminleri yapılmıştır. Kazaya sebep olan etkenleri belirlemek için makine öğrenme tekniklerinden Decision Tree, Random Forest (RF), Logistic Regression (LR), Support Vector Machine (SVM), K-Nearest Neighbours (KNN) ve Navie Bayes (NB) algoritmaları kullanılarak karşılaştırmalı bir başarı analizi yapılmıştır. Sonuçlar Precision, Recall and F1-Score ölçütlerine göre değerlendirilmiştir. Decision Tree algoritmasının kaza ciddiyetini sınıflandırma accuracy değeri %99.6 doğrulukla diğerleri arasında en iyi performans sağladığı belirlenmiştir.

Keywords

• Sınıflandırma
• kaza şiddeti
• makine öğrenmesi
• trafik kazası

References

1. Aldhari, I., Almoshaogeh, M., Jamal, A., Alharbi, F., Alinizzi, M., Haider, H., 2022. Severity Prediction of Highway Crashes in Saudi Arabia Using Machine Learning Techniques. Applied Sciences, 13, (1), 233.
2. Assi, K., 2020. Prediction of traffic crash severity using deep neural networks: a comparative study. In 2020 International Conference on Innovation and Intelligence for Informatics, December, Computing and Technologies (3ICT) (pp. 1-6). IEEE.
3. Azhar, A., Rubab, S., Khan, M. M., Bangash, Y. A., Alshehri, M. D., Illahi, F., Bashir, A. K., 2023. Detection and prediction of traffic accidents using deep learning techniques. Cluster Computing, 26, (1), 477-493.
4. Baykal, T., Ergezer, F., Eriskin, E., & Terzi, S., 2023. Accident Severity Prediction in Big Data Using Auto-Machine Learning. Scientia Iranica.
5. Chakraborty, M., Gates, T. J., Sinha, S., 2023. Causal analysis and classification of traffic crash injury severity using machine learning algorithms. Data science for transportation, 5, (2), 12.
6. Colagrande, S., 2022. A methodology for the characterization of urban road safety through accident data analysis. Transportation research procedia, 60, 504-511.
7. Danesh, A., Ehsani, M., Moghadas Nejad, F., Zakeri, H., 2022. Prediction model of crash severity in imbalanced dataset using data leveling methods and metaheuristic optimization algorithms. International journal of crashworthiness, 27, (6), 1869-1882.
8. Dong, C., Shao, C., Li, J., Xiong, Z., 2018. An improved deep learning model for traffic crash prediction. Journal of Advanced Transportation, 2018, 1-13.

9. Formosa, N., Quddus, M., Ison, S., Abdel-Aty, M., Yuan, J., 2020. Predicting real-time traffic conflicts using deep learning. Accident Analysis & Prevention, 136, 105429.
10. Hossain, M. J., Ivan, J. N., Zhao, S., Wang, K., Sharmin, S., Ravishanker, N., Jackson, E., 2023. Considering demographics of other involved drivers in predicting the highest driver injury severity in multi-vehicle crashes on rural two-lane roads in California. Journal of Transportation Safety & Security, 15, (1), 43-58.
11. Hou, Q., Huo, X., Leng, J., Mannering, F., 2022. A note on out-of-sample prediction, marginal effects computations, and temporal testing with random parameters crash-injury severity models. Analytic methods in accident research, 33, 100191.
12. Hussain, S. F., Ashraf, M. M., 2023. A novel one-vs-rest consensus learning method for crash severity prediction. Expert Systems with Applications, 228, 120443.
13. Khattak, A., Almujibah, H., Elamary, A., Matara, C. M., 2022. Interpretable Dynamic Ensemble Selection Approach for the Prediction of Road Traffic Injury Severity: A Case Study of Pakistan’s National Highway N-5. Sustainability, 14, (19), 12340.
14. Kong, J. S., Lee, K. H., Kim, O. H., Lee, H. Y., Kang, C. Y., Choi, D., Sung, T. E., 2023. Machine learning-based injury severity prediction of level 1 trauma center enrolled patients associated with car-to-car crashes in Korea. Computers in biology and medicine, 153, 106393.
15. Kukartsev, V., Mikhalev, A., Stashkevich, A., Moiseeva, K., Kauts, I., 2022. Analysis of Data in solving the problem of reducing the accident rate through the use of special means on public roads. In 2022 IEEE International IOT, Electronics and Mechatronics Conference (IEMTRONICS), June, 1-4. IEEE.
16. Kunt, M. M., Aghayan, I., Noii, N., 2011. Prediction for traffic accident severity: comparing the artificial neural network, genetic algorithm, combined genetic algorithm and pattern search methods. Transport, 26, (4), 353-366.
17. Kushwaha, M., Abirami, M. S., 2021. Comparative Analysis on the Prediction of Road Accident Severity Using Machine Learning Algorithms. In International Conference on Micro-Electronics and Telecommunication Engineering, September, 269-280. Singapore: Springer Nature Singapore.
18. Li, K., Xu, H., Liu, X., 2022. Analysis and visualization of accidents severity based on LightGBM-TPE. Chaos, Solitons & Fractals, 157, 111987.
19. Ma, Z., Mei, G., Cuomo, S., 2021. An analytic framework using deep learning for prediction of traffic accident injury severity based on contributing factors. Accident Analysis & Prevention, 160, 106322.
20. Manzoor, M., Umer, M., Sadiq, S., Ishaq, A., Ullah, S., Madni, H. A., Bisogni, C., 2021. RFCNN: Traffic accident severity prediction based on decision level fusion of machine and deep learning model. IEEE Access, 9, 128359-128371.
21. Marcillo, P., Valdivieso Caraguay, Á. L., Hernández-Álvarez, M., 2022. A Systematic Literature Review of Learning-Based Traffic Accident Prediction Models Based on Heterogeneous Sources. Applied Sciences, 12, (9), 4529.
22. 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.
23. Rabbani, M. B. A., Musarat, M. A., Alaloul, W. S., Ayub, S., Bukhari, H., Altaf, M., 2022. Road accident data collection systems in developing and developed countries: a review. International Journal of Integrated Engineering, 14, (1), 336-352.
24. Rahim, M. A., Hassan, H. M., 2021. A deep learning based traffic crash severity prediction framework. Accident Analysis & Prevention, 154, 106090.
25. Rezaei, S., Liu, X., 2019. Deep learning for encrypted traffic classification: An overview. IEEE communications magazine, 57, (5), 76-81.
26. Sameen, M. I., Pradhan, B., 2017. Severity prediction of traffic accidents with recurrent neural networks. Applied Sciences, 7, (6), 476.
27. Sameen, M. I., Pradhan, B., Shafri, H. Z. M., Hamid, H. B., 2019. Applications of deep learning in severity prediction of traffic accidents. In GCEC 2017: Proceedings of the 1st Global Civil Engineering Conference 1 (pp. 793-808). Springer Singapore.
28. Santos, K., Dias, J. P., Amado, C., 2022. A literature review of machine learning algorithms for crash injury severity prediction. Journal of safety research, 80, 254-269.
29. Sattar, K., Chikh Oughali, F., Assi, K., Ratrout, N., Jamal, A., Masiur Rahman, S., 2023. Transparent deep machine learning framework for predicting traffic crash severity. Neural Computing and Applications, 35, (2), 1535-1547.
30. Shaygan, M., Meese, C., Li, W., Zhao, X. G., Nejad, M., 2022. Traffic prediction using artificial intelligence: review of recent advances and emerging opportunities. Transportation research part C: emerging technologies, 145, 103921.
31. Vaiyapuri, T., Gupta, M., 2021. Traffic accident severity prediction and cognitive analysis using deep learning. Soft Computing, 1-13.
32. World Health Organization, “Road Traffic Injuries”, 2023. Date of Access https://www.who.int/news-room/fact-sheets/detail/road-traffic-injuries
33. Yang, Z., Zhang, W., Feng, J., 2022. Predicting multiple types of traffic accident severity with explanations: A multi-task deep learning framework. Safety science, 146, 105522.
34. Zhang, S., Khattak, A., Matara, C. M., Hussain, A., Farooq, A., 2022. Hybrid feature selection-based machine learning Classification system for the prediction of injury severity in single and multiple-vehicle accidents. PLoS one, 17, (2), e0262941.
35. Dataset, “US Accidents 2016-2023. Date of Access:https://www.kaggle.com/datasets/sobhanmoosavi/us-accidents
36. Yan, M., Shen, Y., 2022. Traffic accident severity prediction based on random forest. Sustainability, 14, (3), 1729.
37. Yas, Q. M., Zaidan, A. A., Zaidan, B. B., Rahmatullah, B., Karim, H. A., 2018. Comprehensive insights into evaluation and benchmarking of real-time skin detectors: Review, open issues & challenges, and recommended solutions. Measurement, 114, 243-260.
38. Rodionova, M., Skhvediani, A., Kudryavtseva, T., 2022. Prediction of crash severity as a way of road safety improvement: The case of SaintPetersburg, Russia. Sustainability, 14, (16), 9840.