Yaya Trafik Kazalarının Şiddetinin Tahmini ile Sürücü ve Yaya Kusurlarının Değerlendirilmesi

Abstract

Bu çalışmada, makine öğrenmesi algoritmaları olan AdaBoost, Gradient Boosting, XGBoost, K-En Yakın Komşular, Lojistik Regresyon, Destek Vektörü Sınıflandırıcısı, Karar Ağacı ve Rastgele Orman kullanılarak yaralı yaya sayısına göre kazaların şiddetini sınıflandırmak amacıyla yayaların karıştığı trafik kazaları incelenmiştir. Rastgele Orman modeli, yayaların karıştığı trafik kazalarını sınıflandırmak için en iyi model olarak belirlenmiş, %95'lik yüksek tahmin doğruluğu, 0,95'lik F1 puanı elde etmiş ve düşük hata ölçütleri göstermiştir. Araştırmada, yaya geçitlerinin varlığı, kavşak türü, sürücü yaşı, günün saati, ay ve mevsimsel değişiklikler gibi faktörlerin yanı sıra hem sürücü hem de yaya kusurları analiz edilmiştir. Sonuçlar, kavşak olmayan yerlerdeki kazaların öncelikle hız yapmak gibi sürücü hatalarından kaynaklandığını, istenmeyen yerlerde geçmek gibi yaya hatalarının da genel kaza oranına önemli ölçüde katkıda bulunduğunu ortaya koymuştur. Bulgular, trafik güvenliğini artırmak ve yaya yaralanmalarını ve ölümlerini azaltmak için yaya kazalarının özelliklerine ilişkin değerli bilgiler sunmuştur.

Keywords

• Kaza
• Yaya
• Makine Öğrenmesi
• Kusurlar

Prediction of Pedestrian Traffic Accident Severity and Evaluation of Driver and Pedestrian Faults

Abstract

This study investigated pedestrians involved traffic accidents with the aim of classifying the severity of accidents based on the number of injured pedestrians using machine learning algorithms, including AdaBoost, Gradient Boosting, XGBoost, K-Nearest Neighbors (KNN), Logistic Regression, Support Vector Classifier, Decision Tree, and Random Forest. The Random Forest model was identified as the best model for classifying pedestrian-involved traffic accidents, achieving high predictive accuracy of 95%, an F1 score of 0.95, and demonstrating low error metrics. The research analyzed both driver and pedestrian faults, alongside factors such as the presence of pedestrian crossings, intersection type, driver age, time of day, month and seasonal variations. The results revealed that accidents at locations without intersections were primarily caused by driver faults, such as speeding, while pedestrian faults, such as crossing at unintended locations, also significantly contribute to the overall accident rate. The findings offered valuable insights into the characteristics of pedestrian accidents to improve traffic safety and reduce pedestrian injuries and fatalities.

Keywords

• Accident
• Pedestrian
• Machine learning
• Faults

References

1. Acito, F. (2023). Classification and Regression Trees. In Predictive Analytics with KNIME: Analytics for Citizen Data Scientists (pp. 169-191): Springer.
2. Babu Nuthalapati, S., and Nuthalapati, A. (2024). Accurate weather forecasting with dominant gradient boosting using machine learning. Int. J. Sci. Res. Arch, 12(2), 408-422.
3. Campisi, T., Kuşkapan, E., Çodur, M. Y., and Dissanayake, D. (2024). Exploring the influence of socio-economic aspects on the use of electric scooters using machine learning applications: A case study in the city of Palermo. Research in Transportation Business & Management, 56, 101172.
4. Chen, C., Zhang, G., Qian, Z., Tarefder, R. A. and Tian, Z. (2016). Investigating driver injury severity patterns in rollover crashes using support vector machine models. Accident Analysis Prevention, 90, 128-139.
5. Chen, C., Zhang, G., Tarefder, R., Ma, J., Wei, H. and Guan, H. (2015). A multinomial logit model-Bayesian network hybrid approach for driver injury severity analyses in rear-end crashes. Accident Analysis Prevention, 80, 76-88.
6. Choi, J., Gu, B., Chin, S. and Lee, J.-S. (2020). Machine learning predictive model based on national data for fatal accidents of construction workers. Automation in Construction, 110, 102974.
7. Costa, V. G. and Pedreira, C. E. (2023). Recent advances in decision trees: An updated survey. Artificial Intelligence Review, 56(5), 4765-4800.
8. Coşkun, S., Kartal, M., Coşkun, A. and Bircan, H. (2004). Lojistik regresyon analizinin incelenmesi ve diş hekimliğinde bir uygulaması. Cumhuriyet Üniversitesi Diş Hekimliği Fakültesi Dergisi, 7(1), 42-50.

9. Çeven, S. and Albayrak, A. (2024). Traffic accident severity prediction with ensemble learning methods. Computers Electrical Engineering, 114, 109101.
10. Davagdorj, K., Pham, V. H., Theera-Umpon, N. and Ryu, K. H. (2020). XGBoost-based framework for smoking-induced noncommunicable disease prediction. International journal of environmental research public health, 17(18), 6513.
11. Esmaeili-Falak, M. and Benemaran, R. S. (2024). Ensemble extreme gradient boosting based models to predict the bearing capacity of micropile group. Applied Ocean Research, 151, 104149.
12. Fountas, G., Anastasopoulos, P. C. and Abdel-Aty, M. (2018). Analysis of accident injury-severities using a correlated random parameters ordered probit approach with time variant covariates. Analytic methods in accident research, 18, 57-68.
13. Gamil, S., Zeng, F., Alrifaey, M., Asim, M. and Ahmad, N. (2024). An Efficient AdaBoost Algorithm for Enhancing Skin Cancer Detection and Classification. Algorithms, 17(8), 353.
14. Gökdağ, M. and Baş, F. İ. (2019). The Effect of Fatigue and Sleepiness upon Driver Behaviors. Erzincan University Journal of Science Technology, 12(2), 850-862.
15. Iranitalab, A. and Khattak, A. (2017). Comparison of four statistical and machine learning methods for crash severity prediction. Accident Analysis Prevention, 108, 27-36.
16. Itzkin, M., Palmsten, M. L., Buckley, M. L., Birchler, J. J. and Torres-Garcia, L. M. (2025). Developing a decision tree model to forecast runup and assess uncertainty in empirical formulations. Coastal Engineering, 195, 104641.
17. Izonin, I., Tkachenko, R., Shakhovska, N. and Lotoshynska, N. (2021). The additive input-doubling method based on the SVR with nonlinear kernels: Small data approach. Symmetry, 13(4), 612.
18. Jamal, A., Zahid, M., Tauhidur Rahman, M., Al-Ahmadi, H. M., Almoshaogeh, M., Farooq, D. and Ahmad, M. (2021). Injury severity prediction of traffic crashes with ensemble machine learning techniques: A comparative study. nternational journal of injury control safety promotion, 28(4), 408-427.
19. Kang, K. and Ryu, H. (2019). Predicting types of occupational accidents at construction sites in Korea using random forest model. Safety Science, 120, 226-236.
20. KGM. (2024). Trafik Kazaları Özeti 2023: Karayollaı Genel Müdürlüğü, Trafik Güvenliği Dairesi Başkanlığı.
21. Kuşkapan, E., Çodur, M. Y. and Atalay, A. (2021). Speed violation analysis of heavy vehicles on highways using spatial analysis and machine learning algorithms. Accident Analysis Prevention, 155, 106098.
22. Kuşkapan, E., Sahraei, M. A., Çodur, M. K. and Çodur, M. Y. (2022a). Pedestrian safety at signalized intersections: Spatial and machine learning approaches. Journal of Transport Health, 24, 101322.
23. Kuşkapan, E., Çodur, M. K. and Çodur, M. Y. (2022b). Türkiye’deki Demiryolu Enerji Tüketiminin Yapay Sinir Ağlari İle Tahmin Edilmesi. Konya Journal of Engineering Sciences, 10(1), 72-84.
24. Liao, Y. and Vemuri, V. R. (2002). Using text categorization techniques for intrusion detection. Paper presented at the 11th USENIX Security Symposium (USENIX Security 02).
25. Ma, Z., Mei, G. and 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.
26. Meek, C., Thiesson, B. and Heckerman, D. (2002). The learning-curve sampling method applied to model-based clustering. Journal of Machine Learning Research, 2(Feb), 397-418.
27. Obasi, I. C. and Benson, C. (2023). Evaluating the effectiveness of machine learning techniques in forecasting the severity of traffic accidents. Heliyon, 9(8).
28. Otchere, D. A., Ganat, T. O. A., Ojero, J. O., Tackie-Otoo, B. N. and Taki, M. Y. (2022). Application of gradient boosting regression model for the evaluation of feature selection techniques in improving reservoir characterisation predictions. Journal of Petroleum Science Engineering, 208, 109244.
29. Pachouly, J., Ahirrao, S., Kotecha, K., Selvachandran, G. and Abraham, A. (2022). A systematic literature review on software defect prediction using artificial intelligence: Datasets, Data Validation Methods, Approaches, and Tools. Engineering Applications of Artificial Intelligence, 111, 104773.
30. Petridou, E. and Moustaki, M. (2000). Human factors in the causation of road traffic crashes. European journal of epidemiology, 16, 819-826.
31. Raman, P., Kannan, N., Kumar, S. and Raunak, K. (2020). Analysis and prediction of industrial accidents using machine learning. International Journal of Advanced Science and Technology, 29, 4990-5000.
32. Sameen, M. I. and Pradhan, B. (2017). Severity prediction of traffic accidents with recurrent neural networks. Applied Sciences, 7(6), 476.
33. Sarkar, S., Pateshwari, V. and Maiti, J. (2017). Predictive model for incident occurrences in steel plant in India. Paper presented at the 2017 8th International Conference on Computing, Communication and Networking Technologies (ICCCNT).
34. Sekulić, A., Kilibarda, M., Heuvelink, G. B., Nikolić, M. and Bajat, B. (2020). Random forest spatial interpolation. Remote Sensing, 12(10), 1687.
35. Tiwari, G. (2020). Progress in pedestrian safety research. International journal of injury control safety promotion, 27(1), 35-43.
36. Ullah, I., Raza, B., Malik, A. K., Imran, M., Islam, S. U. and Kim, S. W. (2019). A churn prediction model using random forest: analysis of machine learning techniques for churn prediction and factor identification in telecom sector. IEEE access, 7, 60134-60149.
37. Wang, Y. and Ni, X. S. (2019). A XGBoost risk model via feature selection and Bayesian hyper-parameter optimization. arXiv, arXiv:1901.08433.
38. WHO. (2022). Preventing injuries and violence: an overview (9240047131). Retrieved from https://iris.who.int/handle/10665/361331
39. WHO. (2023a). Global status report on road safety 2023: summary: World Health Organization.
40. WHO. (2023b). Pedestrian safety: a road safety manual for decision-makers and practitioners, second edition. Geneva: World Health Organization.
41. Xiao, L., Dong, Y. and Dong, Y. (2018). An improved combination approach based on Adaboost algorithm for wind speed time series forecasting. Energy Conversion Management, 160, 273-288.
42. Yang, Y., Wang, K., Yuan, Z. and Liu, D. (2022). Predicting Freeway Traffic Crash Severity Using XGBoost‐Bayesian Network Model with Consideration of Features Interaction. Journal of advanced transportation, 2022(1), 4257865.
43. Yoon, J. (2021). Forecasting of real GDP growth using machine learning models: Gradient boosting and random forest approach. Computational Economics, 57(1), 247-265.