Makine Öğrenmesi Algoritmalarını Kullanılarak Pandemi Şartları Altında Trafik Kazalarının Analizi

Abstract

2019 yılında ortaya çıkan COVID-19 pandemisi, ruhsal, psikolojik, sosyal, ekonomik, sağlık ve ulaşım olmak üzere hayatın tüm alanlarına etki ettiği gözlemlenmiştir. COVID-19 ‘dan kaynaklı pandemi süreci birçok olumsuz sonuçlarına rağmen, bazı olumlu sonuçlar da doğurmuştur. Bu çalışmada, pandemi sürecinin olumlu sonuçlarından biri detaylı olarak ele alınmıştır. Çalışma, Türkiye’de Zonguldak ili de dahil olmak üzere tüm büyükşehirleri kapsamaktadır. Bu çalışma ile, COVID-19 karantinalarının 2012-2019 yılları arasında gerçekleşen ölümlü ve yaralanmalı trafik kazaları üzerindeki etkisi, Extreme Gradient Boost (XGBoost) algoritması kullanılarak detaylı olarak araştırılmıştır. Google Colab platformunda Python programlama dilinde makine öğrenmesi kullanılarak doğrusal olmayan regresyon analizleri yapılmıştır. Analiz sonucunda 2020 yılı için tahmini kaza sayısı elde edilmiş ve bu sayı 2020 yılında büyükşehirlerde ve Zonguldak'ta meydana gelen gerçek ölümlü ve yaralanmalı kaza verileri ile karşılaştırılmıştır. Bu analiz, COVID-19 karantinalarının Zonguldak, Diyarbakır ve Ordu illeri hariç tüm büyükşehirlerde trafik kazalarında azalmaya neden olduğunu göstermiştir. Makine öğrenimi algoritmaları ile 2020 yılı için büyükşehirlerde tahmin edilen trafik kaza sayılarının, 2020 yılında gerçekleşen trafik kaza sayılarına göre %18,3 oranında daha yüksek olduğu ortaya çıkmıştır. Dolayısıyla Makine öğrenmesi ile doğru tahminler yapılabilse de deprem, savaş ve pandemi gibi olağanüstü durumlarda hata payı olabileceği gözlemlenmiştir.

Keywords

• Karantina
• Trafik kazaları
• Kaza Tahmin Modeli
• Makine Öğrenmesi
• Extreme Gradient Boost

Analysis Of Traffic Accidents Using Machine Learning Under Pandemic Conditions

Abstract

The COVID-19 pandemic that emerged in 2019 affected all aspects of life, including spiritual, psychological, social, economic, health and transportation aspects. Despite its negative consequences, however, the COVID-19 pandemic also produced some positive results. This study investigated the effect of COVID-19 lockdowns on killed-and-injured traffic accidents in metropolitan cities and Zonguldak Province in Turkey from 2012–2019 using the Extreme Gradient Boost (XGBoost) algorithm. Nonlinear regression analyses were performed using machine learning in Python programming language on the Google Colab platform. The analysis provided an estimated number of accidents for 2020, which was compared with the real killed-and-injured accidents data from metropolitan cities and in Zonguldak in 2020. The comparison showed that COVID-19 lockdowns caused a decrease in traffic accidents in metropolitan cities and Zonguldak Province, except in Diyarbakır and Ordu. It has been revealed that the number of traffic accidents predicted by machine learning algorithms in metropolitan areas for 2020 is 18.3% higher than the number of traffic accidents in 2020. Therefore, although accurate predictions can be made with machine learning, it has been observed that there may be a margin of error in extraordinary situations such as earthquakes, wars and pandemics.

Keywords

• Lockdown
• Traffic accidents
• Accident prediction model
• Machine learning
• Extreme gradient boost

References

1. Aloi, A., Alonso, B., Benavente, J., Cordera, R., Echániz, E., González, F., Ladisa, C., Lezama-Romanelli, R., López-Parra, Á., Mazzei, V., Perrucci, L., Prieto-Quintana, D., Rodríguez, A., & Sañudo, R. (2020). Effects of the COVID-19 Lockdown on Urban Mobility: Empirical Evidence from the City of Santander (Spain). Sustainability, 12(9), 3870. https://doi.org/10.3390/su12093870
2. Bayraktutan, Y., & Özbilgin, M. (2013). Türkiye’de İller Düzeyinde Karayolu Yük Trafiği Dağılımının Analizi. Çukurova Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, 17(2), 81-92.
3. Bazlamit, S. M., Eid, A., & Al-mofleh, H. (2020). Impact of fasting on traffic accidents. Jordan Journal of Civil Engineering, 14(2), 431–442.
4. Brodeur, A., Cook, N., & Wright, T. (2021). On the effects of COVID-19 safer-at-home policies on social distancing, car crashes and pollution. Journal of Environmental Economics and Management, 106, 102427. https://doi.org/10.1016/j.jeem.2021.102427
5. Chang, L.-Y., & Wang, H.-W. (2006). Analysis of traffic injury severity: An application of non-parametric classification tree techniques. Accident Analysis & Prevention, 38(5), 1019–1027. https://doi.org/10.1016/j.aap.2006.04.009
6. Chong, M., Abraham, A., & Paprzycki, M. (2005). No TitleTraffic accident analysis using machine learning paradigms. Informatica, 29(1), 89–98.
7. Christey, G., Amey, J., Campbell, A., & Smith, A. (2020). Variation in volumes and characteristics of trauma patients admitted to a level one trauma centre during national level 4 lockdown for COVID-19 in New Zealand. The New Zealand Medical Journal, 133(1513), 81-88.
8. Deok, K. C. (2019). Data-Driven Materials Modeling with XGBoost Algorithm and Statistical Inference Analysis for Prediction of Fatigue Strength of Steels. International Journal of Precision Engineering and Manufacturing, 20(1), 129–138. https://doi.org/10.1007/s12541-019-00048-6

9. Envepo A.Ş. (2018) Makine Öğrenmesi Nasıl Çalışır? Makine Öğrenme Algoritmaları. https://www.envepo.com/blog/makine-ogrenmesi-nasil-calisir-makine-ogrenme-algoritmalari
10. Emniyet Genel Müdürlüğü Trafik Başkanlığı (2020). Trafik İstatistik Bülteni Ülke Geneli̇. https://trafik.gov.tr/kurumlar/trafik.gov.tr/04-Istatistik/Aylik/202503/Mart-2025.pdf
11. Gökdaǧ, M., Kaya, M. D., Atalay, A., & Haşiloǧlu, A. S. (2004). Injuries and fatalities in Turkish road traffic accidents. Proceedings of the Institution of Civil Engineers: Transport, 157(4), 231–237. https://doi.org/10.1680/tran.2004.157.4.231
12. Ibrahem Ahmed Osman, A., Najah Ahmed, A., Chow, M. F., Feng Huang, Y., & El-Shafie, A. (2021). Extreme gradient boosting (Xgboost) model to predict the groundwater levels in Selangor Malaysia. Ain Shams Engineering Journal, 12(2),1545-1556. https://doi.org/10.1016/j.asej.2020.11.011
13. Jayavel, M., & Lizy, M. L. (2014). Knowledge and Attitude Regarding prevention of Road Traffic Accidents among Adolescents. Innovations in Pharmaceuticals and Pharmacotherapy (IPP), 2(1), 328–339.
14. Jovic Vranes, A., Bjegovic Mikanovic, V., Milin Lazovic, J., & Kosanovic, V. (2018). Road traffic safety as a public health problem: Evidence from Serbia. Journal of Transport and Health, 8, 55–62. https://doi.org/10.1016/j.jth.2017.12.005
15. Korkmaz, E. (2022). COVID-19 Salgın Sürecinin Toplu Taşıma Sistemlerine Etkisinin Anket Yöntemiyle İstanbul-Ankara İçin İncelenmesi. Afet ve Risk Dergisi, 5(1), 247-260. https://doi.org/10.35341/afet.1060291
16. Kwon, O. H., Rhee, W., & Yoon, Y. (2015). Application of classification algorithms for analysis of road safety risk factor dependencies. Accident Analysis & Prevention, 75, 1–15. https://doi.org/10.1016/j.aap.2014.11.005
17. Lin, L., Shi, F., & Li, W. (2021). Assessing inequality, irregularity, and severity regarding road traffic safety during COVID-19. Scientific Reports, 11(1), 1-7. https://doi.org/10.1038/s41598-021-91392-z
18. Lin, Y., & Li, R. (2020). Real-time traffic accidents post-impact prediction: Based on crowdsourcing data. Accident Analysis and Prevention, 145(2020), 1-11 105696. https://doi.org/10.1016/j.aap.2020.105696
19. Liu, W. Q., Hwang, B. G., Shan, M., & Looi, K. Y. (2019). Prefabricated Prefinished Volumetric Construction: Key Constraints and Mitigation Strategies. IOP Conference Series: Earth and Environmental Science, 385(1), 1-7. https://doi.org/10.1088/1755-1315/385/1/012001
20. Ma, J., Ding, Y., Cheng, J. C. P., Tan, Y., Gan, V. J. L., & Zhang, J. (2019). Analyzing the Leading Causes of Traffic Fatalities Using XGBoost and Grid-Based Analysis: A City Management Perspective. IEEE Access, 7, 148059–148072. https://doi.org/10.1109/ACCESS.2019.2946401
21. Metintas, S. (2020). Epidemiology of COVID-19. Eurasian Journal of Pulmonology, 22(4), 2-7. https://doi.org/10.4103/ejop.ejop_55_20
22. Muhammad, L. J., Salisu, S., Yakubu, A., Malgwi, Y. M., Abdullahi, E. T., Mohammed, I. . A., & Muhammad, N. A. (2017). Using Decision Tree Data Mining Algorithm to Predict Causes of Road Traffic Accidents, its Prone Locations and Time along Kano –Wudil Highway. International Journal of Database Theory and Application, 10(1), 197–206. https://doi.org/10.14257/ijdta.2017.10.1.18
23. Nuñez, J. H., Sallent, A., Lakhani, K., Guerra-Farfan, E., Vidal, N., Ekhtiari, S., & Minguell, J. (2020). Impact of the COVID-19 Pandemic on an Emergency Traumatology Service: Experience at a Tertiary Trauma Centre in Spain. Injury, 51(7), 1414–1418. https://doi.org/10.1016/j.injury.2020.05.016
24. Oguzoglu, U. (2020). Covid-19 Lockdowns and Decline in Traffic Related Deaths and Injuries. SSRN Electronic Journal. 13278, 19, 1-17. https://doi.org/10.2139/ssrn.3608527
25. Parsa, A. B., Movahedi, A., Taghipour, H., Derrible, S., & Mohammadian, A. (Kouros). (2020). Toward safer highways, application of XGBoost and SHAP for real-time accident detection and feature analysis. Accident Analysis and Prevention, 136(2020), 105405. https://doi.org/10.1016/j.aap.2019.105405
26. Qureshi, A. I., Huang, W., Khan, S., Lobanova, I., Siddiq, F., Gomez, C. R., & Suri, M. F. K. (2020). Mandated societal lockdown and road traffic accidents. Accident Analysis and Prevention, 146(2020), 105747. https://doi.org/10.1016/j.aap.2020.105747
27. Rezapour Mashhadi, M. M., Saha, P., & Ksaibati, K. (2017). Impact of traffic Enforcement on Traffic Safety. International Journal of Police Science & Management, 19(4), 238–246. https://doi.org/10.1177/1461355717730836
28. Saladié, Ò., Bustamante, E., & Gutiérrez, A. (2020). COVID-19 lockdown and reduction of traffic accidents in Tarragona province, Spain. Transportation Research Interdisciplinary Perspectives, 8(2020), 100218. https://doi.org/10.1016/j.trip.2020.100218
29. Selimoğlu, Eda. (2014). Trafik Kazalarının Nedenleri , Sonuçları ve Kazaların Önlenmesine İlişkin Öneriler. Ziraat Mühendisliği Dergisi, 361, 51–54.
30. Shilling, F., & Waetjen, D. (2020). Special Reports: Impact of COVID-19 on California Traffic Crashes. Road Ecology Center https://roadecology.ucdavis.edu/content/reports-covid-19-mitigation-and-traffic
31. Sohn, S. Y., & Shin, H. (2001). Pattern recognition for road traffic accident severity in Korea. Ergonomics, 44(1), 107–117. https://doi.org/10.1080/00140130120928
32. Tang, J., Zheng, L., Han, C., Liu, F., & Cai, J. (2020). Traffic Incident Clearance Time Prediction and Influencing Factor Analysis Using Extreme Gradient Boosting Model. Journal of Advanced Transportation, 2020, 1-12. https://doi.org/10.1155/2020/6401082
33. Türkiye İstatistik Kurumu. (2020). Türkiye İstatistik Kurumu. Türkiye karayollarında 2012-2018 yılları arasında gerçekleşen trafik kazaları verileri. https://data.tuik.gov.tr/bulten/index?p=karayolu-trafik-kaza-istatistikleri-2020-37436
34. World Health Organization (2019). World Health Organization, Statistics Annual 2019: Geneva., WHO, Statistics Annual. https://iris.who.int/bitstream/handle/10665/324835/9789241565707-eng.pdf
35. Yavuz, A. A., Ergül, B., & Aşık, E. G. (2021). Trafik Kazalarının Makine Öğrenmesi Yöntemleri Kullanılarak Değerlendirilmesi Evaluation of Traffic Accidents Using Machine Learning Methods. Uluslararası Mühendislik Araştırma ve Geliştirme Dergisi, 13(1), 66–73. https://doi.org/10.29137/umagd.705156