Forecasting of defects causing traffic accidents using time series analysis methods

Abstract

Traffic accidents can cause millions of people to lose their lives, get injured and lose money every year. Many factors can be mentioned in the occurrence of traffic accidents that have such a big impact. The analysis of these factors and taking steps for the future are great importance in terms of transportation safety. In this study, the defects that cause traffic accidents were examined in five categories. Using time series analysis models, a forecast was made for the values of the defects until 2030. The study concluded that there would be an increase in driver defects which have the highest rate in the occurrence of traffic accidents and in road defect values, while pedestrian and passenger defect values would remain stable, and there would be a decrease in road defect values. Considering the findings obtained, suggestions were presented for all stakeholders creating traffic according to the vision zero understanding.

Keywords

• Traffic accident defects
• Time series analysis
• Prediction
• Transportation safety

Trafik kazalarına sebep olan kusurların zaman serisi analiz yöntemleriyle kestirimi

Abstract

Trafik kazaları her yıl milyonlarca insanın hayatını kaybetmesine, yaralanmasına ve maddi kayıplara sebep olabilmektedir. Böylesine büyük etkisi olan trafik kazalarının meydana gelmesinde ise birçok faktörden söz edilebilmektedir. Bu faktörlerin analizi, geleceğe yönelik adımlar atılması ise ulaşım güvenliği açısından büyük bir öneme sahiptir. Bu çalışmada trafik kazalarına sebep olan kusurlar beş kategoride incelenmiştir. Zaman serisi analizi modelleri kullanılarak 2030 yılına kadar kusurların değerlerine yönelik tahmin yapılmıştır. Çalışmada trafik kazalarının meydana gelmesinde en yüksek orana sahip olan sürücü ile yol kusur değerlerinde artma meydana geleceği, yaya ve yolcu kusurlarının stabil devam edeceği, yol kusurlarında ise azalma meydana geleceği sonucuna ulaşılmıştır. Elde edilen bulgular dikkate alınarak vizyon sıfır anlayışına göre trafiği oluşturan tüm paydaşlara yönelik öneriler sunulmuştur.

Keywords

• Trafik kaza kusurları
• Zaman serisi analizi
• Kestirim
• Ulaşım güvenliği

References

1. Oktopianto, Y., R. Rukman, and R.P. Marwanto, Improving traffic safety through a community participation approach, Jurnal Pengabdian Kepada Masyarakat Semangat Nyata Untuk Mengabdi (JKPM Senyum), 3(2), 125-130, (2023).
2. Deretić, N., et al., SARIMA modelling approach for forecasting of traffic accidents, Sustainability, 14(8), 4403, (2022).
3. Cai, B. and Q. Di, Different forecasting model comparison for near future crash prediction, Applied Sciences, 13(2), 759, (2023).
4. https://unece.org/sites/default/files/2021-01/UNRSF_who_we_are_Jan21%20%28002%29.pdf
5. Hokmabadi, R., et al., The role of high-risk behaviors, fatigue, and drowsiness in the occurrence of road accidents and near miss accidents among Tehran truck drivers in 2019, Journal of Occupational Health and Epidemiology, 10(4), 258-265, (2021).
6. Toroyan, T., M.M. Peden, and K. Iaych, WHO Launches second global status report on road safety, BMJ Publishing Group Ltd, (2013).
7. Najaf, P., et al., Evaluating traffic safety policies for developing countries based on equity considerations, Journal of Transportation Safety & Security, 9(sup1), 178-203, (2017).
8. Sohail, A., et al., Data-driven approaches for road safety: A comprehensive systematic literature review, Safety Science, 158, 105949, (2023).

9. Kaygisiz, Ö., M. Senbil, and A. Yildiz, Influence of urban built environment on traffic accidents: The case of Eskisehir (Turkey). Case Studies On Transport Policy, 5(2), 306-313, (2017).
10. Ihueze, C.C. and U.O. Onwurah, Road traffic accidents prediction modelling: An analysis of Anambra State, Nigeria, Accident Analysis & Prevention, 112, 21-29, (2018).
11. Jomnonkwao, S., S. Uttra, and V. Ratanavaraha, forecasting road traffic deaths in Thailand: Applications of time-series, curve estimation, multiple linear regression, and path analysis models, Sustainability, 12(1), 395, (2020).
12. Sumit, K., et al., An exploration of characteristics and time series forecast of fatal road crashes in Manipal, India. Sustainability, 14(5), 2851, (2022).
13. Twenefour, F., et al., Time series analysis of road traffic accidents in Ghana, Asian J Probab Stat, (2021).
14. Fassois, S. D., & Sakellariou, J. S. Time-series methods for fault detection and identification in vibrating structures. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 365(1851), 411-448, (2007).
15. Hansen, J. V., & Nelson, R. D. Neural networks and traditional time series methods: a synergistic combination in state economic forecasts. IEEE transactions on Neural Networks, 8(4), 863-873, (1997).
16. Cortez, P., Rio, M., Rocha, M., & Sousa, P. Multi‐scale Internet traffic forecasting using neural networks and time series methods. Expert Systems, 29(2), 143-155, (2012).
17. Amiri‐Simkooei, A. R., Tiberius, C. C., & Teunissen, P. J. Assessment of noise in GPS coordinate time series: methodology and results. Journal of Geophysical Research: Solid Earth, 112(B7), (2007).
18. Akın, M. and S. Eyduran, Zaman serisi analiz yöntemlerini kullanarak 2016-2025 dönemi Türkiye avokado üretiminin belirlenmesi, Yüzüncü Yıl Üniversitesi Tarım Bilimleri Dergisi, 27(2), 252-258, (2017).
19. Kınacı, H., M.G. Ünsal, and R. Kasap, A close look at 2019 novel coronavirus (COVID 19) infections in Turkey using time series analysis & efficiency analysis, Chaos, Solitons & Fractals, 143, 110583, (2021).
20. Gokkus, U., M. S. Yildirim and M. M. Aydin, Estimation of container traffic at seaports by using several soft computing methods: A case of Turkish Seaports, Discrete Dynamics in Nature and Society, 2984853, (2017).
21. Günel, A. Regresyon denkleminin baarısını ölçmede kullanılan belirleme katsayısı ve kritiği, Doğuş Üniversitesi Dergisi, 4(2), 133-140, (2003).
22. Kirca, M. M. Yapı seramiği endüstrisinde kusurlu üretim, ürün sınıflandırma ve verimlilik sürecinin Bayes ağları ile analizi (Master's thesis, Fen Bilimleri Enstitüsü).
23. Pektaş, Ali Osman, SPSS ile Veri Madenciliği, Dikeyeksen Yayınları, ISBN:978-605-86660-4-7, İstanbul, (2013).
24. Kristianssen, A. C., Andersson, R., Belin, M. Å., & Nilsen, P. Swedish Vision Zero policies for safety–A comparative policy content analysis, Safety science, 103, 260-269, (2018).
25. Belin, M. Å., Tillgren, P., & Vedung, E. Vision Zero–a road safety policy innovation, International journal of injury control and safety promotion, 19(2), 171-179, (2012).
26. Trafik Güvenliği Vizyonumuz, https://www.guvenlitrafik.gov.tr/3-trafik-guvenligivizyonumuz#:~:text=Trafik%20g%C3%BCvenli%C4%9Fi%20vizyonumuzun%20on%20y%C4%B1ll%C4%B1k,TRAF%C4%B0K%20S%C4%B0STEM%C4%B0N%C4%B0N%20VATANDA%C5%9ELARIMIZA%20SUNULMASI'd%C4%B1r .
27. https://unece.org/projects-2#