The Journal of The Korea Institute of Intelligent Transport Systems (한국ITS학회 논문지)

The Korea Institute of Intelligent Transport Systems (한국ITS학회)
권호 표지
DOI QR코드

DOI QR Code

Comparative Analysis of Traffic Accident Severity of Two-Wheeled Vehicles Using XGBoost

XGBoost를 활용한 이륜자동차 교통사고 심각도 비교분석

  • Kwon, Cheol woo (Department of Urban Convergence Engineering, Incheon National University) ;
  • Chang, Hyun ho (Urban Science Institute, College of Urban Science, Incheon National University)
  • 권철우 (인천대학교 도시융.복합학과) ;
  • 장현호 (인천대학교 도시과학연구원)
  • Received : 2021.06.08
  • Accepted : 2021.07.23
  • Published : 2021.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

Emergence of the COVID 19 pandemic has resulted in a sharp increase in the number of two-wheeler vehicular traffic accidents, prompting the introduction of numerous efforts for their prevention. This study applied XGBoost to determine the factors that affect severity of two-wheeled vehicular traffic accidents, by examining data collected over the past 10 years and analyzing the influence of each factor. Among the total factors assessed, variables affecting the severity of traffic accidents were overwhelmingly high in cases of signal violations, followed by the age group of drivers (60s or older), factors pertaining only to the car, and cases of centerline infringement. Based on the research results, a reasonable legal reform plan was proposed to prevent serious traffic accidents and strengthen safety management of two-wheeled vehicles. Based on the research results, we propose a reasonable legal reform plan to prevent serious traffic accidents and strengthen safety management of two-wheeled vehicles.

최근 코로나 19의 영향으로 이륜자동차 교통사고의 발생은 이전보다 급격히 증가하게 되었고 이륜자동차 사고방지를 위한 다각적인 노력이 필요한 시점이다. 본 연구에서는 XGBoost를 활용하여 최근 10년간 발생한 이륜자동차 교통사고 자료로 사고 심각도에 영향인자를 도출하여 각 영향인자가 주는 영향력을 분석하였다. 전체 변수 중 교통사고 심각도에 영향을 주는 변수는 신호 위반을 하였을 경우가 압도적으로 높았으며, 운전자 연령대가 60대 이상일 경우, 이륜자동차 단독사고일 경우, 중앙선 침범 사고일 경우 순으로 높은 것으로 나타났다. 연구 결과를 바탕으로 이륜자동차의 심각한 교통사고의 방지와 안전관리를 강화하기 위한 합리적인 제도 개편방안을 제시하였다.

Keywords

Acknowledgement

본 연구는 국토교통부 교통물류연구사업의 연구비지원(21TLRP-B148966-04)에 의해 수행되었습니다.

References

  1. Annie R. R., Srihari P. and Meena P.(2020), "Prediction of Road Accident Severity Using Machine Learning Algorithm," International Journal of Advanced Science and Technology, vol. 29, no. 6, pp.116-120.
  2. Chen T. and Carlos G.(2016), "XGBoost: A scalable tree boosting system," In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp.785-794.
  3. Chen T. and Guestrin C.(2016), "XGBoost: A scalable tree boosting system," In Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining. San Francisco, CA, USA, pp.785-794.
  4. Choi C. Y., Kim H. K., Kim Y. C. and Kim S. S.(2020), "Prediction of Track Quality Index (TQI) Using Vehicle Acceleration Data based on Machine Learning," Journal of Korean Geosynthetics Society, vol. 19, no. 1, pp.45-53.
  5. Han D. J., Kim E. C. and Ji M. K.(2020), "Analysis of Severity Factors in Personal Mobility (PM) Traffic Accidents," Journal of Korean Society of Transportation, vol. 38, no. 3, pp.232-247. https://doi.org/10.7470/jkst.2020.38.3.232
  6. Jessica P. N., Montserrat G. and Manuela A.(2019), "Predicting Motor Insurance Claims Using Telematics Data-XGBoost versus Logistic Regression," MDPI, vol. 7, no. 70, pp.1-16.
  7. Jun M., Yuexiong D., Jack C. P., Yi T., Vincent J. L. and JingCheng Z.(2019), "Analyzing the Leading Causes of Traffic Fatalities Using XGBoost and Grid-Based Analysis: A City Management Perspective," IEEE, vol. 7, pp.148062-148072.
  8. Kim T. H. and Park M. H.(2019), "Risk Factors Related to Accident Severity of Two-wheeled Vehicles Using Ordered Probit Model: A Case of Incheon Metropolitan City," International Journal of Highway Engineering, vol. 21, no. 2, pp.71-79. https://doi.org/10.7855/ijhe.2019.21.2.071
  9. Korea National Police Agency(2021), Traffic accident statistics.
  10. KOROAD(2016), Traffic accident characteristics of elderly drivers over the past 5 years.
  11. KOTI(2014), Legal System Improvement Plans for Accident Prevention and Safety Management of Motorcycle in Korea.
  12. KOTI(2020), KOTI Special Edition 05", pp.24-29.
  13. Lee Y. J. and Sun J. W.(2020), "Predicting Highway Concrete Pavement Damage using XGBoost," Journal of Construction Engineering and Management, vol. 21, no. 6, pp.46-55.
  14. MOLIT(2021), Total Registered Motor Vehicles.
  15. Mussone L., Bassani M. and Masci P.(2017), "Analysis of factors affecting the severity of crashes in urban road intersections," Accident Anal. Prevention, vol. 103, pp.112-122. https://doi.org/10.1016/j.aap.2017.04.007
  16. Na H. and Park B. H.(2012), "Analysis on the Accident Severity of Motorcycle Using Ordered Logit Model," Korea Planning Association, vol. 47, no. 4, pp.233-240.
  17. Park J. W. and Shin C. S.(2019), "A Study on Comparison of the Machine Learning Models for the Trip Distance Prediction of the Seoul Public Bike Sharing Service," Journal of Knowledge Information Technology and Systems, vol. 14, no. 2, pp.625-634. https://doi.org/10.34163/jkits.2019.14.6.005
  18. Park S. J., Kho S. Y. and Park H. C.(2019), "The Effects of Road Geometry on the Injury Severity of Expressway Traffic Accident Depending on Weather Conditions," Journal of the Korea Institute of Intelligent Transport Systems, vol. 18, no. 2, pp.12-28. https://doi.org/10.12815/kits.2019.18.2.12
  19. Yoon J. H. and Lee S. G.(2019), "Comparative Analysis of Factors Affecting the Severity of Pedestrian Crash by Daytime and Nighttime in Seoul, Korea," Journal of Korea Planning Association, vol. 54, no. 7, pp.70-88. https://doi.org/10.17208/jkpa.2019.12.54.7.70
  20. Zhang D., Qiu R. W., Deng Y., Ji D. and Li T.(2019), "Novel framework for image attribute annotation with gene selection XGBoost algorithm and relative attribute model," Appl. Soft Comput., vol. 80, pp.57-79. https://doi.org/10.1016/j.asoc.2019.03.017