Journal of Korean Society of Industrial and Systems Engineering (산업경영시스템학회지)

Society of Korea Industrial and System Engineering (한국산업경영시스템학회)
권호 표지
DOI QR코드

DOI QR Code

Development of Traffic Accident Prediction Model Based on Traffic Node and Link Using XGBoost

XGBoost를 이용한 교통노드 및 교통링크 기반의 교통사고 예측모델 개발

  • Received : 2022.03.23
  • Accepted : 2022.05.06
  • Published : 2022.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

This study intends to present a traffic node-based and link-based accident prediction models using XGBoost which is very excellent in performance among machine learning models, and to develop those models with sustainability and scalability. Also, we intend to present those models which predict the number of annual traffic accidents based on road types, weather conditions, and traffic information using XGBoost. To this end, data sets were constructed by collecting and preprocessing traffic accident information, road information, weather information, and traffic information. The SHAP method was used to identify the variables affecting the number of traffic accidents. The five main variables of the traffic node-based accident prediction model were snow cover, precipitation, the number of entering lanes and connected links, and slow speed. Otherwise, those of the traffic link-based accident prediction model were snow cover, precipitation, the number of lanes, road length, and slow speed. As the evaluation results of those models, the RMSE values of those models were each 0.2035 and 0.2107. In this study, only data from Sejong City were used to our models, but ours can be applied to all regions where traffic nodes and links are constructed. Therefore, our prediction models can be extended to a wider range.

Keywords

Acknowledgement

This work is supported by VAIV Company Inc. which carried out the Sejong Technopark Foundation's 「Sejong Autonomous Driving Big Data Control Center Construction and Operation」 Project.

References

  1. Chen, T. and Guestrin, C., XGBoost: A Scalable Tree Boosting System, KDD'16, 2016, pp. 785-794.
  2. Cho, N.H., Jun, C.M., and Kang, Y.O., A visualization of traffic accidents hotspot along the road network, Journal of Cadastre & Land InformatiX, 2018, Vol.48, No.1, pp. 201-213. https://doi.org/10.22640/LXSIRI.2018.48.1.201
  3. Im, J.B., Development of Accident Frequency Estimation Models Using Random Parameter, University of Seoul, 2015.
  4. Jeong, Y.H. and Choi, Y.W., A study on the analysis of urban highways traffic accident's impact factors based on building discriminant models: Busan Metropolitan City, KSCE Journal of Civil and Environmental Engineering Research, 2014, Vol. 34, No. 4, pp. 1269-1278.
  5. Kang, Y.G., Traffic Accident Frequency Prediction Model in Urban Signalized Intersections with Intelligent Theories, University of Seoul, 2008.
  6. Kang, Y.O., Son, S.R., and Cho, N.H., Analysis of traffic accidents injury severity in seoul using decision trees and spatiotemporal data visualization, Journal of Cadastre & Land InformatiX, 2017, Vol. 47, No. 2, pp.233-254. https://doi.org/10.22640/LXSIRI.2017.47.2.223
  7. Korea Meteorological Agency Data Open Portal, http://data.kma.go.kr.
  8. Korea Ministry of Construction and Transportation, Plan Intersection Design Guidelines, 2004.
  9. Korea National Transport Information Center, http://its.go.kr.
  10. Korea Traffic Accident Analysis System, http://taas.koroad.or.kr.
  11. Korean National Police Agency, http:// police.go.kr.
  12. Lee, K.J., Jung, I.G,. Noh, Y.H., Yoon, S.G., and Cho, Y.S., The effect of road weather factors on traffic accident: Focused on Busan area, Journal of the Korean Data and Information Science Society, 2015, Vol. 26, No. 3, pp. 661-668. https://doi.org/10.7465/jkdi.2015.26.3.661
  13. Lee, S.H., Park, M.H., and Woo, Y.H., A study on developing crash prediction model for urban intersections considering random effects, The Journal of The Korea Institute of Intelligent Transport Systems, 2015, Vol.14, No.1, pp. 85-93. https://doi.org/10.12815/kits.2015.14.1.085
  14. Lundberg, S.M. and Lee, S.I., A Unified Approach to Interpreting Model Predictions, Advances in Neural Information Processing Systems, 2017, 30.
  15. Oh, H. U., Correlation between design consistency and accident rates based on standard deviations of highway design elements, International Journal of Highway Engineering, Vol.11, No.2, 2009, pp. 159-166.
  16. Park, M.H., Relationship between interstate highway accidents and heterogeneous geometrics by random parameter negative binomial model: A case of interstate highway in Washington State, USA, J. Korea Soc. of Civil Eng., 2013, Vol. 33, No. 6, pp. 2437-2445. https://doi.org/10.12652/Ksce.2013.33.6.2437
  17. Ryu, J.D., Development of Expressway Traffic Accident Prediction Model Using Deep Learning, University of Ajou, 2018.
  18. United States Geological Survey, https://earthexplorer.usgs.gov.