Studying the Comparative Analysis of Highway Traffic Accident Severity Using the Random Forest Method

doi:10.15683/kosdi.2024.3.31.156

All Issue

2024 Vol.20, Issue 1 Preview Page Next Page

Original Article

Studying the Comparative Analysis of Highway Traffic Accident Severity Using the Random Forest Method Random Forest를 활용한 고속도로 교통사고 심각도 비교분석에 관한 연구: 이선민¹ㆍ윤병조²*ㆍ웃위린³
Sun-min Lee¹, Byoung-Jo Yoon²*, WutYeeLwin³; ¹Researcher, College of Urban Science, Incheon National University, Incheon, Republic of Korea
²Professor, College of Urban Science, Incheon National University, Incheon, Republic of Korea
³Researcher, College of Urban Science, Incheon National University, Incheon, Republic of Korea

31 March 2024. pp. 156-168

PDF

Abstract

Purpose: The trend of highway traffic accidents shows a repeating pattern of increase and decrease, with the fatality rate being highest on highways among all road types. Therefore, there is a need to establish improvement measures that reflect the situation within the country. Method: We conducted accident severity analysis using Random Forest on data from accidents occurring on 10 specific routes with high accident rates among national highways from 2019 to 2021. Factors influencing accident severity were identified. Result: The analysis, conducted using the SHAP package to determine the top 10 variable importance, revealed that among highway traffic accidents, the variables with a significant impact on accident severity are the age of the perpetrator being between 20 and less than 39 years, the time period being daytime (06:00-18:00), occurrence on weekends (Sat-Sun), seasons being summer and winter, violation of traffic regulations (failure to comply with safe driving), road type being a tunnel, geometric structure having a high number of lanes and a high speed limit. We identified a total of 10 independent variables that showed a positive correlation with highway traffic accident severity. Conclusion: As accidents on highways occur due to the complex interaction of various factors, predicting accidents poses significant challenges. However, utilizing the results obtained from this study, there is a need for in-depth analysis of the factors influencing the severity of highway traffic accidents. Efforts should be made to establish efficient and rational response measures based on the findings of this research.

Keywords

Highway

Traffic Accidents

Accident Severity

Machine Learning

Random Forest

Feature Importance

연구목적: 고속도로 교통사고의 추세는 증감을 반복하며 도로 종류 중 고속도로에서의 치사율은 최고치를 나타내고 있다. 따라서 국내 실정을 반영한 개선대책 수립이 필요하다. 연구방법: Random Forest를 활용해 2019년부터 2021년까지 전국 고속도로 노선 중 사고 다발 10개 노선에서 발생한 교통사고 자료로 사고 심각도 분석 및 사고 심각도에 미치는 영향요인을 도출하였다. 연구결과: SHAP 패키지를 활용해 상위 10개의 변수 중요도를 분석한 결과, 고속도로 교통사고 중 사고 심각도에 높은 영향을 미치는 변수는 가해자 연령이 20세 이상 39세 미만, 시간대가 주간(06:00-18:00), 주말(토~일), 계절이 여름과 겨울, 법규위반이 안전운전불이행, 도로 형태가 터널, 기하구조상 차로 수가 많고 제한속도가 높은 경우로 총 10개의 독립변수에서 고속도로 교통사고 심각도와 양(+)의 상관관계를 가지는 것으로 분석되었다. 결론: 고속도로에서의 사고 발생은 매우 다양한 요인의 복합적인 작용으로 인해 발생하므로 사고 예측에 많은 어려움이 있지만 본 연구로 도출된 결과를 활용해 고속도로 교통사고 심각도에 영향을 주는 요인을 심층적으로 분석해 효율적이고 합리적인 대응책 수립을 위한 노력이 필요하다.

키워드

고속도로

교통사고

사고 심각도

머신러닝

랜덤 포레스트

변수 중요도

References

Almamlook, R.E., Kwayu, K.M., Alkasisbeh, M.R., Frefer, A.A. (2019). "Comparison of machine learning algorithms for predicting traffic accident severity." IEEE Jordan International Joing Conference on Electrical Engineering and Information Technology(JEEIT), Amman, Jordan, pp. 272-276. 10.1109/JEEIT.2019.8717393
Breiman, L. (2001). "Random forests." Machine Learning, Vol. 45, pp. 5-32. 10.1023/A:1010933404324
Kang, H.-S., Noh, M.-G. (2022). "Classifying the severity of pedestrian accidents using ensemble machine learning algorithms: A case study of Daejeon City." The Society of Digital Policy & Management, Vol. 20, No. 5, pp. 39-46.
Kim, S.-H., Lym, Y.-B., Kim, K.-J. (2021). "Classifying severity of senior driver accidents in capital regions based on machine learning algorithms." The Society of Digital Policy & Management, Vol.19, No. 4, pp. 25-31.
Korea National Police Agency (2021). Traffic Accident Statistics. Seoul.
Kwon, C.-W., Chang, H.-H. (2021). "Comparative analysis of traffic accident severity of tow-wheeled vehicles using XGBoost." Journal of Information Technology Services, Vol. 20, No. 4, pp.1-12. 10.12815/kits.2021.20.4.1
Lee, G.-H., Rho, J.-H. (2015). "A development of traffic accident model by random parameter: Focus on capital area and Busan 4-legs signalized intersections." The Journal of The Korea Institute of Intelligent Transport Systems, Vol. 14, No. 6, pp. 91-99. 10.12815/kits.2015.14.6.091
Lee, J.-E., Kim, Y.-B., Kim, J.-N. (2020). "Hyperparameter optimization for image classification in convolutional neural network." The Journal of Korea Institute of Convergence Signal Processing, Vol. 21, No. 3, pp. 148-153.
Park, J.-S. (2011). "Severity analysis of the vehicle-pedestrian crashes at signalized intersection." Regional Policy Review, Vol. 22, No. 1, pp. 1-12.
Yoon, B.-J., Lee, S.-Y., Jung, S.-Y. (2017). "A study on the factors of highway traffic accidents affecting the EPDO." The Korean Society of Disaster Information, Goyang, pp.251-252.

Information

Publisher :The Korean Society of Disaster Information
Publisher(Ko) :한국재난정보학회
Journal Title :Journal of the Society of Disaster Information
Journal Title(Ko) :한국재난정보학회논문집
Volume : 20
No :1
Pages :156-168
DOI :https://doi.org/10.15683/kosdi.2024.3.31.156

[1] Almamlook, R.E., Kwayu, K.M., Alkasisbeh, M.R., Frefer, A.A. (2019). "Comparison of machine learning algorithms for predicting traffic accident severity." IEEE Jordan International Joing Conference on Electrical Engineering and Information Technology(JEEIT), Amman, Jordan, pp. 272-276. 10.1109/JEEIT.2019.8717393

[2] Breiman, L. (2001). "Random forests." Machine Learning, Vol. 45, pp. 5-32. 10.1023/A:1010933404324

[3] Kang, H.-S., Noh, M.-G. (2022). "Classifying the severity of pedestrian accidents using ensemble machine learning algorithms: A case study of Daejeon City." The Society of Digital Policy & Management, Vol. 20, No. 5, pp. 39-46.

[4] Kim, S.-H., Lym, Y.-B., Kim, K.-J. (2021). "Classifying severity of senior driver accidents in capital regions based on machine learning algorithms." The Society of Digital Policy & Management, Vol.19, No. 4, pp. 25-31.

[5] Korea National Police Agency (2021). Traffic Accident Statistics. Seoul.

[6] Kwon, C.-W., Chang, H.-H. (2021). "Comparative analysis of traffic accident severity of tow-wheeled vehicles using XGBoost." Journal of Information Technology Services, Vol. 20, No. 4, pp.1-12. 10.12815/kits.2021.20.4.1

[7] Lee, G.-H., Rho, J.-H. (2015). "A development of traffic accident model by random parameter: Focus on capital area and Busan 4-legs signalized intersections." The Journal of The Korea Institute of Intelligent Transport Systems, Vol. 14, No. 6, pp. 91-99. 10.12815/kits.2015.14.6.091

[8] Lee, J.-E., Kim, Y.-B., Kim, J.-N. (2020). "Hyperparameter optimization for image classification in convolutional neural network." The Journal of Korea Institute of Convergence Signal Processing, Vol. 21, No. 3, pp. 148-153.

[9] Park, J.-S. (2011). "Severity analysis of the vehicle-pedestrian crashes at signalized intersection." Regional Policy Review, Vol. 22, No. 1, pp. 1-12.

[10] Yoon, B.-J., Lee, S.-Y., Jung, S.-Y. (2017). "A study on the factors of highway traffic accidents affecting the EPDO." The Korean Society of Disaster Information, Goyang, pp.251-252.

Journal of the Society of Disaster Information ISSN:1976-2208(Print) 2671-5287(Online) 한국재난정보학회논문집

All Issue