Analysis of the Impact Factors of Peak and Non-peak Time Accident Severity Using XGBoost

doi:10.15683/kosdi.2024.6.30.440

All Issue

2024 Vol.20, Issue 2 Preview Page Next Page

Original Article

Analysis of the Impact Factors of Peak and Non-peak Time Accident Severity Using XGBoost XGBoost를 활용한 첨두, 비첨두시간 사고 심각도 영향요인 분석: 성제민¹ㆍ윤병조²*
Je Min Seong¹, Byoung Jo Yoon²*; ¹Researcher, College of Urban Science, Incheon National University, Incheon, Republic of Korea
²Professor, College of Urban Science, Incheon National University, Incheon, Republic of Korea

30 June 2024. pp. 440-447

PDF

Abstract

Purpose: The number of registered vehicles in Korea continues to increase. As traffic volume increases gradually due to improved quality of life, the severity of accidents is expected to increase and congestion problems are also expected. Therefore, it is necessary to analyze the accident factors of pointed traffic accidents and non-pointed traffic accidents. Method: The severity of the apical and non-pointed traffic accidents in Incheon Metropolitan City is analyzed by dividing them into apical and non-pointed traffic accidents to investigate the factors affecting the accident. XGBoost machine learning techniques were applied to analyze the severity of pointed and non-pointed traffic accidents and visualized as plot through the results. Result: It was analyzed that during non-peak hours, such as the case of the victim's vehicle type at peak times, the victim's vehicle type and construction machinery are variables that increase the severity of the accident. Conclusion: It is meaningful to derive the seriousness factors of apical and non-pointed accidents, and it is hoped that it will be used to reduce congestion costs by reducing the seriousness of accidents in the case of apical and non-pointed in the future.

Keywords

Machine Learning

XGBoost

Accident Severity

Variable Importance

Peak

Non-Peak

연구목적: 국내의 차량 등록 대수는 계속 증가하고 있다. 삶의 질 향상으로 인한 교통량 또한 점진적으로 증가하므로 사고 심각도가 증가 및 혼잡문제 또한 야기될 것으로 예상된다. 따라서, 첨두 교통사고와 비첨두 교통사고의 사고 요인을 분석할 필요가 있다고 판단된다. 연구방법: 인천광역시의 첨두 및 비첨두 교통사고의 심각도를 첨두와 비첨두로 나누어 분석하여 사고에 영향을 미치는 요인을 알아보고자 한다. XGBoost 머신러닝 기법을 적용하여 첨두 및 비첨두 교통사고 심각도를 분석하였으며 결과를 통하여 plot으로 시각화하였다. 연구결과: 첨두시 피해운전자 차종_승합인 경우 등 비 첨두시는 피해운전자 차종_건설기계 등이 사고 심각도를 높이게 되는 변수인 것으로 분석되었다. 결론: 첨두와 비첨두 사고 심각도의 요인을 도출한 것에 의의가 있고 추후 첨두 및 비첨두시의 사고 심각도를 낮추고 국내 교통의 혼잡 요인을 분석하여 혼잡 비용을 줄일 수 있는 것에 활용되기를 바란다.

키워드

머신러닝

XGBoost

사고심각도

변수중요도

첨두

비첨두

References

Chen, T, Calos, G. (2016). "XGBoost: A scalable tree boosting system." In Proceedings of the 22nd Acm Sigkdd International Conference on Knowledge Discovery and Data Mining, New York, US, pp. 785-794. 10.1145/2939672.2939785
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, J.-J., Lee, Y.-R., Lim, D.-H., Ahn, H.-C. (2021). "A Study on the Employee Turnover Prediction using XGBoost and SHAP." Journal of Information Systems, Vol. 30, No. 4, pp. 21-42.
Lee, J.-J., Lee, Y.-R., Lim, D.-H., Ahn, H.-C. (2021). "A study on the employee turnover prediction using XGBoost and SHAP." Korean Society for Information System, Vol. 30, No. 4, pp. 21-42.
Lee, Y.-J., Sun, J.-W. (2020). "Predicting highway concrete pavement damage using XGBoost." Journal of Construction Engineering and Management, Vol. 21, No. 6, pp. 46-55.
Lee, Y.-J., Sun, J.-W. (2020). "Predicting highway concrete pavement damage using XGBoost." Korean Journal of Construction Engineering and Management, Vol. 21, No. 6, pp. 46-55.
Sim, D.-C., Lee,J.-Y., Jang, J.-W., Lee, M.-W. (2022). "Prediction of chloride concentration in groundwater on Jeju Island using XGBoost regression machine learning." Journal of the Geological Society of Korea, Vol. 58, No. 2. 10.14770/jgsk.2022.58.2.243
Yoon, B.-J., Ko, E.-H, Yang, S.-R. (2016). "Comparative analysis on peak and non-peak hours traffic accident using logistic regression analysis." The Korean Society of Disaster Information Regular Academic Conferences and Special Seminars, Il San, Korea, pp. 283-284.
Yoon, B.-J., Lee, S.-M., Lwin, W.-Y. (2024). "Studying the comparative analysis of highway traffic accident severity using the random forest method." Journal of the Society of Disaster Information, Vol. 20, No. 1, pp. 156-168.
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, Vol. 2017, No. 11, pp. 251-252.
Yoon, J.-H., 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. 10.17208/jkpa.2019.12.54.7.70

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 :2
Pages :440-447
DOI :https://doi.org/10.15683/kosdi.2024.6.30.440

[1] Chen, T, Calos, G. (2016). "XGBoost: A scalable tree boosting system." In Proceedings of the 22nd Acm Sigkdd International Conference on Knowledge Discovery and Data Mining, New York, US, pp. 785-794. 10.1145/2939672.2939785

[2] 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

[3] Lee, J.-J., Lee, Y.-R., Lim, D.-H., Ahn, H.-C. (2021). "A Study on the Employee Turnover Prediction using XGBoost and SHAP." Journal of Information Systems, Vol. 30, No. 4, pp. 21-42.

[4] Lee, J.-J., Lee, Y.-R., Lim, D.-H., Ahn, H.-C. (2021). "A study on the employee turnover prediction using XGBoost and SHAP." Korean Society for Information System, Vol. 30, No. 4, pp. 21-42.

[5] Lee, Y.-J., Sun, J.-W. (2020). "Predicting highway concrete pavement damage using XGBoost." Journal of Construction Engineering and Management, Vol. 21, No. 6, pp. 46-55.

[6] Lee, Y.-J., Sun, J.-W. (2020). "Predicting highway concrete pavement damage using XGBoost." Korean Journal of Construction Engineering and Management, Vol. 21, No. 6, pp. 46-55.

[7] Sim, D.-C., Lee,J.-Y., Jang, J.-W., Lee, M.-W. (2022). "Prediction of chloride concentration in groundwater on Jeju Island using XGBoost regression machine learning." Journal of the Geological Society of Korea, Vol. 58, No. 2. 10.14770/jgsk.2022.58.2.243

[8] Yoon, B.-J., Ko, E.-H, Yang, S.-R. (2016). "Comparative analysis on peak and non-peak hours traffic accident using logistic regression analysis." The Korean Society of Disaster Information Regular Academic Conferences and Special Seminars, Il San, Korea, pp. 283-284.

[9] Yoon, B.-J., Lee, S.-M., Lwin, W.-Y. (2024). "Studying the comparative analysis of highway traffic accident severity using the random forest method." Journal of the Society of Disaster Information, Vol. 20, No. 1, pp. 156-168.

[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, Vol. 2017, No. 11, pp. 251-252.

[11] Yoon, J.-H., 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. 10.17208/jkpa.2019.12.54.7.70

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

All Issue