Analysis of the severity of traffic accidents on the highway by age group of offered drivers using machine learning techniques

Minseo Cho; JaeSoon Choi

doi:10.22702/jkai.2024.14.2.22

All Issue

2024 Vol.14, Issue 2 Preview Page Next Page

Scientific Paper

Analysis of the severity of traffic accidents on the highway by age group of offered drivers using machine learning techniques 머신러닝기법을 이용한 가해운전자 연령대별 고속도로 내 교통사고 심각도 분석

31 December 2024. pp. 237-249

PDF XML

Abstract

Recently, due to aging in our country, not only the elderly population but also accidents caused by elderly drivers are increasing. To this end, various policies are being implemented, but research on analyzing factors affecting actual accidents involving elderly drivers is very lacking. Meanwhile, machine-learning and deep-learning technology, one of the AI technologies in all fields of engineering, has recently developed significantly, and research cases utilizing various data are rapidly increasing. Taking these points into consideration, this study aims to use machine-learning techniques to identify various factors that affect traffic accidents, including elderly drivers. For this purpose, accident data on 9 highway routes from 2014 to 2022 were collected and analyzed, and influence factors by age were derived. There are four machine-learning algorithms used in impact analysis: AdaBoost, XGBoost, Random Forest, and SVM. The algorithm most suitable for this analysis was selected through comparison of results. Also, we paid attention to recent climate change phenomena and conducted impact analysis under specific climate conditions.

Keywords

Traffic accident severity analysis

Machine-learning technology

Offending drivers

Age groups

Climate change

References

Kang, H.-S. and 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, 20(5), pp. 39-46.

Kim, S., Lym, Y. and Kim, K.J. (2021). "Classifying severity of senior driver accidents in capital regions based on machine learning algorithms", Journal of Digital Convergence, 19(4), pp. 25-31.

10.14400/JDC.2015.13.4.25

Korea Road Traffic Authority (KRTA) (2023). Traffic accident analysis system (TAAS). Retrieved November 15, 2024, from https://taas.koroad.or.kr/sta/acs/gus/selectAgeTfcacd.do?menuId=WEB_KMP_OVT_MVT_TAG_AGT

Lee, S.H. and Woo, Y.H. (2018). "A study on the improvement of prediction accuracy for traffic accident models using machine learning (Generalized Regression Neural Network)", International Journal of Highway Engineering, 20(6), pp.179-189.

10.7855/IJHE.2018.20.6.179

Son, S.O. and Park, J.Y. (2022). "Assessment of crash prediction models for intersections with severity weight parameters using data science approaches." Journal of Korean Society of Transportation, 40(2), pp. 190-204.

10.7470/jkst.2022.40.2.190

Kwon, C.W. and Chang, H.H. (2021). "Comparative analysis of traffic accident severity of two-wheeled vehicles using XGBoost", Journal of Korea Institute of Intelligent Transport Systems, 20(4), pp. 1-12.

10.12815/kits.2021.20.4.1

Information

Publisher :KOREAN ASPHALT INSTITUTE
Publisher(Ko) :한국아스팔트학회
Journal Title :Journal of the Korean Asphalt Institute
Journal Title(Ko) :한국아스팔트학회지
Volume : 14
No :2
Pages :237-249
Received Date : 2024-12-19
Revised Date : 2024-12-24
Accepted Date : 2024-12-31
DOI :https://doi.org/10.22702/jkai.2024.14.2.22

Journal of the Korean Asphalt Institute ISSN:2234-0785(Print) 2635-9553(Online) 한국아스팔트학회지

All Issue