A study on predictive models for identifying risk-areas to mitigate drunk driving accident damage

MinSeok Oh; JaeSoon Choi

doi:10.22702/jkai.2024.14.2.21

All Issue

2024 Vol.14, Issue 2 Preview Page Next Page

Scientific Paper

A study on predictive models for identifying risk-areas to mitigate drunk driving accident damage 음주사고 피해경감을 위한 음주사고취약지역 예측 모델에 관한 연구

31 December 2024. pp. 226-236

PDF XML

Abstract

This study aims to develop a predictive model for identifying risk areas to mitigate the damage caused by drunk driving accidents. Using drunk driving accident data from the TAAS database, the RandomForest algorithm was applied to estimate the probability of severe accidents for each autonomous district in Seoul. A risk map of Seoul’s districts was created based on the estimates. For High-Risk Areas, the importance of accident-related variables was analyzed to identify the underlying causes of accidents. The findings of this study are expected to contribute to identifying key risk factors of drunk driving accidents and devising effective measures for accident prevention. It is anticipated that further utilization of machine learning algorithms will enhance the model’s performance and provide more effective solutions for preventing severe accidents caused by drunk driving.

Keywords

Machine Learning

Drunk Driving

Severe Accidents

Accident Prediction

Risk Map

Variable Importance

References

Ibrahim, M.R., Haworth, J., Christie, N., Cheng, T. and Hailes, S. (2021). "Cycling Near Misses: A Review of the Current Methods, Challenges and the Potential of an AI-embedded System", Transport Reviews, 41(3), pp. 304-328.

10.1080/01441647.2020.1840456

Jun, H.J., Kang, S., Jung, S., Kim, T., Cho, C.H., Jhoo, W.Y., Kim, J.Y. and Heo, J.P. (2021). "A Deep Learning Approach to Predict Elderly and Child Pedestrian Crash Hot Spots in the Seoul Metropolitan Area", Journal of Korea Planning Association, 56(7), pp. 115-127.

10.17208/jkpa.2021.12.56.7.115

Kim, G.S. and Lee, B.H. (2019). "Prediction of DUI Risk Zone by Big Data Analysis Proceedings of KIIT Conference", Korean Institute of Information Technology, pp. 391-392.

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) (2024). Traffic Accident Analysis System (TAAS).

Korean Statistical Information Service (KOSIS) (2023a). Status of Licensed Drivers.

Korean Statistical Information Service (KOSIS) (2023b). Status of Registered Vehicles.

Kyoung, J. (2024). "A Study on the Efficiency Measures of the Prevention Policy for Drunk Driving - Focused on the Foreign Cases and Trigger Factors", Hanyang Law Association, 35(2), pp. 51-79.

10.35227/HYLR.2024.5.35.2.51

Lee, S.M., Yoon, B.H. and 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, 20(1), pp. 156-168.

Ogden, K.W. (1996). "Safer Roads: A Guide to Road Safety Engineering", Avebury Technical.

Seo, J. and Lee, S. (2016). "A Study on the Physical Environmental Factors Influencing Pedestrian Traffic Accidents in Seoul, Korea: Focused on the 2014 TAAS Data", Journal of Korea Planning Association, 51(3), pp. 197-216.

10.17208/jkpa.2016.06.51.3.197

Velog (2023). https://velog.io/@sykim0/%EB%A8%B8%EC%8B%A0%EB%9F%AC%EB%8B%9D-Random-Forest

Yoon, S.M., Oh, C., Park, H.J. and Chung, B.J. (2016). "Identification of Factors Affecting the Crash Severity and Safety Countermeasures Toward Safer Work Zone Traffic Management", Journal of Korean Society of Transportation, 34(4), pp. 354-372.

10.7470/jkst.2016.34.4.354

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 :226-236
Received Date : 2024-11-13
Revised Date : 2024-12-15
Accepted Date : 2024-12-31
DOI :https://doi.org/10.22702/jkai.2024.14.2.21

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

All Issue