All Issue

2025 Vol.43, Issue 4 Preview Page

Article

Identifying Factors Affecting Injury Severity on Right-Turn Accidents at Signalized Intersections Using Machine Learning

머신러닝을 활용한 신호교차로 우회전 사고심각도 영향 요인 분석

Yongsik YOU1
,
Jeonghun YANG2
,
Taehyuk CHOI3
,
Tai-jin SONG4*
유 용식1
,
양 정훈2
,
최 태혁3
,
송 태진4*
1Ph.d Course, Department of Urban Engineering, Chungbuk National University, Cheongju 28644, Korea
2Deputy General Manager, Traffic Accident Analysis Center, Road Traffic Authority, Wonju 26466, Korea
3Undergraduate Student, Department of Urban Engineering, Chungbuk National University, Cheongju 28644, Korea
4Associate Professor, Department of Urban Engineering, Chungbuk National University, Cheongju 28644, Korea
1충북대학교 도시공학과 석박사통합과정
2한국도로교통공단 교통사고종합분석센터 차장
3충북대학교 도시공학과 학부과정
4충북대학교 도시공학과 부교수
*Corresponding Author
31 August 2025. pp. 438-450
PDF XML Citation
Abstract

The government has recently recognized the injury severity on right-turn accidents in the country and has made significant efforts to mitigate related damages, including revising relevant laws and regulations. This study aims to identify the factors affecting the injury severity on right-turn accidents, initiated by the pressing social issue and the lack of prior research in this area. For this study, data covering 253 right-turn accidents over a six-year period (2018–2023) from 25 high-frequency right-turn accident locations nationwide, as reported in press releases, were collected. Based on this data, a total of 23 variables were constructed for each individual accident. Using the constructed dataset, the factors influencing accident severity were analyzed using the Random Forest model, a widely used approach in machine learning classification, and the Binary Logistic Regression model. The advantage of using a random forest model to select important variables and logistic regression to calculate the size of the effect is that you can consider both the performance and the explanatory power of the model. This study identified seven statistically significant factors (p < 0.05): the age group of the pedestrian victim (human-related), the type of offending vehicle (vehicle-related), and five road-traffic-related factors, speed limit, dedicated right-turn lane, the presence of raised crosswalks, the distance between the stop line and the crosswalk, and the right-turn curve radius. The findings of this study are expected to assist policymakers and practitioners in formulating effective measures to substantially reduce right-turn accidents.

Keywords
accident severity
random forest
right-turn traffic accidents
signalized intersection accidents
traffic accident black spot

최근 정부는 국내 우회전 교통사고의 심각성을 인지하여 관련된 법제도를 정비하는 등 우회전 사고에 따른 피해 저감을 위해 많은 노력을 기울이고 있다. 본 연구는 이와 같은 사회적 배경, 그리고 관련된 선행연구의 부재에 따라 우회전 사고심각도의 영향 요인들을 찾고자 하였다. 연구를 위해 보도자료에서 발표된 전국의 우회전 사고다발지 25개에 대한 최근 6년(2018-2023)간의 우회전 사고자료 253건이 수집되었다. 이를 토대로 총 23개의 변수를 개별 사고별로 구축하였다. 구축된 자료를 가지고 기계학습 분류모형에서 대표적으로 활용되는 랜덤포레스트 모형과 이항 로지스틱 회귀모형으로 사고심각도 요인을 분석하였다. 두가지 모델을 같이 사용하는 방법은 모델의 성능과 설명력을 모두 고려할 수 있다는 장점이 있다. 연구 결과, 총 7개의 요인(인적 측면에 해당되는 피해 보행자 연령층, 차량 측면에 해당되는 가해 차량의 차종, 도로교통 측면에 해당되는 접근로 제한속도, 우회전 전용차로 유무, 고원식 횡단보도 유무, 정지선-횡단보도 간격, 우회전 곡선반경)이 통계적으로 유의(p < 0.05)한 것으로 나타났다. 연구 결과는 정책 결정권자 및 실무자로 하여금 국내 우회전 사고에 대한 실질적 감소대책 마련에 도움이 될 것으로 기대된다. 향후에는 우회전 교통사고 다발교차로와 미발생 교차로간 비교 연구가 필요하며, 운전자 행태자료가 결합된 연구 또한 필요할 것으로 판단된다.

키워드
사고심각도
랜덤포레스트
우회전 교통사고
신호교차로 사고
교통사고 다발지
References
1

AlMamlook R. E., Kwayu K. M., Alkasisbeh M. R., Frefer A. A. (2019), Comparison of Machine Learning Algorithms for Predicting Traffic Accident Severity, 2019 IEEE Jordan International Joint Conference on Electrical Engineering and Information Technology (JEEIT), 272-276.

10.1109/JEEIT.2019.8717393
2

Awasthi S. (2020), Random Forests in Machine Learning: A Detailed Explanation, datamahadev.com.

3

Breiman L. (2001), Random forests, Machine learning, 45, 5-32.

10.1023/A:1010933404324
4

Gi H. S., Kim E. C. (2023), A Study on the Influence of Triangular Islands on Intersection Traffic Crashes: Focusing on Incheon Metropolitan City, J. Korean Soc. Transp., 41(1), Korean Society of Transportation, 119-134.

10.7470/jkst.2023.41.1.119
5

Kang H., Noh M. (2022), Classifying the Severity of Pedestrian Accidents Using Ensemble Machine Learning Algorithms: A Case Study of Daejeon City, Journal of Digital Convergence, 20(5), 39-46.

10.14400/JDC.2022.20.5.039
6

Khattak M. W., Pirdavani A., De Winne P., Brijs T., De Backer H. (2021), Estimation of Safety Performance Functions for Urban Intersections Using Various Functional Forms of the Negative Binomial Regression Model and a Generalized Poisson Regression Model, Accident Analysis & Prevention, 151, 105964.

10.1016/j.aap.2020.105964
7

Kidando E., Kitali A. E., Kutela B., Karaer A., Ghorbanzadeh M., Koloushani M., Ozguven E. E. (2022), Use of Real-time Traffic and Signal Timing Data in Modeling Occupant Injury Severity at Signalized Intersections, Transportation Research Record, 2676(2), 825-839.

10.1177/03611981211047836
8

Kim S., Lym Y., Kim K. J. (2021), Classifying Severity of Senior Driver Accidents In Capital Regions Based on Machine Learning Algorithms, Journal of Digital Convergence, 19(4), 25-31.

10.14400/JDC.2021.19.4.025
9

KoRoAD (Korea Road Traffic Authority) (2022), Press release, https://www.koroad.or.kr/main/board/6/7437/board_view.do?&cp=21&listType=list&bdOpenYn=Y&bdNoticeYn=N, 2022.02.17.

10

Lee J. E., Kim Y. B., Kim J. N. (2020), Hyperparameter Optimization for Image Classification in Convolutional Neural Network, Journal of the Institute of Convergence Signal Processing, 21(3), 148-153.

11

Lee K. Y., Kim Y. S. (2021), Predictive Model for the Employment Retention of Persons with Disabilities, Journal of Special Education, 37(2), 73-95.

10.31863/JSE.2021.05.37.2.73
12

Lee S. M., Yoon B. J. (2024), Studying the Comparative Analysis of Highway Traffic Accident Severity Using the Random Forest Method, Journal of the Society of Disaster Information, 20(1), 156-168.

10.15683/KOSDI.2024.3.31.156
13

Lee S., Yoon B. J., Wut 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), 156-168.

10.15683/KOSDI.2024.3.31.156
14

Mitra S., Bhowmick D. (2020), Status of Signalized Intersection Safety-A Case Study of Kolkata, Accident Analysis & Prevention, 141, 105525.

10.1016/j.aap.2020.105525
15

National Police Agency (2023), Traffic Pavement Marking Installation and Operation manual.

16

Sandri M., Zoccolotto P. (2010), Analysis and Correction of Bias in Total Decrease in Node Impurity Measures for Tree-based Algorithms, Statistics and Computing, 20(4), 393-407.

10.1007/s11222-009-9132-0
17

Sharafeldin M., Farid A., Ksaibati K. (2022), Injury Severity Analysis of Rear-end Crashes at Signalized Intersections, Sustainability 14(21), 13858.

10.3390/su142113858
18

Vajari M. A., Aghabayk K., Sadeghian M., Shiwakoti N. (2020), A Multinomial Logit Model of Motorcycle Crash Severity at Australian intersections, Journal of safety research, 73, 17-24.

10.1016/j.jsr.2020.02.008
19

Wang J., Ma S., Jiao P., Ji L., Sun X., Lu H. (2023), Analyzing the Risk Factors of Traffic Accident Severity Using a Combination of Random Forest and Association Rules, Applied Sciences, 13(14), 8559.

10.3390/app13148559
20

Yan M., Shen Y. (2022), Traffic Accident Severity Prediction Based on Random Forest, Sustainability, 14(3), 1729.

10.3390/su14031729
21

Yang J. H., Park J. S., Rim H. S., Kim K. H., Song T. J. (2024), Identifying Factors Affecting the Severity of Rear-End Crashes at Signalized Intersection Approaches Using Machine Learning Technologies, J. Korean Soc. Transp., 42(2), Korean Society of Transportation, 212-230.

10.7470/jkst.2024.42.2.212
22

Yassin S. S., Pooja (2020), Road Accident Prediction and Model Interpretation Using a Hybrid K-means and Random Forest Algorithm Approach, SN Applied Sciences, 2(9), 1576.

10.1007/s42452-020-3125-1
23

Yoo J. E. (2015), Random Forests, an Alternative Data Mining Technique to Decision Tree, Journal of Education Evaluation, 28(2), 427-448.

24

Yuan R., Gu X., Peng Z., Xiang Q. (2023), Analysis of Factors Affecting Occupant Injury Severity in Rear-end Crashes by Different Struck Vehicle Groups: A Random Thresholds Random Parameters Hierarchical Ordered Probit Model, Journal of Transportation Safety and Security, 15(6), 636-657.

10.1080/19439962.2022.2098891
Information
  • Publisher :Korean Society of Transportation
  • Publisher(Ko) :대한교통학회
  • Journal Title :Journal of Korean Society of Transportation
  • Journal Title(Ko) :대한교통학회지
  • Volume : 43
  • No :4
  • Pages :438-450
  • Received Date : 2024-12-31
  • Revised Date : 2025-02-06
  • Accepted Date : 2025-04-08
  • DOI :https://doi.org/10.7470/jkst.2025.43.4.438
Journal Informaiton Journal of Korean Society of Transportation Journal of Korean Society of Transportation
Archives
: 2015 Vol.34~
  • NRF
  • KOFST
  • crossref cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close