All Issue

2025 Vol.43, Issue 2 Preview Page

Article

Analyzing the Associations between the Fatal Accidents of Older Adult Drivers and Road Environments in Seoul, Korea: Focusing on Non-linear Relationships and Interaction Effects Using Machine Learning

서울시 고령 운전자의 중상 및 사망사고와 도로 환경의 연관성 분석: 기계학습을 활용한 비선형성과 상호작용 효과를 중심으로

Jeonghun MOON1
,
Jinjoo JANG1
,
Sugie LEE2*
문 정훈1
,
장 진주1
,
이 수기2*
1Master’s Degree, Department of Urban Planning and Engineering, Hanyang University, Seoul 04763, Korea
2Professor, Department of Urban Planning and Engineering, Hanyang University, Seoul 04763, Korea
1한양대학교 도시공학과 석사과정
2한양대학교 도시공학과 교수
*Corresponding Author
30 April 2025. pp. 161-180
PDF XML Citation
Abstract

This study analyzes traffic accident data from the TAAS (2017-2019) to examine non-linear relationships and interaction effects between road environmental factors and fatal accidents involving older adult drivers in Seoul. Machine learning-based tree ensemble algorithms and the SHAP method were used to provide insights integrating theoretical perspectives. The main findings are as follows: First, the XGBoost model performed best in predicting accidents for both older adult drivers and non-older adult drivers, with significant improvement observed for non-older adult drivers using the SMOTE technique. Second, for older adult drivers, road network characteristics and complex environments (intersection count, commercial facility density) were key factors, while non-older adult drivers showed more flexibility, reducing the importance of these factors. Green space proportion was found to lower accident probability for older adult drivers. Third, non-linear patterns were observed in variables such as Closeness, commercial facility density, and openness, with accident probability rising sharply beyond certain thresholds. Finally, interaction effects based on Attention Restoration Theory indicated that in areas with high commercial facility density or enclosed environments, an optimal green space ratio reduced accident probability. These results suggest that green spaces can enhance attention and reduce accidents for older adult drivers in complex environments. This study informs road environment design and traffic policy development to reduce older adult drivers accidents, highlighting the need for tailored safety strategies based on non-linear patterns and interactions.

Keywords
ensemble algorithms
fatal accidents
interaction effects
non-linear relationships
older adult drivers

본 연구는 2017년부터 2019년까지의 TAAS 교통사고 데이터를 활용하여 서울시 고령 운전자의 중상 및 사망사고 발생과 도로 환경적 요소 간의 비선형 관계 및 상호작용 효과를 탐구하였다. 이를 위해 기계학습 기반의 트리 앙상블 알고리즘과 SHAP 기법을 적용하고, 이론적 관점을 결합하여 심층적인 통찰을 도출하였다. 주요 연구 결과는 다음과 같다. 첫째, XGBoost 모형은 고령 및 비고령 운전자의 교통사고 예측에서 가장 우수한 성능을 보였으며, 특히 비고령 운전자의 예측에서는 SMOTE 기법을 활용한 성능 개선이 관찰되었다. 둘째, 고령 운전자의 사고 예측에서는 도로 네트워크의 구조적 특성과 복잡한 도로 환경(교차로 수, 상업시설 밀도)이 중요한 변수로 작용하는 반면, 비고령 운전자는 도로 환경에 더 유연하게 반응하여 해당 변수들의 중요도가 낮음을 확인하였다. 특히, 녹지 비율은 고령 운전자의 사고 확률을 저감시키는 중요한 요소로 나타났다. 셋째, SER 이론을 바탕으로 도로 환경과 사고 확률 간의 비선형 관계를 분석한 결과, Closeness, 상업시설 밀도, 개방감 등에서 비선형적 패턴이 발견되었으며, 특정 임계치를 초과할 경우 사고 확률이 급격히 증가하는 경향이 나타났다. 마지막으로, ART 이론을 기반으로 녹지 비율과 도로 환경 요소 간의 상호작용 효과를 분석한 결과, 상업시설 밀도가 높은 지역이나 폐쇄적인 도로 환경에서 적정 녹지 비율이 조성되면 사고 확률이 감소하는 경향을 보였다. 이러한 결과는 고령 운전자가 복잡한 도로 환경에서 자연적 요소인 녹지를 통해 주의 회복을 돕고, 사고를 예방할 수 있음을 시사한다. 본 연구는 고령 운전자의 사고를 줄이기 위한 도로 환경 설계 및 교통 관리 정책 수립에 유용한 정보를 제공하며, 특히 비선형적 사고 예측 패턴과 상호작용 효과 분석을 기반으로 한 맞춤형 교통 안전 전략의 필요성을 강조한다.

키워드
앙상블 알고리즘
중상 및 사망사고
상호작용 효과
비선형 관계
고령 운전자
References
1

Ahmed S., Hossain M. A., Ray S. K., Bhuiyan M. M. I., Sabuj S. R. (2023), A Study on Road Accident Prediction and Contributing Factors Using Explainable Machine Learning Models: Analysis and Performance, Transportation Research Interdisciplinary Perspectives, 19, 100814.

10.1016/j.trip.2023.100814
2

Ali Y., Haque M. M., Mannering F. (2023), Assessing Traffic Conflict/Crash Relationships with Extreme Value Theory: Recent Developments and Future Directions for Connected and Autonomous Vehicle and Highway Safety Research, Analytic Methods in Accident Research, 39, 100276.

10.1016/j.amar.2023.100276
3

Alshehri A. H., Alanazi F., Yosri A. M., Yasir M. (2024), Comparing Fatal Crash Risk Factors by Age and Crash Type by Using Machine Learning Techniques, PLoS One, 19(5), e0302171.

10.1371/journal.pone.030217138709785PMC11073736
4

Beck K. H., Daughters S. B., Ali B. (2013), Hurried Driving: Relationship to Distress Tolerance, Driver Anger, Aggressive and Risky Driving in College Students, Accident Analysis & Prevention, 51, 51-55.

10.1016/j.aap.2012.10.01223182783
5

Bélanger A., Gagnon S., Yamin S. (2010), Capturing the Serial Nature of Older Drivers' Responses towards Challenging Events: A Simulator Study, Accident Analysis & Prevention, 42(3), 809-817.

10.1016/j.aap.2009.07.01020380907
6

Chen T., Guestrin C. (2016), Xgboost: A Scalable Tree Boosting System, In Proceedings of the 22nd Acm Igkdd International Conference on Knowledge Discovery and Data Mining, 785-794.

10.1145/2939672.2939785
7

Cicchino J. B., McCartt A. T. (2015), Critical Older Driver Errors in A National Sample of Serious U.S. Crashes, Accident Analysis & Prevention, 80, 211-219.

10.1016/j.aap.2015.04.01525916662
8

Clarke D. D., Ward P., Bartle C., Truman W. (2010), Older Drivers' Road Traffic Crashes in the UK, Accident Analysis & Prevention, 42(4), 1018-1024.

10.1016/j.aap.2009.12.00520441808
9

Cleveland W. S. (1979), Robust Locally Weighted Regression And Smoothing Scatterplots. Journal of The American Statistical Association, 74(368), 829-836.

10.1080/01621459.1979.10481038
10

Day A. J., Brasher K., Bridger R. S. (2012), Accident Proneness Revisited: The Role of Psychological Stress and Cognitive Failure, Accident Analysis & Prevention, 49, 532-535.

10.1016/j.aap.2012.03.02823036431
11

Fu R., Guo Y., Yuan W., Feng H., Ma Y. (2011), The Correlation Between Gradients of Descending Roads and Accident Rates, Safety Science, 49(3), 416-423.

10.1016/j.ssci.2010.10.006
12

Guo A. W., Brake J. F., Edwards S. J., Blythe P. T., Fairchild R. G. (2010), The Application of In-Vehicle Systems for Elderly Drivers, European Transport Research Review, 2, 165-174.

10.1007/s12544-010-0037-y
13

Hadayeghi A., Shalaby A. S., Persaud B. (2003), Macrolevel Accident Prediction Models for Evaluating Safety of Urban Transportation Systems, Transportation Research Record, 1840(1), 87-95..

10.3141/1840-10
14

Han S. S., Park B. H. (2011), Comparative Analysis of Traffic Accident Severity Based on the Ordered Logit Model in the Case of Cheongju, Journal of Korea Planning Association, 46(2), 183-192.

15

Harvey C., Aultman-Hall L. (2015), Urban Streetscape Design and Crash Severity, Transportation Research Record, 2500(1), 1-8.

10.3141/2500-01
16

Kim K. H., Moon J. H., Hong J. Y. (2022), Analysis of Crash Probability for Hazardous Materials Transportation Using A Logistic Regression Model, Korean Journal of Hazardous Materials, 10(1), 7-16.

10.31333/kihm.2022.10.1.7
17

Kim S., Lee S. (2023), Nonlinear Relationships and Interaction Effects of An Urban Environment on Crime Incidence: Application of Urban Big Data and An Interpretable Machine Learning Method, Sustainable Cities and Society, 91, 104419.

10.1016/j.scs.2023.104419
18

Kweon J., Lee S. (2024), Analysis of Influencing Factors of Unauthorized  Electric Kickboard Parking by Type in Seoul, Korea. Journal of Korea Planning Association, 59(2), 104-120.

10.17208/jkpa.2024.04.59.2.104
19

Lee J., Gim T. H. (2019), Examining the Characteristics of Traffic Accidents Involving Elderly Drivers in Seoul, South Korea. The Korea Spatial Planning Review, 102, 19-34.

10.15793/kspr.2019.102..002
20

Lee S. Y., Han S. J., Chung Y. S. (2020), Injury Severity of Freeway Crashes in Rainy Weather Using Ordered Probit Model, Journal of Transport Research, 27(1), 1-11.

21

Lim S. J., Park J. T., Kim Y. I., Kim T. H. (2012), Analysis of Elderly Drivers' Accident Models Considering Operations and Physical Characteristics, J. Korean Soc. Transp., 30(6), Korean Society of Transportation, 37-46.

10.7470/jkst.2012.30.6.037
22

Nassiri H., Mohammadpour S. I., Dahaghin M. (2023), Forecasting Time Trends of Fatal Motor Vehicle Crashes in Iran Using An Ensemble Learning Algorithm, Traffic Injury Prevention, 24(1), 44-49.

10.1080/15389588.2022.213027936278888
23

Oh J. S., Lee E. Y., Ryu J. B., Lee W. Y. (2015), An Analysis for Main Vulnerable Situations and Human Errors of Elderly Drivers' Traffic Accidents, Journal of Transport Research, 22(4), 57-75.

10.34143/jtr.2015.22.4.57
24

Park C., Lee S. (2016), An Analysis of the Characteristics of Street Environment Affecting Pedestrian Accidents- Applications of Street Segment Analysis Unit and Spatial Statistics. Journal of the Urban Design Institute of Korea, 17(3), 105-121.

25

Park E., Lee S. (2024), Analysis of Spatial Distribution Characteristics and Influencing Factors of the Origin and Destination of Consumer Logistics in Seoul, Korea. Journal of Korea Planning Association, 59(3), 148-165.

10.17208/jkpa.2024.06.59.3.148
26

Park J. I., Kim S., Kim J. K. (2023), Exploring Spatial Associations Between Near-Miss and Police-Reported Crashes: The Heinrich's Law in Traffic Safety, Transportation Research Interdisciplinary Perspectives, 19, 100830.

10.1016/j.trip.2023.100830
27

Park J. S. (2023), Analysis of The Visual Characteristics of Street Scenery Affecting Car Traffic Accidents in Seoul, Korea: Using Street View Panorama Image and Computer Vision Techniques, Master's Thesis, Hanyang University.

28

Prokhorenkova L., Gusev G., Vorobev A., Dorogush A. V., Gulin A. (2018), CatBoost: Unbiased Boosting with Categorical Features, Advances in Neural Information Processing Systems, 31.

29

Pulugurtha S. S., Duddu V. R., Kotagiri Y. (2013), Traffic Analysis Zone Level Crash Estimation Models Based on Land Use Characteristics, Accident Analysis & Prevention, 50, 678-687.

10.1016/j.aap.2012.06.01622785088
30

Rhee K. A., Kim J. K., Lee Y. I., Ulfarsson G. F. (2016), Spatial Regression Analysis of Traffic Crashes in Seoul. Accident Analysis & Prevention, 91, 190-199.

10.1016/j.aap.2016.02.02326994374
31

Shapley L. S. (1953), Stochastic Games, Proceedings of the National Academy of Sciences, 39(10), 1095-1100.

10.1073/pnas.39.10.1953
32

TAAS, (2023), Traffic Accient Analysis System (TAAS)(http://taas.rota.or.kr)

33

Theeuwes J. (2021), Self-Explaining Roads: What Does Visual Cognition Tell Us About Designing Safer Roads?, Cognitive Research: Principles And Implications, 6(1), 15.

10.1186/s41235-021-00281-633661408PMC8030273
34

Wada Y., Asami Y., Hino K., Nishi H., Shiode S., & Shiode N. (2023). Road Junction Configurations And The Severity of Traffic Accidents in Japan, Sustainability, 15(3), 2722.

10.3390/su15032722
35

Wen X., Xie Y., Wu L., Jiang L. (2021), Quantifying and Comparing the Effects of Key Risk Factors on Various Types of Roadway Segment Crashes with LightGBM and SHAP, Accident Analysis & Prevention, 159, 106261.

10.1016/j.aap.2021.10626134182322
36

Xiao L., Lo S., Liu J., Zhou J., Li Q. (2021), Nonlinear and Synergistic Effects of TOD on Urban Vibrancy: Applying Local Explanations for Gradient Boosting Decision Tree, Sustainable Cities and Society, 103063, 1-16.

10.1016/j.scs.2021.103063
37

Yan R., Hu L., Li J., Lin N. (2024), Accident Severity Analysis of Traffic Accident Hot Spot Areas in Changsha City Considering Built Environment. Sustainability, 16(7), 3054.

10.3390/su16073054
38

Yang C., Chen M., Yuan Q. (2021), The Application of XGBoost and SHAP to Examining the Factors in Freight Truck-Related Crashes: An Exploratory Analysis, Accident Analysis & Prevention, 158, 106153.

10.1016/j.aap.2021.10615334034073
39

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

10.7470/jkst.2016.34.4.354
40

Yuan Y., Chen X., Wang J. (2020), Object-Contextual Representations for Semantic Segmentation, European Conference on Computer Vision, 173-190.

10.1007/978-3-030-58539-6_11
41

Yue H. (2024), Investigating the Influence of Streetscape Environmental Characteristics on Pedestrian Crashes at Intersections Using Street View Images and Explainable Machine Learning, Accident Analysis & Prevention, 205, 107693.

10.1016/j.aap.2024.10769338955107
Information
  • Publisher :Korean Society of Transportation
  • Publisher(Ko) :대한교통학회
  • Journal Title :Journal of Korean Society of Transportation
  • Journal Title(Ko) :대한교통학회지
  • Volume : 43
  • No :2
  • Pages :161-180
  • Received Date : 2024-10-22
  • Revised Date : 2024-11-20
  • Accepted Date : 2025-02-03
  • DOI :https://doi.org/10.7470/jkst.2025.43.2.161
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