All Issue

2024 Vol.42, Issue 3 Preview Page

Article

Multi-Stage Machine Learning Approach to Assess Crash Risk Using Vehicle Maneuver Data

차량 주행궤적 데이터를 활용한 Multi-Stage 머신러닝 기반의 사고 위험 예측 연구

Nuri PARK1
,
Juneyoung PARK2*
박 누리1
,
박 준영2*
1Ph.D. Student, Department of Smart City Engineering, Hanyang University, Ansan 1558, Korea
2Associate Professor, Department of Transportation & Logistics Engineering/Smart City Engineering, Hanyang University, Ansan 15588, Korea
1한양대학교 스마트시티공학과 박사과정
2한양대학교 교통·물류공학과/스마트시티공학과 부교수
*Corresponding Author
30 June 2024. pp. 331-347
PDF XML Citation
Abstract

The selection of indicators that can catch the risky traffic flow is important to predict crash risk on highways. Unsupervised machine learning techniques can be a new approach to deriving important crash risk indicators. This paper applies a multi-stage methodology using both unsupervised and supervised machine learning techniques systematically to evaluate crash risks. The proposed multi-stage methodology is composed of three stages. In the first stage, select variables that can classify risky and general traffic flow well using K-means clustering and Random forest. The second stage is the combination of variables that were derived in the first stage to construct important variable sets for detecting crash precursors. Lastly, third stage, crash prediction models with variable sets, which are selected from the second step, were developed using the support vector machine method. For the real-time crash prediction model, individual vehicle trajectory data were collected from commercial vehicles and used. As a result of this study, the multi-stage models that include variable selection through a combination of K-means clustering and Random Forest methods improved the predictive performance. This study proposes a new approach to selecting important variables that cannot be found by supervised learning when developing a crash prediction model. It is expected that more crashes can be prevented by performing proactive traffic safety management using the methodology suggested in this study.

Keywords
crash precursor
crash risk
machine learning
multi-stage model
safety indicators

교통사고 발생 예방과 대응을 위하여 실시간으로 사고위험 상황을 예측하고 적절한 조처를 하는 방안에 관한 연구가 진행되고 있다. 교통사고는 매우 드물게 발생하는 무작위 이벤트이기 때문에 실시간 사고 위험 예측에서 사고 발생 징후를 포착하고 위험한 교통류 특성을 명확히 구분할 수 있는 안전 지표를 선택하는 것이 중요하다. 본 연구에서는 머신러닝 기법 중 비지도 학습과 지도학습 방법론을 동시에 활용하여 중요도 높은 핵심 안전 지표를 선별하였으며, 선정된 안전 지표를 활용해 사고위험 예측모형을 개발하는 Multi-stage process의 사고 위험 예측 모형 개발 절차를 제안하였다. 첫 번째 단계에서는 K-means Clustering과 Random Forest 방법론을 사용하여 사고위험 교통류와 일반 교통류를 잘 분류할 수 있는 변수를 선별하였으며, 두 번째 단계에서는 첫 번째 단계에서 도출된 핵심 변수의 조합을 마련하였다. 마지막으로 세 번째 단계에서는 이진 분류에 많이 사용되는 머신러닝 기법인 Support Vector Machine 모형을 사용해 변수 조합별 사고 위험 예측 모형을 개발하고, 예측 성능을 비교하였다. 이를 통해 본 연구에서는 사고위험 예측모형에 독립변수로 활용되는 안전 지표를 선별할 때 비지도 학습 및 지도 학습 기반 핵심 변수 선별 방법론의 효과를 측정하였다. 또한, 본 연구에서는 실시간으로 변화하는 차량의 위험 주행행태 포착을 위해 상업용 차량의 Digital Tachograph(DTG)에서 수집되는 주행궤적 데이터를 사용하였다. 연구 결과, 본 연구에서 제안한 Multi-stage 기반 사고 위험 예측 모형 개발 방식은 모형의 예측 성능을 개선하는 것으로 나타났으며, 핵심 변수 선별에 지도학습만으로는 도출되지 않는 새로운 중요한 변수를 고려할 수 있는 것으로 나타났다. 본 연구에서 제안된 방법론을 사용하여 선제적 교통안전 관리 전략을 마련할 수 있으며, 이를 통해 교통사고를 예방하고, 교통안전 관리 전략을 통해 사전에 대응할 수 있을 것으로 기대한다.

키워드
사고 발생 징후
사고위험
머신러닝
multi-stage 모형
안전 지표
References
1

Abdel-Aty M. A., Hassan H. M., Ahmed M., Al-Ghamdi A. S. (2012), Real-time Prediction of Visibility Related Crashes, Transportation Research Part C: Emerging Technologies, 24, 288-298.

10.1016/j.trc.2012.04.001
2

Abdel-Aty M., Pande A. (2005), Identifying Crash Propensity using Specific Traffic Speed Conditions, Journal of Safety Research, 36(1), 97-108.

10.1016/j.jsr.2004.11.00215752487
3

Abdel-Aty M., Pande A., Das A., Knibbe W. J. (2008), Assessing Safety on Dutch Freeways with Data from Infrastructure-based Intelligent Transportation Systems, Transportation Research Record, 2083(1), 153-161.

10.3141/2083-18
4

Abdel-Aty M., Uddin N., Pande A. (2005), Split Models for Predicting Multivehicle Crashes during High-speed and Low-speed Operating Conditions on Freeways, Transportation Research Record, 1908(1), 51-58.

10.1177/0361198105190800107
5

Abdel-Aty M., Uddin N., Pande A., Abdalla M. F., Hsia L. (2004), Predicting Freeway Crashes from Loop Detector Data by Matched Case-control Logistic Regression, Transportation Research Record, 1897(1), 88-95.

10.3141/1897-12
6

Abou Elassad Z. E., Mousannif H., Al Moatassime H. (2020), A Real-time Crash Prediction Fusion Framework: An Imbalance-aware Strategy for Collision Avoidance Systems, Transportation Research Part C: Emerging Technologies, 118, 102708.

10.1016/j.trc.2020.102708
7

Ahmed M., Abdel-Aty M. (2013), A Data Fusion Framework for Real-time Risk Assessment on Freeways, Transportation Research Part C: Emerging Technologies, 26, 203-213.

10.1016/j.trc.2012.09.002
8

Assi K., Rahman S. M., Mansoor U., Ratrout N. (2020), Predicting Crash Injury Severity with Machine Learning Algorithm Synergized with Clustering Technique: A Promising Protocol, International Journal of Environmental Research and Public Health, 17(15), 5497.

10.3390/ijerph1715549732751470PMC7432564
9

Bagdadi O., Várhelyi A. (2013), Development of a Method for Detecting Jerks in Safety Critical Events, Accident Analysis & Prevention, 50, 83-91.

10.1016/j.aap.2012.03.03223200443
10

Basso F., Basso L. J., Bravo F., Pezoa R. (2018), Real-time Crash Prediction in an Urban Expressway using Disaggregated Data, Transportation Research Part C: Emerging Technologies, 86, 202-219.

10.1016/j.trc.2017.11.014
11

Basso F., Pezoa R., Varas M., Villalobos M. (2021), A Deep Learning Approach for Real-time Crash Prediction using Vehicle-by-vehicle Data, Accident Analysis & Prevention, 162, 106409.

10.1016/j.aap.2021.10640934600313
12

Boser B. E., Guyon I. M., Vapnik V. N. (1992), A Training Algorithm for Optimal Margin Classifiers, In Proceedings of the Fifth Annual Workshop on Computational Learning Theory, 144-152.

10.1145/130385.130401
13

Breiman L. (2001), Random Forests, Machine Learning, 45, 5-32.

10.1023/A:1010933404324
14

Cai Q., Abdel-Aty M., Yuan J., Lee J., Wu Y. (2020), Real-time Crash Prediction on Expressways using Deep Generative Models, Transportation Research Part C: Emerging Technologies, 117, 102697.

10.1016/j.trc.2020.102697
15

Cheng Z., Yuan J., Yu B., Lu J., Zhao Y. (2022), Crash Risks Evaluation of Urban Expressways: A Case Study in Shanghai, IEEE Transactions on Intelligent Transportation Systems, 23(9), 15329-15339.

10.1109/TITS.2022.3140345
16

Chevalier A. et al. (2017), Predictors of Older Drivers' Involvement in Rapid Deceleration Events, Accident Analysis & Prevention, 98, 312-319.

10.1016/j.aap.2016.10.01027810673
17

Cui M. (2020), Introduction to the K-means Clustering Algorithm Based on the Elbow Method, Accounting, Auditing and Finance, 1(1), 5-8.

18

Dias C., Miska M., Kuwahara M., Warita H. (2009), Relationship between Congestion and Traffic Accidents on Expressways: An Investigation with Bayesian Belief Networks, In Proceedings of 40th Annual Meeting of Infrastructure Planning (JSCE).

19

Dingus, T. A. et al. (2006), The 100-car Naturalistic Driving Study, Phase Ii-results of the 100-car Field Experiment, United States, Department of Transportation, National Highway Traffic Safety Administration, No. DOT-HS- 810-593.

10.1037/e624282011-001
20

Feng F., Bao S., Sayer J. R., Flannagan C., Manser M., Wunderlich R. (2017), Can Vehicle Longitudinal Jerk be used to Identify Aggressive Drivers? An Examination using Naturalistic Driving Data, Accident Analysis & Prevention, 104, 125-136.

10.1016/j.aap.2017.04.01228499141
21

Formosa N., Quddus M., Ison S., Abdel-Aty M., Yuan J. (2020), Predicting Real-time Traffic Conflicts using Deep Learning, Accident Analysis & Prevention, 136, 105429.

10.1016/j.aap.2019.10542931931409
22

Hossain M., Muromachi Y. (2012), A Bayesian Network Based Framework for Real-time Crash Prediction on the Basic Freeway Segments of Urban Expressways, Accident Analysis & Prevention, 45, 373-381.

10.1016/j.aap.2011.08.00422269521
23

Huang T., Wang S., Sharma A. (2020), Highway Crash Detection and Risk Estimation using Deep Learning, Accident Analysis & Prevention, 135, 105392.

10.1016/j.aap.2019.10539231841865
24

Huang Z., Gao Z., Yu R., Wang X., Yang K. (2017), Utilizing Latent Class Logit Model to Predict Crash Risk, In 2017 IEEE/ACIS 16th International Conference on Computer and Information Science (ICIS), 161-165, IEEE.

10.1109/ICIS.2017.7959987
25

Kamrani M., Arvin R., Khattak A. J. (2018), Extracting Useful Information from Basic Safety Message Data: An Empirical Study of Driving Volatility Measures and Crash Frequency at Intersections, Transportation Research Record, 2672(38), 290-301.

10.1177/0361198118773869
26

Kim Y., Oh C., Choe B., Choi S., Kim K. (2018), Development of a Methodology for Detecting Intentional Aggressive Driving Events using Multi-agent Driving Simulations, J. Korean Soc. Transp., 36(1), Korean Society of Transportation, 51-65.

10.7470/jkst.2018.36.1.051
27

Kim Y., Park J., Oh C. (2021), A Crash Prediction Method Based on Artificial Intelligence Techniques and Driving Behavior Event Data, Sustainability, 13(11), 6102.

10.3390/su13116102
28

Lei T., Peng J., Liu X., Luo Q. (2021), Crash Prediction on Expressway Incorporating Traffic Flow Continuity Parameters Based on Machine Learning Approach, Journal of Advanced Transportation, 8820402.

10.1155/2021/8820402
29

Li P., Abdel-Aty M. (2022), A Hybrid Machine Learning Model for Predicting Real-time Secondary Crash Likelihood, Accident Analysis & Prevention, 165, 106504.

10.1016/j.aap.2021.10650434844080
30

Lin L., Wang Q., Sadek A. W. (2015), A Novel Variable Selection Method Based on Frequent Pattern Tree for Real-time Traffic Accident Risk Prediction, Transportation Research Part C: Emerging Technologies, 55, 444-459.

10.1016/j.trc.2015.03.015
31

MacQueen J. (1967, June), Some Methods for Classification and Analysis of Multivariate Observations, In Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, 1(14), 281-297.

32

Mohamed M. G., Saunier N., Miranda-Moreno L. F., Ukkusuri S. V. (2013), A Clustering Regression Approach: A Comprehensive Injury Severity Analysis of Pedestrian-vehicle Crashes in New York, US and Montreal, Canada, Safety science, 54, 27-37.

10.1016/j.ssci.2012.11.001
33

Oh C., Oh J. S., Ritchie S. G. (2005), Real-time Hazardous Traffic Condition Warning System: Framework and Evaluation, IEEE Transactions on Intelligent Transportation Systems, 6(3), 265-272.

10.1109/TITS.2005.853693
34

Park S., Son S. O., Park J., Oh C., Hong S. (2021), Using Vehicle Data as a Surrogate for Highway accident Data, In Proceedings of the Institution of Civil Engineers-Municipal Engineer, 174(2), 67-74, Thomas Telford Ltd.

10.1680/jmuen.20.00012
35

Shi Q., Abdel-Aty M. (2015), Big Data Applications in Real-time Traffic Operation and Safety Monitoring and Improvement on Urban Expressways, Transportation Research Part C: Emerging Technologies, 58, 380-394.

10.1016/j.trc.2015.02.022
36

Wang L., Abdel-Aty M., Lee J., Shi Q. (2019), Analysis of Real-time Crash Risk for Expressway Ramps using Traffic, Geometric, Trip Generation, and Socio-demographic Predictors, Accident Analysis & Prevention, 122, 378-384.

10.1016/j.aap.2017.06.00328689932
37

Wang L., Abdel-Aty M., Shi Q., Park J. (2015), Real-time Crash Prediction for Expressway Weaving Segments, Transportation Research Part C: Emerging Technologies, 61, 1-10.

10.1016/j.trc.2015.10.008
38

World Health Organization (2019), Global Status Report on Road Safety 2018, World Health Organization.

39

Wu M., Shan D., Wang Z., Sun X., Liu J., Sun M. (2019), A Bayesian Network Model for Real-time Crash Prediction Based on Selected Variables by Random Forest, In 2019 5th International Conference on Transportation Information and Safety (ICTIS), 670-677, IEEE.

10.1109/ICTIS.2019.8883694
40

Wu Y., Abdel-Aty, M., Cai, Q., Lee, J., Park, J. (2018), Developing an Algorithm to Assess the Rear-end Collision Risk under Fog Conditions using Real-time Data, Transportation Research Part C: Emerging Technologies, 87, 11-25.

10.1016/j.trc.2017.12.012
41

Xia Y., Qin Y., Li X., Xie J. (2022), Risk Identification and Conflict Prediction from Videos Based on TTC-ML of a Multi-lane Weaving Area, Sustainability, 14(8), 4620.

10.3390/su14084620
42

Xu C., Wang W., Liu P., Guo R., Li Z. (2014), Using the Bayesian Updating Approach to Improve the Spatial and Temporal Transferability of Real-time Crash Risk Prediction Models, Transportation Research Part C: Emerging Technologies, 38, 167-176.

10.1016/j.trc.2013.11.020
43

Yang K., Wang X., Yu R. (2018), A Bayesian Dynamic Updating Approach for Urban Expressway Real-time Crash Risk Evaluation, Transportation Research Part C: Emerging Technologies, 96, 192-207.

10.1016/j.trc.2018.09.020
44

You J., Wang J., Guo J. (2017), Real-time Crash Prediction on Freeways using Data Mining and Emerging Techniques, Journal of Modern Transportation, 25(2), 116-123.

10.1007/s40534-017-0129-7
45

Yu R., Abdel-Aty M. (2013), Utilizing Support Vector Machine in Real-time Crash Risk Evaluation, Accident Analysis & Prevention, 51, 252-259.

10.1016/j.aap.2012.11.02723287112
46

Yuan Z., He K., Yang Y. (2022), A Roadway Safety Sustainable Approach: Modeling for Real-time Traffic Crash with Limited Data and Its Reliability Verification, Journal of Advanced Transportation, 1570521.

10.1155/2022/1570521
47

Zhai B., Lu J., Wang Y., Wu B. (2020), Real-time Prediction of Crash Risk on Freeways under Fog Conditions, International Journal of Transportation Science and Technology, 9(4), 287-298.

10.1016/j.ijtst.2020.02.001
Information
  • Publisher :Korean Society of Transportation
  • Publisher(Ko) :대한교통학회
  • Journal Title :Journal of Korean Society of Transportation
  • Journal Title(Ko) :대한교통학회지
  • Volume : 42
  • No :3
  • Pages :331-347
  • Received Date : 2024-04-19
  • Revised Date : 2024-05-08
  • Accepted Date : 2024-06-10
  • DOI :https://doi.org/10.7470/jkst.2024.42.3.331
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