Driving Behavior Risk Measurement and Cluster Analysis Driven by Vehicle Trajectory Data
Source abstract
Abstract
The correct identification and timely pre-warning of driving behavior risks can remind drivers to correct their unsafe driving behaviors effectively. First of all, four risk evaluation indicators of driving behavior were defined based on lateral and longitudinal driving characteristics: the lateral stability indicator, the longitudinal stability indicator, the car-following risk indicator, and the lane-changing risk indicator. The Pearson correlation coefficient method was used to analyze the correlation of the four indicators, and the conclusion showed that the four indicators were very weakly correlated or presented an irrelevant correlation. Thus, the four indicators can describe different driving behavior risks. Secondly, the criteria importance through intercriteria correlation (CRITIC) method was used to determine the weight of each indicator, and a comprehensive measurement model of driving behavior risk was established. To test the model, this study preprocessed the trajectory data of small vehicles in Lanes 1–5 of the I-80 Expressway from the NGSIM dataset, collected statistical analysis results of vehicle speed and acceleration, and obtained the parameters data required for risk assessment. Then, based on the obtained trajectory data, the variation laws and the thresholds of the four indicators were determined by using the interquartile difference method. Finally, by using the K-means clustering algorithm, the risk types of driving behavior were divided into four categories, namely, dangerous, aggressive, safe, and conservative. The dangerous, aggressive, safe, and conservative driving behaviors accounted for 5.40%, 23.30%, 43.22%, and 28.08% of the total samples, respectively. The expert’s assessment results of the driving behavior risk aligned with the results obtained from the model measurements. This indicated that the driving behavior risk measurement model here described can evaluate a driver’s risk status in real time, provide safety tips for the driver, and offer theoretical support for driving safety warning systems.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Traffic and Road Safety · Autonomous Vehicle Technology and Safety · Traffic control and management
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Mechanical and Electrical Engineering, Guangzhou University, Guangzhou 510006, China
School of Civil Engineering, Guangzhou University, Guangzhou 510006, China
Guangdong Communication Planning & Design Institute Group Co., Ltd., Guangzhou 510507, China
References (43)
Show source-provided references
1. Real-Time Detection System of Driver Distraction Using Machine Learning10.1109/TITS.2013.2247760 ↗
2. Enhancing Driver Distraction Recognition Using Generative Adversarial Networks10.1109/TIV.2019.2960930 ↗
3. Research on risky driving behavior evaluation model based on CIDAS real data10.1177/0954407020985972 ↗
4. A study of freeway crash risk prediction and interpretation based on risky driving behavior and traffic flow data10.1016/j.aap.2021.106328 ↗
5. Ucar, S., Patnayak, C., Oza, P., Hoh, B., and Oguchi, K. (2019, January 4–6). Management of anomalous driving behavior. Proceedings of the 2019 IEEE Vehicular Networking Conference, Los Angeles, CA, USA.10.1109/VNC48660.2019.9062814 ↗
6. Analyzing driver behavior under naturalistic driving conditions: A review10.1016/j.aap.2020.105908 ↗
7. The mediating effect of driver characteristics on risky driving behaviors moderated by gender, and the classification model of driver’s driving risk10.1016/j.aap.2021.106038 ↗
8. Personality and professional drivers’ driving behavior10.1016/j.trf.2018.10.017 ↗
9. Chandra, R., Bhattacharya, U., Mittal, T., Bera, A., and Manocha, D. (2020, January 25–29). Cmetric: A driving behavior measure using centrality functions. Proceedings of the 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Las Vegas, NV, USA.10.1109/IROS45743.2020.9341720 ↗
10. Wang, L., Zhou, N., and Kang, Z.H. (2021, January 5–7). An unsupervised driving behavior pattern recognition algorithm based on clustering and LDA model. Proceedings of the 2nd International Conference on Artificial Intelligence and Computer Engineering, Hangzhou, China.10.1109/ICAICE54393.2021.00061 ↗
11. The relation between self-reported driving style and driving behaviour. A simulator study10.1016/j.trf.2018.04.017 ↗
12. Jiang, R., Zhu, S., Chang, H., Wu, J., Ding, N., Liu, B., and Qiu, J. (2021). Determining an Improved Traffic Conflict Indicator for Highway Safety Estimation Based on Vehicle Trajectory Data. Sustainability, 13.10.3390/su13169278 ↗
13. Development of a lane change risk indicator using vehicle trajectory data10.1016/j.aap.2017.10.015 ↗
14. Classification and Evaluation of Driving Behavior Safety Levels: A Driving Simulation Study10.1109/OJITS.2022.3149474 ↗
15. Matousek, M., Yassin, M., van der Heijden, R., and Kargl, F. (2018, January 3–6). Robust detection of anomalous driving behavior. Proceedings of the IEEE Vehicular Technology Conference, Porto, Portugal.10.1109/VTCSpring.2018.8417777 ↗
16. Collin, A., Bilka, A., Pendleton, S., and Tebbens, R.D. (November, January 19). Safety of the intended driving behavior using rulebooks. Proceedings of the IEEE Intelligent Vehicles Symposium (IV), Las Vegas, NV, USA.
17. Prediction of dangerous driving behavior based on vehicle motion state and passenger feeling using Cloud Model and Elman Neural Network10.3389/fnbot.2021.641007 ↗
18. Qiao, X., Zheng, L., Li, Y., Ren, Y., Zhang, Z., Zhang, Z., and Qiu, L. (2021). Characterization of the Driving Style by State–Action Semantic Plane Based on the Bayesian Nonparametric Approach. Appl. Sci., 11.10.3390/app11177857 ↗
19. Geng, X., Liang, H., Yu, B., Zhao, P., He, L., and Huang, R. (2017). A Scenario-Adaptive Driving Behavior Prediction Approach to Urban Autonomous Driving. Appl. Sci., 7.10.3390/app7040426 ↗
20. Abdi, H. (2010). Encyclopedia of Research Design, Sage.
21. Monitoring the coefficient of variation: A literature review10.1016/j.cie.2021.107600 ↗
22. Ding, R., Pan, C., Dai, Z., and Xu, J. (2022). Lateral Oscillation Characteristics of Vehicle Trajectories on the Straight Sections of Freeways. Appl. Sci., 12.10.3390/app122211498 ↗
23. Analysis of the transition condition of rear-end collisions using time-to-collision index and vehicle trajectory data10.1016/j.aap.2020.105676 ↗
24. Risk perception and the warning strategy based on safety potential field theory10.1016/j.aap.2020.105805 ↗
25. Application of proximal surrogate indicators for safety evaluation: A review of recent developments and research needs10.1016/j.iatssr.2017.02.001 ↗
26. Wang, K., Xue, Q., and Lu, J.J. (2021). Risky driver recognition with class imbalance data and automated machine learning framework. Int. J. Environ. Res. Public Health, 18.10.3390/ijerph18147534 ↗
27. Test for significance of Pearson’s correlation coefficient
28. Self-delayed feedback car-following control with the velocity uncertainty of preceding vehicles on gradient roads10.1007/s11071-021-06970-7 ↗
29. Cooperative car following control with electronic throttle and perceived headway errors on gyroidal roads10.1016/j.apm.2022.04.010 ↗
30. Analytic posteriors for Pearson’s correlation coefficient10.1111/stan.12111 ↗
31. Performance evaluation of the GIS-based data mining techniques of best-first decision tree, random forest, and naive Bayes tree for landslide susceptibility modeling10.1016/j.scitotenv.2018.06.389 ↗
32. Comparison of the percentile estimation method and mixture (maximum likelihood and least square) method for estimating parameters of Johnson bounded distribution
33. Chen, S., Xue, Q., Zhao, X., Xing, Y., and Lu, J.J. (2021). Risky driving behavior recognition based on vehicle trajectory. Int. J. Environ. Res. Public Health, 18.10.3390/ijerph182312373 ↗
34. Laurikkala, J., Juhola, M., Kentala, E., Lavrac, N., Miksch, S., and Kavsek, B. (2000, January 20–25). Informal identification of outliers in medical data. Proceedings of the Fifth International Workshop on Intelligent Data Analysis in Medicine and Pharmacology, Berlin, Germany.
35. Investigating the impact of data normalization on classification performance10.1016/j.asoc.2019.105524 ↗
36. Urban rail transit operation safety evaluation based on an improved CRITIC method and cloud model
37. Krishnan, A.R., Kasim, M.M., Hamid, R., and Ghazali, M.F. (2021). A modified CRITIC method to estimate the objective weights of decision criteria. Symmetry, 13.10.3390/sym13060973 ↗
38. The new combination with CRITIC and WASPAS methods for the time and attendance software selection problem10.1007/s12597-019-00371-6 ↗
39. Research on K-value selection method of K-means clustering algorithm
40. How much can k-means be improved by using better initialization and repeats?10.1016/j.patcog.2019.04.014 ↗
41. A continuum model considering the uncertain velocity of preceding vehicles on gradient highways10.1016/j.physa.2021.126561 ↗
42. Na, S., Xumin, L., and Yong, G. (2010, January 2–4). Research on k-means clustering algorithm: An improved k-means clustering algorithm. Proceedings of the 2010 Third International Symposium on Intelligent Information Technology and Security Informatics, Jian, China.10.1109/IITSI.2010.74 ↗
43. The mystery of the Z-score10.12945/j.aorta.2016.16.014 ↗