Abstract
This study explores the relationship between driver age and traffic risk factors through cluster analysis to support targeted traffic safety education. Based on expressway accident data collected in Xianyang, Shaanxi Province, from 2021 to 2023, the K-means++ algorithm was used to identify the risk tendencies of different driver groups. The results show that the optimal number of clusters is three. Group 1 includes young and elderly drivers and is more likely to be involved in casualty accidents, mainly related to rear-end collisions and following operation errors. Group 2 includes young and middle-aged drivers with lower casualty risk but a stronger tendency toward violations, mainly involving oblique and rear-end collisions, as well as steering and following operation errors. Group 3 also consists of young and middle-aged drivers and has the largest number of accidents, with relatively high proportions of rear-end, frontal, and side collisions. Overall, the following operation errors are the key risk factors, suggesting the need for both educational and technological interventions.
References
[1] Kong L-Z. Analysis of Human Factors in Causes of Traffic Accidents. Chin. J. Saf. Sci. 2013;23(1):28.
[2] Bucsuházy K, Matuchová E, Zůvala R, et al. Human factors contributing to the road traffic accident occurrence. Transp. Res. Procedia. 2020;45:555-561.
[3] Petridou E, Moustaki M. Human factors in the causation of road traffic crashes. Eur. J. Epidemiol. 2000;16:819-826.
[4] Prasolenko O, Lobashov O, Galkin A. The human factor in road traffic city. Int. J. Autom. Control Intell. Syst. 2015;1(3):77-84.
[5] Noy YI. Human factors in modern traffic systems. Ergonomics. 1997;40(10):1016-1024.
[6] Zhang Y, Jing L, Sun C, et al. Human factors related to major road traffic accidents in China. Traffic Inj. Prev. 2019;20(8):796-800.
[7] Fang Y-R. Experimental Study on Differences in Driving Behavior Characteristics of Different Categories of Drivers. Saf. Environ. Eng. 2020;27(5):204-208.
doi:10.13578/j.cnki.issn.1671-1556.2020.05.030.
[8] Cai X-Y, Tian X-Y, Weng J, et al. Visibility of Small Targets under Highway Tunnel Lighting Considering Driver Age. Sci. Technol. Eng. 2023;23(8):3396-3402.
[9] Guan M-Q, Gong Q-N. Analysis of Accident Tendency of Engineering Vehicle Drivers Based on Grey Clustering Method. Highway. 2017;62(11):177-182.
[10] Kim HS, Yoon DS, Shin HS, et al. Driving characteristics analysis of young and middle-aged drivers. In: Proc. Int. Conf. Inf. Commun. Technol. Converg. (ICTC). IEEE; 2016:864-867.
[11] Scott-Parker B, De Regt T, Jones C, et al. The situation awareness of young drivers, middle-aged drivers, and older drivers: Same but different? Case Stud. Transp. Policy. 2020;8(1):206-214.
[12] Ulak MB, Ozguven EE, Spainhour L. Age-based stratification of drivers to evaluate the effects of age on crash involvement. Transp. Res. Procedia. 2017;22:551-560.
[13] Hu L, Bao X, Wu H, et al. A study on correlation of traffic accident tendency with driver characters using in-depth traffic accident data. J. Adv. Transp. 2020;2020:9084245.
[14] Li H-R, Peng L-Q, Wu C-Z, et al. Traffic Accident Analysis on Long Downhill Sections for Heavy Freight Vehicles Based on Cluster Analysis. Sci. Technol. Rev. 2016;34(2):71-75.
[15] Zhou Y-E, Gong H-F, Zhao C-X, et al. Speed–Density Model for Logistics Applicable in Mountainous Cities. Sci. Technol. Eng. 2021;21(4):1624-1628.
[16] Liu S-X, Su D-L, Chi G-D, et al. Running Risk Assessment at Freeway Weaving Sections Based on Driving Simulation Experiments. Sci. Technol. Eng. 2021;21(2):751-757.
How to cite this paper
Research on the Relationship Between Driver Age and Traffic Risk Factors Based on K-means++ Clustering
How to cite this paper: Rongfang Zhang, Yufei Ma, Jingsheng Chen, Zihao He. (2026). Research on the Relationship Between Driver Age and Traffic Risk Factors Based on K-means++ Clustering. Engineering Advances, 6(1), 55-60.
DOI: http://dx.doi.org/10.26855/ea.2026.03.012