A data-driven Bayesian network for probabilistic crash risk assessment of individual driver with traffic violation and crash records. (October 2022)

• Record Type: Journal Article
• Authors: Joo, Yang-Jun; Kho, Seung-Young; Kim, Dong-Kyu; Park, Ho-Chul
• Is Part Of: Accident analysis and prevention. Volume 176(2022)
• Publication Date: 2022-10
• Subjects: Crash risk assessment -- Bayesian network -- Probabilistic graphical model -- Traffic crash -- Traffic violation; Accidents -- Prevention -- Periodicals; Accident Prevention -- Periodicals; Accidents -- Prévention -- Périodiques; 363.106
• DOI: 10.1016/j.aap.2022.106790
• Languages: English
• ISSNs: 0001-4575

Abstract

Highlights: This study suggested a method for assessing the risk of a crash based on long-term, traceable data for large groups of drivers. Risk factors of drivers that affect future traffic violations and crashes were quantitatively identified based on the Bayesian network. This study described the application of the method for assessing a driver's risk and provided guidelines for the drivers' safety. Abstract: In recent years, individual drivers' crash risk assessments have received much attention for identifying high-risk drivers. To this end, we propose a probabilistic assessment method of crash risks with a reproducible long-term dataset (i.e., traffic violations, license, and crash records). In developing this method, we used 7.75 million violations and crashes of 5.5 million individual drivers in Seoul, South Korea, from June 2013 to June 2017 (four years). The stochastic process of the Bayesian network (BN), whose structure is optimized by tabu-search, successfully evaluates individual drivers' crash and violation probability. In addition, the cluster analysis classifies drivers into five distinctive groups according to their estimated violation and crash probabilities. As a result, this study found that the estimated average crash rate within a cluster converges with the actual crash rate by the proposed framework without privacy issues. We also confirm that violation records and expected crash probability are strongly correlated, and there is a direct relationship between a driver's previous violations and crash record and the future at-fault crash. The proposed assessment method is valuable in developing proactive driver education programs and safety countermeasures, including adjusting the penalty system and developing user-based insurance by recognizing dangerous drivers and identifying their properties.