Crash prediction based on traffic platoon characteristics using floating car trajectory data and the machine learning approach. (December 2019)

• Record Type: Journal Article
• Authors: Wang, Junhua; Luo, Tianyang; Fu, Ting
• Is Part Of: Accident analysis and prevention. Volume 133(2019)
• Publication Date: 2019-12
• Subjects: Urban expressway -- Floating car trajectory -- Traffic platoon -- Crash propensity prediction -- Binary logistic regression -- Support vector machine; Accidents -- Prevention -- Periodicals; Accident Prevention -- Periodicals; Accidents -- Prévention -- Périodiques; 363.106
• DOI: 10.1016/j.aap.2019.105320
• Languages: English
• ISSNs: 0001-4575

Abstract

Highlights: Wide-coverage and time-efficient traffic data for crash prediction is important. The traffic platoon the crash vehicle has been in may affect the crash outcome. The paper predicts crashes using platoon characteristics from floating car data. Both the binary logistic model and the support vector machine were applied. The support vector machine outperformed the binary logistic model in prediction. Abstract: Predicting crash propensity helps study safety on urban expressways in order to implement countermeasures and make improvements. It also helps identify and prevent crashes before they happen. However, collecting real-time wide-coverage traffic information for crash prediction has been challenging. More importantly, previous studies have failed to consider the characteristics of the traffic platoon (vehicle group) that the crash vehicle belongs to before the crash occurs. This paper aims to model crash propensity based on traffic platoon characteristics collected by the floating car method, which provides a time-efficient and reliable solution to collecting traffic information. Crash and floating car data are collected from the Middle Ring Expressway in Shanghai, China. Both the binary logistic model and the support vector machine are applied. A data preparation method, involving crash data filtering, floating car data filtering and data matching on the road network, is introduced for the safety analysis purpose. Results suggest that the traffic platoon information collected from floating cars accompanied works reasonably in predicting crashes on expressways. The support vector machine, with an overall accuracy of 85%, outperformed the binary logistic model which had an overall accuracy of 60%. Results further suggest the application of floating car technologies and the support vector machine in real-time crash prediction. Despite this, the study also concludes the merits of the binary logistic model over the support vector machine model in explaining the impact of different factors that contribute to crash occurrences.