A paper titled “Impact of real-time traffic characteristics on crash occurrence: The case of rare events” authored by Athanasios Theofilatos, George Yannis, Pantelis Kopelias and Fanis Papadimitriou is now published in Accident Analysis and Prevention Journal. This paper investigates crash likelihood by utilizing real-time traffic data from three random loop detectors in the Attica Tollway located in Greater Athens Area in Greece and by proposing a framework driven by appropriate statistical models (Bias Correction and Firth method) in order to overcome the problems that arise when the number of crashes is very low. Under this approach instead of using traditional logistic regression methods, crashes are considered as rare events. The method and findings of the study provide insights on the mechanism of crash occurrence and also revealed that lower speeds are more likely to result in accident.
Impact of real-time traffic characteristics on crash occurrence: The case of rare events, 2018
Related Posts
-
Unfolding the dynamics of driving behavior: a machine learning analysis from Germany and Belgium, July 2024
July 3rd, 2024 | Comments Off on Unfolding the dynamics of driving behavior: a machine learning analysis from Germany and Belgium, July 2024 -
Safety evaluation via conflict classification during automated shuttle bus service operations, June 2024
July 2nd, 2024 | Comments Off on Safety evaluation via conflict classification during automated shuttle bus service operations, June 2024 -
European Commission – Promoting Safe Mobility: Protective Equipment, June 2024
June 27th, 2024 | Comments Off on European Commission – Promoting Safe Mobility: Protective Equipment, June 2024