The Viability of Using Automatic Vehicle Identification Data for Real-Time Crash Prediction

Real-time crash prediction research attempted the use of data from inductive loop detectors; however, no safety analysis has been carried out using traffic data from one of the most growing nonintrusive surveillance systems, i.e., the tag readers on toll roads known as automatic vehicle identification (AVI) systems. In this paper, for the first time, the identification of freeway locations with high crash potential has been examined using real-time speed data collected from AVI. Travel time and space mean speed data collected by AVI systems and crash data of a total of 78 mi on the expressway network in Orlando in 2008 were collected. Utilizing a random forest technique for significant variable selection and stratified matched case-control to account for the confounding effects of location, time, and season, the log odds of crash occurrence were calculated. The length of the AVI segment was found to be a crucial factor that affects the usefulness of the AVI traffic data. While the results showed that the likelihood of a crash is statistically related to speed data obtained from AVI segments within an average length of 1.5 mi and crashes can be classified with about 70% accuracy, all speed parameters obtained from AVI systems spaced at 3 mi or more apart were found to be statistically insignificant to identify crash-prone conditions. The findings of this study illustrate a promising real-time safety application for one of the most widely used and already present intelligent transportation systems, with many possible advances in the context of advanced traffic management