Abstract
This study is intended to focus on the major factors affecting traffic crash rates and severity levels, in addition to identifying crash-prone locations (i.e., black spots) based on the two indicators. The available crash data for different road segments used for the analysis were obtained from the Washington state database provided by the Highway Safety Information System (HSIS) for the years 2006 to 2011. A Random Forest (RF) classifier was used to predict the outcome level of crash severity, while crash rates were predicted by applying RF regressor. Certain features were selected for each model besides the abstraction of new features to check if there are unobserved correlations affecting the independent variables, such as accounting for the number and weight of crashes within 1 km2 area by implementing the Getis-Ord Gi∗ index. Moreover, to calculate the collective risk (CR) score, crash rates were adjusted to incorporate crash severity weights (cost per severity type) and regression-to-the-mean (RTM) bias via Empirical Bayes (EB) method. Finally, segments were ranked according to their CR score.
Highlights
In recent years, crash rate and crash severity were the two major indicators used to assess roadway’s traffic safety, as well as identifying crash-prone locations
A weighted risk index or a combination of crash frequency and severity should prove an advantage over having only crash rate as an index of traffic hazards, without any regard to severity level or vice versa
Crash severity was found to be correlated to some unobserved random features such as weather conditions and collision points. ese features were needed to be drawn from a suitable distribution to be used in the model’s testing stage
Summary
Crash rate and crash severity were the two major indicators used to assess roadway’s traffic safety, as well as identifying crash-prone locations. Reducing crash rates and severity requires different strategic approaches and policies that aim at reducing the exposure for traffic accidents. Both reliable historical crash data and well-developed prediction models are essential in the process of estimating the impact of human and environmental-based features on the frequency and outcome of a crash incident. Observed or predicted indicators can be utilized to rank road facilities according to their overall risk score, allowing traffic safety agencies to distinguish which facilities have the priority in future crash countermeasure policies
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
