Road crashes are events which depend on a variety of factors and which exhibit different magnitudes of outputs when evaluated with respect to the effects on road users. Despite a lot of research into the evaluation of crash likelihood and frequency, only a few works have focused exclusively on crash severity with these limited to sections of freeways and multilane highways. Hence, at present there is a large gap in knowledge on factors affecting the severity of crashes for other road categories, facilities, and scenarios. The paper deals with the identification of factors affecting crash severity level at urban road intersections. Two official crash records together with a weather database, a traffic data source with data aggregated into 5min intervals, and further information characterising the investigated urban intersections were used. Analyses were performed by using a back propagation neural network model and a generalized linear mixed model that enable the impact assessment of flow and other variables. Both methods demonstrate that flows play a role in the prediction of severity levels.
Keywords: 5-min flow; Back-propagation neural network; Crash severity level; Generalized linear mixed model; Road intersection; Short-term data; Urban roads.
Copyright © 2017 Elsevier Ltd. All rights reserved.