Data underlying the publication: "Modelling Driver Expectations for Safe Speeds on Freeway Curves using Bayesian Belief Networks"

This research employs a Bayesian Belief Network to model driver expectations using measured speeds in 153 curves and data on the characteristics of the curve approaches. The data used as input for the Baysian Belief Network is shared here. It contains visual cues such as the direction of a curve, preceding roadway configuration, number of lanes and signs, along with measured 85th percentile speeds.