Traffic capacity of a freeway differs depending on its distinct sections with differentspatial characteristics such as the number and width of lanes, existence and type ofshoulders and/ or medians, traffic characteristics (such as the number of breakdownsdefined using the sudden changes in the speed and density values that occur during theflow phase transition), and population characteristics (rural and urban areas). To accountfor these spatial differences, this paper investigates the hierarchical estimation of thetraffic capacity distribution on a highway using a nonparametric Bayesian approachassuming two prior distributions, namely Dirichlet and Gamma process priors under theminimization of a squared-error loss function. This approach addresses the difficultproblem of the censored observations while treating the model parameters as randomvariables represented by a probability distribution. The methodology is applied on thehighway sections with different spatial characteristics. An application of the method foron and off-ramps of a highway is also presented. Finally, the results are discussedhierarchically with presenting a methodology to simulate censored and breakdownobservations and to analyze them statistically using a bootstrap approach in order toobtain the capacity distributions for sections without sufficient data.
展开▼