Large scale estimation of arterial traffic and structural analysis of traffic patterns using probe vehicles
Résumé
Estimating and analyzing traffi c conditions on large arterial networks is an inherently diffi cult task. The fi rst goal of this article is to demonstrate how arterial tra c conditions can be estimated using sparsely sampled GPS probe vehicle data provided by a small percentage of vehicles. Traffi c signals, stop signs, and other flow inhibitors make estimating arterial traffi c conditions significantly more diffi cult than estimating highway traffi c conditions. To address these challenges, we propose a statistical modeling framework that leverages a large historical database and relies on the fact that tra ffic conditions tend to follow distinct patterns over the course of a week. This model is operational in North California, as part of the Mobile Millennium tra ffic estimation platform. The second goal of the article is to provide a global network-level analysis of tra ffic patterns using matrix factorization and clustering methods. These techniques allow us to characterize spatial tra ffic patterns in the network and to analyze traffi c dynamics at a network scale. We identify tra ffic patterns that indicate intrinsic spatio-temporal characteristics over the entire network and give insight into the traffi c dynamics of an entire city. By integrating our estimation technique with our analysis method, we achieve a general framework for extracting, processing and interpreting traffi c information using GPS probe vehicle data.
Domaines
Machine Learning [stat.ML]
Origine : Fichiers produits par l'(les) auteur(s)
Loading...