The information collected by probe vehicles on the urban signalized network is widely used for traffic monitoring. Traffic conditions could be inferred based on the data collected by these probe vehicles. In recent years, the attempts to estimate link travel time based on probe vehicle data (e.g. positions, time stamps and speeds) are arising. However, due to the low polling frequencies (e.g. 1min or 5min), travel times recorded by probe vehicles provide only partial link or route travel times. In this paper, a three-layer Artificial Neural Network (ANN) model is proposed to estimate the complete link travel time for each individual probe vehicle. The information including positions, time stamps and speeds is input into the model and the output is the complete link travel time. The model is evaluated using the data from vissim simulation model. The results are compared with those from Hellinga's model and distance-proportion model. The evaluation results show that the proposed ANN model performs much better than Hellinga's model and distance-proportion model both in undersaturated conditions and oversaturated conditions.
Comparison of Urban Link Travel Time Estimation Models Based on Probe Vehicle Data
Seventh International Conference on Traffic and Transportation Studies (ICTTS) 2010 ; 2010 ; Kunming, China
Traffic and Transportation Studies 2010 ; 615-626
2010-07-26
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Comparison of Urban Link Travel Time Estimation Models Based on Probe Vehicle Data
British Library Conference Proceedings | 2010
|Urban link travel time estimation based on sparse probe vehicle data
Online Contents | 2013
|Urban link travel time estimation based on sparse probe vehicle data
Elsevier | 2012
|Investigating the Feasibility of Urban Link Travel Time Estimation Based on Probe Vehicle Data
British Library Conference Proceedings | 2009
|