This paper proposes a solution to the problem of limited network sensor coverage caused by insufficient sample size of probe vehicles or inadequate numbers of fixed sensors. A framework is proposed to estimate link travel times using available data from neighbouring links. Two clues are used for real-time travel time estimation: link historical travel time data and online travel time data from neighbour links. In the absence of online travel time data from neighbour links, historical records only have to be relied upon. However, where the two types of data are available, a data fusion scheme can be applied to make use of the two clues. The proposed framework is validated using real-life data from the City of Vancouver, British Columbia. The estimation accuracy is found to be comparable to the existing literature. Overall, the results demonstrate the feasibility of using neighbour links data as an additional source of information that might not have been extensively explored before.
A framework for neighbour links travel time estimation in an urban network
Transportation Planning and Technology ; 35 , 3 ; 281-301
2012-04-01
Article (Journal)
Electronic Resource
English
A framework for neighbour links travel time estimation in an urban network
Online Contents | 2012
|Using buses as probes for neighbor links travel time estimation in an urban network
Online Contents | 2011
|Using buses as probes for neighbor links travel time estimation in an urban network
Taylor & Francis Verlag | 2011
|Modeling travel time variability on urban links in London
British Library Conference Proceedings | 2009
|Modeling of Travel Time Variations on Urban Links in London
Online Contents | 2011
|