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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    A framework for neighbour links travel time estimation in an urban network


    Contributors:

    Published in:

    Publication date :

    2012-04-01




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English






    Using buses as probes for neighbor links travel time estimation in an urban network

    El Esawey, Mohamed / Sayed, Tarek | Taylor & Francis Verlag | 2011


    Modeling travel time variability on urban links in London

    Hasan, S. / Ben-Akiva, M.E. / Choudhury, C. et al. | British Library Conference Proceedings | 2009