As Intelligent Transportation Systems (ITS) gain wider adoption, one critical decision city authorities need to make is what sensors to use to get the traffic data. There is a slew of techniques available varying in accuracy, coverage and cost to install and maintain, not to mention the diversity in which they can be set up and how they may complement each other. Even if a city starts with one preferred sensor (e.g., security cameras), over time, technology presents more options that may synergistically work together (e.g., mobile phones). Consequently, a city planning to use traffic sensors for ITS soon finds that it has to make, and continuously reassess, among multiple sensor types for increased benefits on its ITS investments. In this paper, we empirically explore what subset of sensors work well in what conditions and report that (a) data from Call Data Records (CDRs) of low-cost phones can complement sensors due to their high-coverage and low-cost despite inherent errors, and (b) a prescriptive method can provide optimal sensor subset selection for a traffic condition.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Sensor subset selection for traffic management


    Beteiligte:
    Gupta, R. (Autor:in) / Srivastava, B. (Autor:in)


    Erscheinungsdatum :

    01.10.2011


    Format / Umfang :

    758681 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Automated feature generation for sensor subset selection

    STURLAUGSON LIESSMAN / ETHINGTON JAMES M | Europäisches Patentamt | 2025

    Freier Zugriff

    AUTOMATED FEATURE GENERATION FOR SENSOR SUBSET SELECTION

    STURLAUGSON LIESSMAN / ETHINGTON JAMES M | Europäisches Patentamt | 2020

    Freier Zugriff



    Joint Feature-Basis Subset Selection

    Avidan, S. / IEEE Computer Society | British Library Conference Proceedings | 2004