This paper studies the problem of real-time traffic estimation and incident detection by posing it as a hybrid state estimation problem. An interactive multiple model ensemble Kalman filter is proposed to solve the sequential estimation problem, and to accommodate the switching dynamics and nonlinearity of the traffic incident model. The effectiveness of the proposed algorithm is evaluated through numerical experiments using a perturbed traffic model as the true model. The supporting source code is available for download at https://github.com/Lab-Work/IMM_EnKF_Traffic_Estimation_Incident_Detection.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Interactive multiple model ensemble Kalman filter for traffic estimation and incident detection


    Beteiligte:
    Wang, Ren (Autor:in) / Work, Daniel B. (Autor:in)


    Erscheinungsdatum :

    01.10.2014


    Format / Umfang :

    1278343 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch