The important Research fields in ITS include traffic flow guidance and control. To effectively guide and control the traffic flow, its status must be predicted accurately in real time. Close spatial and temporal associations exist between traffic flow of the road sections and its neighbors in the urban traffic network, traffic state multi-spot time series forecasting is more accuracy than the single ones. In this paper, a predicting model for urban region traffic status is presented by using spatial-temporal data mining technology and autoregressive moving average method. The road network topology and traffic time series datasets of some sections are considered in the predicting model. The model is based on autoregressive moving average method and spatial-temporal association rules. The traffic data from several road sections are used as the sample datasets to verify model's applicability in real time forecasting, and analyze the spatial-temporal association rules of the sections in the urban region traffic network.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Traffic State Forecast of Road Network Based on Spatial-Temporal Data Mining


    Beteiligte:
    Deng, Rui (Autor:in) / Jiang, Lizhu (Autor:in)

    Kongress:

    Third International Conference on Transportation Engineering (ICTE) ; 2011 ; Chengdu, China


    Erschienen in:

    ICTE 2011 ; 734-739


    Erscheinungsdatum :

    13.07.2011




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Traffic Analysis and Forecast for Meghalaya Road Network

    Singh, Manmeet / Kumar, Ravindra | Springer Verlag | 2022




    Critical Section Identification in Road Traffic Network Based on Spatial and Temporal Features of Traffic Flow

    Su, Fei / Zou, Xiaofang / Qin, Yong et al. | British Library Conference Proceedings | 2020