Modern artificial intelligence (AI) and machine learning (ML) traffic prediction models provide accuracy, yet lack interpret-ability. Our approach designs a local neighborhood of segments and time-periods to construct a prediction data set that contain explicit dynamics across properties measured in the spatial temporal frame. The approach performs similarly to a popular TGCN ML model while providing opportunity to understand the relationship between predictor and predictand across the graph structure to which it is applied.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Traffic Speed Prediction Using Explicit Spatial Temporal Dynamics


    Beteiligte:
    Gordon, Richard (Autor:in) / Grimm, Donald K. (Autor:in) / Bai, Fan (Autor:in)


    Erscheinungsdatum :

    24.09.2024


    Format / Umfang :

    1133602 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Spatial–Temporal Tensor Graph Convolutional Network for Traffic Speed Prediction

    Xu, Xuran / Zhang, Tong / Xu, Chunyan et al. | IEEE | 2023




    Spatial and Temporal Patterns in Large-Scale Traffic Speed Prediction.
    Spatiotemporal Patterns in Large-Scale Traffic Speed Prediction

    Asif, Muhammad Tayyab / Dauwels, Justin / Oran, Ali et al. | DSpace@MIT | 2014

    Freier Zugriff

    Attention Mechanism With Spatial-Temporal Joint Model for Traffic Flow Speed Prediction

    Hu, Hexuan / Lin, Zhenzhou / Hu, Qiang et al. | IEEE | 2022