Traffic forecasting is an important prerequisite for the application of intelligent transportation systems in urban traffic networks. The existing works adopted RNN and CNN/GCN, among which GCRN is the state-of-the-art work, to characterize the temporal and spatial correlation of traffic flows. However, it is hard to apply GCRN to the large-scale road networks due to high computational complexity. To address this problem, we propose abstracting the road network into a geometric graph and building a Fast Graph Convolution Recurrent Neural Network (FastGCRNN) to model the spatial-temporal dependencies of traffic flow. Specifically, we use FastGCN unit to efficiently capture the topological relationship between the roads and the surrounding roads in the graph with reducing the computational complexity through importance sampling, combine GRU unit to capture the temporal dependency of traffic flow, and embed the spatiotemporal features into Seq2Seq based on the Encoder-Decoder framework. Experiments on large-scale traffic data sets illustrate that the proposed method can greatly reduce computational complexity and memory consumption while maintaining relatively high accuracy.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Urban Traffic Flow Forecast Based on FastGCRNN


    Beteiligte:
    Ya Zhang (Autor:in) / Mingming Lu (Autor:in) / Haifeng Li (Autor:in)


    Erscheinungsdatum :

    2020




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Unbekannt




    Traffic flow forecast with urban transport network

    Wang, Di / Zhang, Qi / Wu, Shunyao et al. | IEEE | 2016


    Traffic Distribution Forecast of Urban External Traffic Hub Based on Uncertainty

    Zhu, Shunying / Guan, Juxiang / Peng, Wuxiong et al. | ASCE | 2008


    The Forecast of Dynamic Traffic Flow

    Yuan, Z. / Li, W. / Liu, H. et al. | British Library Conference Proceedings | 2000


    Traffic forecast

    Online Contents | 1998


    Traffic Forecast

    NTIS | 1967