Taxi is an important component of the urban transport system in most cities. Accurate taxi demand prediction can effectively reduce the waiting time of passengers and shorten the no-load travel of drivers, which is helpful in alleviating traffic congestion and improving traffic efficiency. Due to the complexity of the traffic system and spatiotemporal dependencies among regions in a road network, traditional prediction methods cannot predict taxi demands of different regions effectively. This paper introduces a Graph Multi-Attention Network (GMAN) to handle the taxi demand prediction problem with better performance, which aims to predict the taxi demands in all regions of a road network in the next time period. The effectiveness of the GMAN is validated based on a large-scale dataset of taxi demands from a real urban road network. Experimental results show that the GMAN outperforms 5 commonly used benchmarking models, including 3 state-of-the-art machine learning models.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Graph Multi-Attention Network-based Taxi Demand Prediction


    Beteiligte:
    Tang, Haifan (Autor:in) / Wu, Youkai (Autor:in) / Guo, Zhaoxia (Autor:in)


    Erscheinungsdatum :

    2022-10-28


    Format / Umfang :

    2230627 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Urban Taxi Demand Forecast Based on Graph Convolutional Network

    Wang, Yaguan / Qin, Yong / Guo, Jianyuan | Springer Verlag | 2022


    Urban Taxi Demand Forecast Based on Graph Convolutional Network

    Wang, Yaguan / Qin, Yong / Guo, Jianyuan | British Library Conference Proceedings | 2022



    BERT-Based Deep Spatial-Temporal Network for Taxi Demand Prediction

    Cao, Dun / Zeng, Kai / Wang, Jin et al. | IEEE | 2022