The fast expansion of vehicles on the road also paves the way for technology to take advantage of the large amount of data created and put it to use. Sustainable traffic and smart traffic management are sweeping urban areas. Previous research has demonstrated that the spatiotemporal data available can be used to alleviate traffic congestion. The mapping of the GTFS (General Transit Feed Specification) data into a graph structure is emphasised in this work. In order to examine the traffic network, we use Graph Neural Networks (GNNs) in this study and forecast the links between them. To the best of our knowledge, this is one of the first attempts to describe the traffic network as a classification problem rather than a prediction problem, which assuages the challenges posed by the complexity of time and space transfiguration. The study's major goal is to highlight the importance of GTFS feeds that can be obtained from a successful public transit system.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Traffic Congestion Prediction Based on Spatio-Temporal Graph Structure Learning


    Contributors:


    Publication date :

    2023-01-27


    Size :

    378998 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Spatio-temporal graph attention networks for traffic prediction

    Ma, Chuang / Yan, Li / Xu, Guangxia | Taylor & Francis Verlag | 2024




    Short-term traffic congestion prediction with Conv–BiLSTM considering spatio-temporal features

    Li, Tao / Ni, Anning / Zhang, Chunqin et al. | IET | 2021

    Free access

    Short‐term traffic congestion prediction with Conv–BiLSTM considering spatio‐temporal features

    Li, Tao / Ni, Anning / Zhang, Chunqin et al. | Wiley | 2020

    Free access