The invention provides a traffic speed prediction method based on a time-space gated graph convolutional network and application thereof, and the method comprises the steps: firstly obtaining traffic speed data through a sensor disposed on a traffic road, and training a deep learning model; generating a global space map with more comprehensive spatial features by using spatial position information of a sensor on a road in combination with a K-hop algorithm, and inputting the generated global space map and traffic speed data into a time-space gating map convolutional network to extract time-varying spatial features and time features; and extracting global features by using a self-attention module, and finally outputting predicted future traffic speed data by using a full-connection network. The model of the invention pays attention to the space information implied in the traffic network, the time-varying characteristics of the space characteristics and the global characteristics, and the accuracy of traffic speed prediction is effectively improved.

    本申请提出了基于时空门控图卷积网络的交通速度预测方法及其应用,包括首先通过设置在交通道路上的传感器获取交通速度数据来训练深度学习模型,之后利用传感器在道路上的空间位置信息结合K‑hop算法生成具有更全面空间特征的全局空间图,然后将生成的全局空间图与交通速度数据输入到时空门控图卷积网络中提取时变空间特征和时间特征,接着利用自注意力模块提取全局特征,最终利用全连接网络输出预测的未来交通速度数据。本申请的模型关注了交通网络中隐含的空间信息、空间特征的时变特性与全局特征,有效地提升了交通速度预测的准确性。


    Access

    Download


    Export, share and cite



    Title :

    Traffic speed prediction method based on time-space gated graph convolutional network and application thereof


    Additional title:

    基于时空门控图卷积网络的交通速度预测方法及其应用


    Contributors:
    LI KAIMIN (author) / ZHANG DONGPING (author) / LEE SUNG-KWON (author) / LAN HAO (author) / YU QIANG (author)

    Publication date :

    2023-04-11


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    Space-time ARMA graph convolutional network traffic flow prediction method

    CAO YANG / XIAO PEICHENG / SHEN QINQIN et al. | European Patent Office | 2024

    Free access

    Traffic flow prediction model based on gated time convolutional network

    KANG MING | European Patent Office | 2023

    Free access

    Traffic flow prediction method and system based on multi-time-sequence convolutional gated graph neural network

    SHI QUAN / ZHANG TENGYUN / SHEN QINQIN et al. | European Patent Office | 2023

    Free access

    Extended Multi-Component Gated Recurrent Graph Convolutional Network for Traffic Flow Prediction

    Zhao, Junhui / Xiong, Xincheng / Zhang, Qingmiao et al. | IEEE | 2024


    Space-time adaptive dynamic graph convolutional network traffic flow prediction method

    CUI WENTIAN / LOU JUNGANG / SHEN QING et al. | European Patent Office | 2024

    Free access