The invention relates to a traffic flow prediction method based on an adaptive graph fusion convolutional network, and the method comprises the following steps: constructing a to-be-predicted road network into a graph model, and naming the graph model as a road network graph model; the historical traffic of the nodes is input to an adaptive graph fusion convolution module for processing, the adaptive graph fusion convolution module is used for establishing an adaptive static adjacency matrix and an adaptive dynamic adjacency matrix according to the generated road network graph model, a static-dynamic graph fusion layer carries out fusion operation, and corresponding spatial features are extracted; organizing the road network spatial features extracted by the adaptive graph fusion convolution module by using the residual enhancement gating cycle unit; processing the hidden state vector sequence by using a node embedded self-attention layer; and constructing a full connection layer to carry out dimension conversion, and inputting the obtained hidden state sequence into the full connection layer to obtain a prediction result on each road section.

    本发明涉及一种基于自适应图融合卷积网络的交通流量预测方法,包括下列步骤:将所需要进行预测的路网构建为图模型,称其为路网图模型;将节点的历史流量输入到自适应图融合卷积模块处理,自适应图融合卷积模块用于根据所生成的路网图模型建立自适应静态邻接矩阵和自适应动态邻接矩阵,并由静态‑动态图融合层进行融合操作,提取对应的空间特征;利用所述残差增强门控循环单元对自适应图融合卷积模块提取到的路网空间特征进行组织;用节点嵌入的自注意力层处理隐状态向量序列;构建全连接层进行维度转换,将得到的隐状态序列输入全连接层,得到各路段上的预测结果。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Traffic flow prediction method based on adaptive graph fusion convolutional network


    Weitere Titelangaben:

    一种基于自适应图融合卷积网络的交通流量预测方法


    Beteiligte:
    XU YAN (Autor:in) / LU YU (Autor:in) / ZHANG QIYUAN (Autor:in) / SU QIAN (Autor:in) / JI CHANGTAO (Autor:in)

    Erscheinungsdatum :

    2023-05-05


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS



    Multibranch Adaptive Fusion Graph Convolutional Network for Traffic Flow Prediction

    Xin Zan / Jasmine Siu Lee Lam | DOAJ | 2023

    Freier Zugriff

    Traffic flow prediction method based on dynamic adaptive adversarial graph convolutional neural network

    WANG HUI / WANG YU / DU KAI | Europäisches Patentamt | 2024

    Freier Zugriff

    Multi-view fusion space-time dynamic graph convolutional network urban traffic flow prediction method

    YUAN GUAN / ZHAO WENZHU / ZHANG YANMEI et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Traffic flow prediction method of space-time attention graph convolutional network based on multi-feature fusion

    CHEN YAJUN / DING ZHIMING / GUO LIMIN | Europäisches Patentamt | 2023

    Freier Zugriff

    Dynamic multi-graph convolutional network traffic flow prediction method based on graph transformation

    HU YONGLI / PENG TING / GUO KAN et al. | Europäisches Patentamt | 2022

    Freier Zugriff