The invention discloses a traffic flow prediction method based on a dynamic adaptive adversarial graph convolutional neural network, and the method comprises the steps: obtaining traffic data, and carrying out the data preprocessing according to the obtained traffic data; constructing a feature matrix of nodes, and combining a node embedding vector and a time embedding vector to generate a dynamic adaptive graph; constructing an adaptive graph convolutional recurrent neural network to extract dynamic spatial dependence; extracting time sequence features by using a gating extension causal network module; and finally, generating predicted traffic data similar to real data by adopting a dynamic adaptive graph convolution module with adversarial training. According to the method, an existing traffic flow prediction model is improved, a universal normal form and a gate module are used, time-varying embedding and node embedding are fused, and a dynamic self-adaptive graph is generated and used for capturing the space-time dependency relationship of each node. In addition, the method considers that the prediction data is consistent with real data at a sequence level and a graph level, so that the convergence speed is higher, and the prediction result is better.

    本发明公开了一种基于动态自适应对抗图卷积神经网络的交通流预测方法,该方法包括:获取交通数据,根据获取到的交通数据进行数据预处理;构建节点的特征矩阵,将节点嵌入向量和时间嵌入向量结合,生成动态自适应图;构建自适应图卷积循环神经网络提取动态空间依赖;使用门控扩展因果网络模块提取时序特征;最后采用带有对抗训练的动态自适应图卷积模块,产生与真实数据相近的预测交通数据。本发明改进了现有的交通流预测模型,使用一个通用的范式和一个门模块,将时变嵌入与节点嵌入融合,生成动态自适应图,用于捕获每个节点的时空依赖关系。另外考虑了预测数据在序列级别和图级别与真实数据保持一致,使得收敛速度更快,预测结果更好。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

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


    Weitere Titelangaben:

    一种基于动态自适应对抗图卷积神经网络的交通流预测方法


    Beteiligte:
    WANG HUI (Autor:in) / WANG YU (Autor:in) / DU KAI (Autor:in)

    Erscheinungsdatum :

    2024-03-08


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G06Q Datenverarbeitungssysteme oder -verfahren, besonders angepasst an verwaltungstechnische, geschäftliche, finanzielle oder betriebswirtschaftliche Zwecke, sowie an geschäftsbezogene Überwachungs- oder Voraussagezwecke , DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES




    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

    Traffic flow prediction method based on multi-view dynamic graph convolutional network

    HUANG XIAOHUI / YE YUMING / LING JIAHAO et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    Short-term traffic flow prediction method based on integrated graph convolutional neural network

    LIU LUYANG / LYU SHUAIQI / BAO XU | Europäisches Patentamt | 2024

    Freier Zugriff

    Traffic flow prediction method based on adaptive graph fusion convolutional network

    XU YAN / LU YU / ZHANG QIYUAN et al. | Europäisches Patentamt | 2023

    Freier Zugriff