According to the traffic flow prediction method based on interactive dynamic graph convolution and probability sparse attention, an IDG-PSATt method is composed of an interactive dynamic graph convolution network IDGCN, a space-time convolution block ST-Conv Block and a probability sparse self-attention mechanism ProbSSATt Block; the method comprises the following steps: step 1, an IDGCN divides a traffic flow time sequence according to intervals, and interactively shares captured dynamic spatio-temporal characteristics; step 2, ST-Conv Block captures complex time dependence of traffic flows at the same position and dynamic spatial correlation of traffic flows at adjacent positions on the same time step length; step 3, the ProbSSATt Block captures dynamic spatio-temporal characteristics so as to improve the medium and long term prediction performance of the IDG-PSATt method; step 4, constructing a dynamic graph convolutional network generated by fusing the adaptive adjacency matrix and the learnable adjacency matrix so as to learn dynamic association hidden among road network nodes; and step 5, traffic flow prediction is carried out through the prediction layer.

    交互动态图卷积及概率稀疏注意力的交通流预测方法,所述的交通流预测方法,IDG‑PSAtt方法由交互式动态图卷积网络IDGCN和时空卷积块ST‑Conv Block以及概率稀疏自注意力机制ProbSSAtt Block构成;步骤一、IDGCN将交通流时间序列按间隔划分,并交互共享捕捉的动态时空特征;步骤二、ST‑Conv Block捕获同一位置交通流的复杂时间依赖性和同一时间步长上邻近位置交通流的动态空间相关性;步骤三、ProbSSAtt Block捕获动态时空特征以提高IDG‑PSAtt方法的中长期预测性能;步骤四、构建一种由自适应邻接矩阵和可学习邻接矩阵融合生成的动态图卷积网络,以学习道路网络节点间隐藏的动态关联;步骤五、通过预测层进行交通流预测。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Traffic flow prediction method based on interactive dynamic graph convolution and probability sparse attention


    Weitere Titelangaben:

    交互动态图卷积及概率稀疏注意力的交通流预测方法


    Beteiligte:
    ZHANG HONG (Autor:in) / CHEN LINBIAO (Autor:in) / CHEN LINLONG (Autor:in) / ZHANG XIJUN (Autor:in) / HOU LIANG (Autor:in) / CHEN ZUOHAN (Autor:in)

    Erscheinungsdatum :

    2023-12-26


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

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



    Traffic Flow Prediction Based on Interactive Dynamic Spatio-Temporal Graph Convolution with a Probabilistic Sparse Attention Mechanism

    Chen, Linlong / Chen, Linbiao / Wang, Hongyan et al. | Transportation Research Record | 2024


    Traffic flow prediction method of space-time convolution fusion probability sparse attention mechanism

    ZHANG HONG / CHEN LINBIAO / CHEN LINLONG et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Traffic flow prediction method based on graph attention convolution network

    ZHENG HONG / ZHANG SIKAI / LIU JIAMOU et al. | Europäisches Patentamt | 2020

    Freier Zugriff


    Traffic flow prediction method and system based on time sequence dependent attention sparse convolution

    LIAO HUICHUAN / TANG JIE / HUANG XIAOHUI | Europäisches Patentamt | 2023

    Freier Zugriff