The invention relates to a traffic flow prediction model based on a gated time convolutional network. According to the traffic flow combined prediction model, a G-TCN models time dependence, spatial correlation and a long-time sequence of traffic flow respectively. A time convolution network (TCN) and a graph convolution network (GCN) are used for capturing time dependence and spatial correlation of traffic flow respectively, and an STA-Block module models the spatial-temporal correlation of a long-time sequence through a spatial-temporal attention mechanism and a gating fusion mechanism. A self-adaptive adjacent matrix is constructed in a G-TCN model, and learning is performed through node embedding. The model can accurately capture the hidden space-time dependency relationship in the traffic flow data.

    本发明涉及一种基于门控时间卷积网络的交通流预测模型,所述的交通流组合预测模型,G‑TCN分别对交通流的时间依赖性,空间相关性和长时间序列进行建模。使用时间卷积网络(TCN)和图卷积网络(GCN)分别捕获交通流的时间依赖性和空间相关性,STA‑Block模块通过时空注意力机制和门控融合机制对长时间序列的时空相关性进行建模。在G‑TCN模型中构造一个自适应邻接矩阵并通过节点嵌入进行学习,该模型能够准确的捕获交通流数据中隐藏的时空依赖关系。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Traffic flow prediction model based on gated time convolutional network


    Weitere Titelangaben:

    一种基于门控时间卷积网络的交通流预测模型


    Beteiligte:
    KANG MING (Autor:in)

    Erscheinungsdatum :

    2023-08-15


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    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 / 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



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

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


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

    SHI QUAN / ZHANG TENGYUN / SHEN QINQIN et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    SHORT-TERM TRAFFIC FLOW PREDICTION METHOD BASED ON CAUSAL GATED-LOW-PASS GRAPH CONVOLUTIONAL NETWORK

    XU XING / MAO HAO / ZHAO YUN | Europäisches Patentamt | 2024

    Freier Zugriff

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

    LI KAIMIN / ZHANG DONGPING / LEE SUNG-KWON et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Optimized traffic flow prediction model based on space-time diagram convolutional network

    ZHANG HONG / ZHAO YUANMENG / CHEN LINLONG et al. | Europäisches Patentamt | 2021

    Freier Zugriff