The invention provides an adaptive space-time neural network traffic prediction model combined with multi-graph fusion. Firstly, three spatial dependencies of DTS are considered, and an initial adjacency matrix is constructed. Secondly, a method of alternately training a graph generation module and a prediction module is adopted, and a loss function with good performance is designed in the training process, so that the model can be self-adjusted. And finally, a fusion mechanism is adopted to fuse the learned matrixes and generate an optimal adjacent matrix, so that the prediction of the road traffic is more accurate.

    本发明提出一种结合了多图融合的自适应时空神经网络交通预测模型。首先考虑DTS三种空间依赖关系,构建初始邻接矩阵。其次,采用图生成模块与预测模块交替训练的方法,并在训练过程中设计了性能良好的损失函数,使得模型能够自我调整。最后,本发明还采用了融合机制来融合学习到的矩阵并产生最优邻接矩阵,这使得道路交通的预测更加准确。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Adaptive space-time neural network traffic prediction model combined with multi-graph fusion


    Weitere Titelangaben:

    一种结合了多图融合的自适应时空神经网络交通预测模型


    Beteiligte:
    ZHANG JING (Autor:in) / SHI WENLONG (Autor:in) / HE DING (Autor:in) / SI KUNLIANG (Autor:in) / CHEN XUEQI (Autor:in) / LU WEIJIE (Autor:in)

    Erscheinungsdatum :

    06.02.2024


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

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



    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

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

    CUI WENTIAN / LOU JUNGANG / SHEN QING et al. | Europäisches Patentamt | 2024

    Freier Zugriff

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

    SHI QUAN / CAO CHENYANG / BAO YINXIN et al. | Europäisches Patentamt | 2025

    Freier Zugriff


    Traffic flow space-time prediction method based on graph neural network

    ZHAO SHENGJIE / CHEN ZIXUAN / ZENG JIN et al. | Europäisches Patentamt | 2024

    Freier Zugriff