The invention discloses a node adaptive learning graph attention neural network traffic flow prediction method, and the method comprises the following steps: S1, carrying out the preprocessing of a traffic flow data set, and dividing the data set into a training set and a test set; s2, performing deep representation on the data by using node adaptive learning, and learning dynamic association between nodes; s3, dynamically capturing spatial dependence by using a node adaptive learning graph attention network; s4, capturing local space-time correlation by using a gating cycle unit, and capturing long-time dependence of each space node in a time dimension by using a Transform layer; and S5, performing prediction output by using a full-connection neural network as a prediction layer. According to the invention, the traffic flow data Euclidean data are converted into non-Euclidean data and a graphic structure, which is more in line with the traffic scene; node adaptive learning, a GAT layer, a GRU layer and a Transform layer are used for capturing time correlation and space correlation of traffic data, and the prediction performance of the model is improved.

    本发明公开了一种节点自适应学习图注意力神经网络交通流预测方法,包括以下步骤:S1:对交通流量数据集进行预处理,并将数据集划分为训练集和测试集;S2:使用节点自适应学习,将数据进行深层次表示,学习节点间的动态关联;S3:使用节点自适应学习图注意力网络动态捕获空间依赖;S4:使用门控循环单元捕获局部时空相关性,使用Transformer层捕捉每个空间节点在时间维度上的长时间依赖;S5:使用全连接神经网络作为预测层,进行预测输出。本发明通过将交通流数据欧几里得数据,转化为非欧数据、图形结构,更符合交通情景;使用节点自适应学习、GAT、GRU和Transformer层捕获交通数据的时间相关性和空间相关性,提高模型的预测性能。


    Access

    Download


    Export, share and cite



    Title :

    Node adaptive learning graph attention neural network traffic flow prediction method


    Additional title:

    节点自适应学习图注意力神经网络交通流预测方法


    Contributors:
    LOU JUNGANG (author) / HUANG XUXIANG (author) / SHEN QING (author) / ZHU SHAOJUN (author)

    Publication date :

    2024-07-05


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    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



    Traffic flow prediction method based on time attention circulation graph convolutional neural network

    FAN WENDONG / SHU MIN / SONG YUN et al. | European Patent Office | 2023

    Free access

    Traffic flow prediction based on graph attention network

    Zhu, Wenyan / Kong, Hoiio / Cai, Wenzheng et al. | SPIE | 2024


    Attention-Based Spatiotemporal Adaptive Graph Diffusion Convolutional Network For Traffic Flow Prediction

    He, Qiansong / Xia, Dawen / Li, Jianjun et al. | Transportation Research Record | 2025


    Graph neural network traffic flow prediction method and system based on attention mechanism

    YU LONGFEI / PENG ZHAOHUI | European Patent Office | 2020

    Free access

    Traffic flow prediction method based on Transform adaptive adversarial graph neural network

    XIA ZHENCHANG / YUAN LINGTIAN / QIU CHENGYI et al. | European Patent Office | 2024

    Free access