The invention discloses a traffic flow prediction method based on a graph attention mechanism and a bidirectional gating circulation unit. The traffic flow prediction method is realized through four steps of capturing spatial dependency features, capturing time dependency features, performing full-connection operation and performing result prediction. According to the method, for a time-space combined reference model, STGCN extracts time-space information by combining graph convolution and one-dimensional time convolution; the DCRNN inputs the image convolution information subjected to spatial dimension processing into a recurrent neural network in an encoder-decoder form to extract space-time dependency features; in terms of spatial-temporal feature extraction, the overall performance is superior to that of other reference models, and a good effect is achieved in the aspect of long-time traffic flow prediction. According to the model, traffic prediction results of different nodes in a real road network are well represented, the space-time dependence characteristics of the traffic road network can be fully captured, the effectiveness of the model in the aspect of long-time traffic flow prediction is better reflected, and the real vehicle speed change trend can be reflected.

    本发明公开了基于图注意力机制和双向门控循环单元交通流预测方法,本发明通过捕获空间依赖特征、捕获时间依赖特征、全连接操作、结果预测这四个步骤予以实现。本发明对于时空结合的基准模型,STGCN通过结合图卷积和一维时间卷积来提取时空信息;DCRNN以编码器‑解码器的形式将空间维度处理过的图卷积信息输入到循环神经网络中来提取时空依赖特征;在时空特征的提取上,整体的表现都优于其他基准模型,在长时交通流预测方面取得了很好的效果。本发明模型在现实路网中不同节点的交通预测结果都表现不错,能充分捕获交通路网的时空依赖特征,更加体现出本发明模型在长时交通流预测方面的有效性,可以反映出真实的车辆速度变化趋势。


    Access

    Download


    Export, share and cite



    Title :

    Traffic flow prediction method based on graph attention mechanism and bidirectional gating circulation unit


    Additional title:

    基于图注意力机制和双向门控循环单元交通流预测方法


    Contributors:
    ZHANG XIJUN (author) / ZHANG BAOQI (author) / ZHANG HONG (author) / ZHANG XIANLI (author) / NIE SHENGYUAN (author)

    Publication date :

    2023-08-01


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    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



    Traffic flow prediction method based on space-time bidirectional attention mechanism

    ZHOU YIMIN / YANG SHUDONG | European Patent Office | 2024

    Free access

    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

    Fusion attention mechanism bidirectional LSTM for short-term traffic flow prediction

    Li, Zhihong / Xu, Han / Gao, Xiuli et al. | Taylor & Francis Verlag | 2024


    Toll station exit prediction method based on gating circulation unit

    SUN DIHUA / ZHAO MIN / ZHANG QIANG et al. | European Patent Office | 2020

    Free access

    Dynamic graph structure attention mechanism short-term traffic flow prediction method

    LOU JUNGANG / WU XUHONG / SHEN QING et al. | European Patent Office | 2023

    Free access