The invention belongs to the technical field of traffic flow prediction, and discloses a space-time normalized graph convolutional neural network traffic flow prediction method and system and a medium, and the method comprises the steps: firstly taking traffic flow data as input, and carrying out the data type conversion through a linear layer; the converted data flows into a space-time normalization module to subdivide the data into high and low frequencies, so that the time convolution TCN captures finer features of the data; transmitting the data subjected to space-time normalization to two parallel gating time convolution modules; adding a residual error in the input of the time convolution module and connecting the residual error to the output of the graph convolution module; the extracted time features are transmitted to a spatial convolution module to extract spatial features, the spatial features are extracted through a spatial-temporal feature extraction module and then flow into a next-layer spatial-temporal module to continue to extract the spatial-temporal features, results extracted by k spatial-temporal extraction modules are connected in a jumping mode to enter an output layer, and finally a predicted value is output. According to the invention, the accuracy of traffic flow prediction is improved.

    本发明属于交通流量预测技术领域,公开了一种时空归一化图卷积神经网络交通流预测方法、系统及介质,首先将交通流量数据作为输入,经过一个线性层将数据类型转换;转换后的数据流入时空归一化模块将数据细分成高低频,使得时间卷积TCN捕获数据更加细微的特征;经过时空归一化后的数据传递给两个并行的门控时间卷积模块;在时间卷积模块的输入中添加残差连接到图卷积模块的输出中;将提取的时间特征传递给空间卷积模块提取空间特征,通过时空特征提取模块提取时空特征之后流入到下一层时空模块继续提取时空特征,将k个时空提取模块提取到的结果跳跃连接进入输出层,最后输出预测值。本发明提高了交通流量预测的准确性。


    Access

    Download


    Export, share and cite



    Title :

    Space-time normalized graph convolutional neural network traffic flow prediction method and system, and medium


    Additional title:

    时空归一化图卷积神经网络交通流预测方法、系统及介质


    Contributors:
    WANG CHUNZHI (author) / WANG LU (author) / YAN LINGYU (author) / PENG XIANJUN (author) / WANG RUOXI (author) / YU LIANG (author) / ZHAO CHONGXI (author) / LI QINGQING (author) / ZHANG WENKAI (author) / LU ZHENDONG (author)

    Publication date :

    2024-01-12


    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



    Space-time ARMA graph convolutional network traffic flow prediction method

    CAO YANG / XIAO PEICHENG / SHEN QINQIN et al. | European Patent Office | 2024

    Free access


    Urban traffic flow space-time prediction scheme based on graph convolutional neural network

    ZHANG RONGQING / WANG HANQIU / LI BING | European Patent Office | 2021

    Free access

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

    CUI WENTIAN / LOU JUNGANG / SHEN QING et al. | 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