The invention relates to a traffic flow prediction method based on a graph attention convolution network, aims to predict medium and long time traffic flow, and belongs to the technical field of urbantraffic planning and flow prediction. The method comprises the following steps: step 1, preprocessing traffic flow data, and outputting a preprocessed data sequence; 2, based on the preprocessed datasequence, extracting spatial features and time features of the data sequence; and 3, inputting the extracted features of the two AGA blocks in the step 2, and obtaining a prediction result at the next moment through a full connection layer. According to the method, a recursive structure which cannot be trained in parallel is not used, and all components of the model are convolutional structures,so that the training time can be reduced; and according to the method, spatial features and time features are extracted respectively by trying to combine a spectrum-based graph convolutional network and a space-based convolutional network for the first time, and the algorithm is outstanding on a space-time traffic network.

    本发明涉及一种基于图注意力卷积网络的交通流量预测方法,旨在预测中长时间交通车流量,属于城市交通规划及流量预测技术领域。包括:步骤1:对交通流量数据预处理,输出预处理完成后的数据序列;步骤2:基于预处理完成后的数据序列,提取数据序列的空间特征以及时间特征;步骤3、输入经过步骤2两个AGA块的特征提取,经过一层全连接层得到下一时刻预测结果。所述方法未使用无法并行训练的递归结构,模型的所有组件都是卷积结构,可以减少训练时间;所述方法是首次尝试结合基于频谱的图卷积网络和基于空间的卷积网络,分别提取空间特征和时间特征,在时空交通网络上算法表现出众。


    Access

    Download


    Export, share and cite



    Title :

    Traffic flow prediction method based on graph attention convolution network


    Additional title:

    一种基于图注意力卷积网络的交通流量预测方法


    Contributors:
    ZHENG HONG (author) / ZHANG SIKAI (author) / LIU JIAMOU (author) / SU HONGYI (author) / YAN BO (author)

    Publication date :

    2020-06-02


    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