The invention discloses a traffic flow prediction method based on a nested time sequence decomposition space-time diagram convolutional network, and the method comprises the steps: decomposing the multi-time scale trend and period of traffic flow information through employing a nested time sequence decomposition module, and carrying out the decomposition of the multi-time scale trend and period of the traffic flow information through the autocorrelation of traffic flow data and a constructed traffic network structure matrix, a space-time diagram convolution layer of a space-time diagram convolution module with improved design is introduced, the space-time relation between nodes and own nodes and the space relation between the nodes and adjacent nodes are considered, the space-time relation between the nodes and the adjacent nodes is also considered, and the time-time relation between the nodes and the non-synchronization length of the adjacent nodes is further considered through the propagation characteristics of traffic flow events. Connection of non-adjacent nodes but sharing similar traffic flow modes is established. Compared with a traditional network, the network can effectively mine the periodic characteristics of the time scale and the propagation characteristics of the space scale of the traffic flow data, and has good prediction accuracy.

    本发明公开了一种基于嵌套时序分解时空图卷积网络的交通流预测方法,通过使用嵌套时序分解模块将这些交通流信息的多时间尺度趋势与周期进行分解,以交通流数据的自相关性,与构建的交通网络结构矩阵,传入引入了改进设计的时空图卷积模块的时空图卷积层,不光考虑了节点和自己节点的时空关系、节点和相邻节点的空间关系,还考虑了节点和相邻节点非同步长的时空关系,通过交通流事件的传播特征,建立起非相邻节点但共享相似交通流模式的连接。此网络相比于传统网络,可以有效的挖掘交通流数据的时间尺度的周期特性和空间尺度的传播特性,有好的预测精确度。


    Access

    Download


    Export, share and cite



    Title :

    Traffic flow prediction method based on nested time sequence decomposition space-time diagram convolutional network


    Additional title:

    一种基于嵌套时序分解时空图卷积网络的交通流预测方法


    Contributors:

    Publication date :

    2023-05-16


    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 diagram convolutional network

    JIANG YUNLIANG / XIA RENHUAN / ZHANG XIONGTAO et al. | European Patent Office | 2022

    Free access

    Traffic flow prediction method based on space-time diagram convolutional network

    JIANG CONG / SONG YUN / DENG ZELIN et al. | European Patent Office | 2023

    Free access

    Traffic flow prediction method of space-time diagram convolutional network

    TENG FEI / WANG ZIDAN / QIAO LU et al. | European Patent Office | 2024

    Free access

    Traffic flow prediction method based on multi-space-time diagram convolutional network

    SHI QUAN / DAI JUNMING / SHEN QINQIN et al. | European Patent Office | 2021

    Free access