The invention discloses a short-term traffic flow prediction method based on a new deep space-time adaptive fusion graph network, and the method comprises the steps: firstly constructing an adaptive adjacency matrix which can be continuously updated in each iteration training; and then parallel fusion is carried out on graphs constructed from different angles according to the traffic flow data to obtain a new space-time fusion matrix. The adaptive matrix and the time-space fusion matrix are subjected to graph diffusion convolution at the same time to capture hidden time-space dependency, and finally captured features are subjected to deeper network model training to obtain a prediction result. According to the invention, a test experiment is carried out on a plurality of traffic flow data sets, and the experiment result shows that the network performance is superior to that of the most advanced method at present.
本发明公开了一种基于新深空时自适应融合图网络的短期交通流预测方法,首先构造自适应邻接矩阵,该邻接矩阵可以在每一次迭代训练中不断更新。然后再根据交通流数据从不同角度构造出来的图进行并行融合得到一个新的时空融合矩阵。自适应矩阵及时空融合矩阵同时进行图扩散卷积来捕获隐藏时空依赖性,最后捕获到的特征去进行更深层次网络模型的训练得出预测结果。本发明在多个交通流数据集上进行测试实验,实验结果表明该网络性能优于目前最先进的方法。
Short-term traffic flow prediction method based on new deep space-time adaptive fusion graph network
基于新深空时自适应融合图网络的短期交通流预测方法
2022-09-06
Patent
Electronic Resource
Chinese
IPC: | G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS |
Road network short-term traffic flow prediction method based on deep space-time residual network
European Patent Office | 2021
|Space-time adaptive dynamic graph convolutional network traffic flow prediction method
European Patent Office | 2024
|Short-term traffic flow prediction method based on space-time convolutional network
European Patent Office | 2023
|European Patent Office | 2024
|Traffic flow prediction method based on adaptive dynamic fusion graph convolutional network
European Patent Office | 2024
|