A traffic flow prediction method based on fusion of space-time adaptive graph learning and dynamic graph convolution is characterized in that an STAHGCN method mainly comprises a gated time convolutional network Gaded TCN and an adaptive mixed graph convolution module AHGCM, the Gaded TCN captures time dependence by using expansion causal convolutional networks of different granularity levels, and the adaptive mixed graph convolution module AHGCM captures the time dependence by using the expansion causal convolutional networks of different granularity levels. The AHGCM is composed of static adaptive graph learning SAGL, dynamic graph learning DGL and a space door fusion mechanism so as to synchronously and fully capture dynamic spatial and temporal characteristics in traffic flow historical data; the SAGL can adaptively capture dynamic spatial features of traffic, and the DGL can capture hidden spatial correlation through a graph attention mechanism and reduce time complexity through parallel computing.
一种时空自适应图学习融合动态图卷积的交通流预测方法,所述的交通流预测方法,其特征如下:STAHGCN方法主要包含门控时间卷积网络Gated TCN和自适应混合图卷积模块AHGCM,Gated TCN利用不同粒度级别的扩张因果卷积网络来捕捉时间依赖性,AHGCM由静态自适应图学习SAGL、动态图学习DGL以及空间门融合机制构成,以同步充分捕捉交通流历史数据中的动态时空特征;SAGL能够自适应地捕获交通的动态空间特征,DGL能够通过图注意力机制捕获隐藏空间相关性的同时通过并行计算降低时间复杂度。
Traffic flow prediction method based on fusion of space-time adaptive graph learning and dynamic graph convolution
一种时空自适应图学习融合动态图卷积的交通流预测方法
2024-01-12
Patent
Elektronische Ressource
Chinesisch
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 / G06Q Datenverarbeitungssysteme oder -verfahren, besonders angepasst an verwaltungstechnische, geschäftliche, finanzielle oder betriebswirtschaftliche Zwecke, sowie an geschäftsbezogene Überwachungs- oder Voraussagezwecke , DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES |
Double-end graph convolution traffic flow prediction method with graph learning
Europäisches Patentamt | 2023
|Periodic adaptive graph convolution circulation network traffic flow prediction method
Europäisches Patentamt | 2023
|Dynamic graph convolution traffic speed prediction method
Europäisches Patentamt | 2020
|Traffic prediction method based on dynamic graph convolution
Europäisches Patentamt | 2023
|Europäisches Patentamt | 2023
|