| ZHANG Hong(张 红),GONG Lei,ZHAO Tianxin,ZHANG Xijun,WANG Hongyan.[J].高技术通讯(英文),2024,30(4):370~379 |
|
| Local-global dynamic correlations based spatial-temporal convolutional network for traffic flow forecasting |
| |
| DOI：10. 3772 / j. issn. 1006-6748. 2024. 04. 004 |
| 中文关键词: |
| 英文关键词: traffic flow forecasting, graph convolutional network (GCN), temporal convolutional network (TCN), attention mechanism (AM) |
| 基金项目: |
| Author Name | Affiliation | | ZHANG Hong(张 红) | (College of Computer and Communication, Lanzhou University of Technology, Lanzhou 730050, P. R. China) | | GONG Lei | | | ZHAO Tianxin | | | ZHANG Xijun | | | WANG Hongyan | |
|
| Hits: 60 |
| Download times: 94 |
| 中文摘要: |
| |
| 英文摘要: |
| Traffic flow forecasting plays a crucial role and is the key technology to realize dynamic traffic guidance and active traffic control in intelligent traffic systems (ITS). Aiming at the complex local and global spatial-temporal dynamic characteristics of traffic flow, this paper proposes a new traffic flow forecasting model spatial-temporal attention graph neural network (STA-GNN) by combining attention mechanism (AM) and spatial-temporal convolutional network. The model learns the hidden dynamic local spatial correlations of the traffic network by combining the dynamic adjacency matrix constructed by the graph learning layer with the graph convolutional network (GCN). The local temporal correlations of traffic flow at different scales are extracted by stacking multiple convolutional kernels in temporal convolutional network (TCN). And the global spatial-temporal dependencies of long-time sequences of traffic flow are captured by the spatial-temporal attention mechanism (STAtt), which enhances the global spatial-temporal modeling and the representational ability of model. The experimental results on two datasets, METR-LA and PEMS-BAY, show the proposed STA-GNN model outperforms the common baseline models in forecasting accuracy. |
|
View Full Text
View/Add Comment Download reader |
| Close |
|
|
|
