| ZHANG Hong (张 红)*,LI Yang*,LUO Shengjun**,ZHANG Pengcheng*,ZHANG Xijun*,YI Min*.[J].高技术通讯(英文),2025,31(3):246~256 |
|
| A local-global dynamic hypergraph convolution with multi-head flow attention for traffic flow forecasting |
| |
| DOI：10. 3772 / j. issn. 1006-6748. 2025. 03. 004 |
| 中文关键词: |
| 英文关键词: traffic flow prediction, multi-head flow attention, graph convolution, hypergraph learning, dynamic spatio-temporal properties |
| 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)
(** School of Computer Science and Engineering, Central South University, Changsha 410017, P. R. China) | | LI Yang* | | | LUO Shengjun** | | | ZHANG Pengcheng* | | | ZHANG Xijun* | | | YI Min* | |
|
| Hits: 19 |
| Download times: 22 |
| 中文摘要: |
| |
| 英文摘要: |
| Traffic flow prediction is a crucial element of intelligent transportation systems. However, accurate traffic flow prediction is quite challenging because of its highly nonlinear, complex, and dynamic characteristics. To address the difficulties in simultaneously capturing local and global dynamic spatiotemporal correlations in traffic flow, as well as the high time complexity of existing models, a multi-head flow attention-based local-global dynamic hypergraph convolution (MFA-LGDHC) prediction model is proposed. which consists of multi-head flow attention (MHFA) mechanism, graph convolution network (GCN), and local-global dynamic hypergraph convolution (LGHC). MHFA is utilized to extract the time dependency of traffic flow and reduce the time complexity of the model.GCN is employed to catch the spatial dependency of traffic flow. LGHC utilizes down-sampling convolution and isometric convolution to capture the local and global spatial dependencies of traffic flow.And dynamic hypergraph convolution is used to model the dynamic higher-order relationships of the traffic road network. Experimental results indicate that the MFA-LGDHC model outperforms current popular baseline models and exhibits good prediction performance. |
|
View Full Text
View/Add Comment Download reader |
| Close |
|
|
|
