TEA-GCN: Transformer-Enhanced Adaptive Graph Convolutional Network for Traffic Flow Forecasting
Traffic flow forecasting is crucial for improving urban traffic management and reducing resource consumption. Accurate traffic conditions prediction requires capturing the complex spatial-temporal dependencies inherent in traffic data. Traditional spatial-temporal graph modeling methods often rely o...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/21/7086 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850062353456955392 |
|---|---|
| author | Xiaxia He Wenhui Zhang Xiaoyu Li Xiaodan Zhang |
| author_facet | Xiaxia He Wenhui Zhang Xiaoyu Li Xiaodan Zhang |
| author_sort | Xiaxia He |
| collection | DOAJ |
| description | Traffic flow forecasting is crucial for improving urban traffic management and reducing resource consumption. Accurate traffic conditions prediction requires capturing the complex spatial-temporal dependencies inherent in traffic data. Traditional spatial-temporal graph modeling methods often rely on fixed road network structures, failing to account for the dynamic spatial correlations that vary over time. To address this, we propose a Transformer-Enhanced Adaptive Graph Convolutional Network (TEA-GCN) that alternately learns temporal and spatial correlations in traffic data layer-by-layer. Specifically, we design an adaptive graph convolutional module to dynamically capture implicit road dependencies at different time levels and a local-global temporal attention module to simultaneously capture long-term and short-term temporal dependencies. Experimental results on two public traffic datasets demonstrate the effectiveness of the proposed model compared to other state-of-the-art traffic flow prediction methods. |
| format | Article |
| id | doaj-art-2e2b5fde574e40aaa2b802bdc6e36c97 |
| institution | DOAJ |
| issn | 1424-8220 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-2e2b5fde574e40aaa2b802bdc6e36c972025-08-20T02:49:56ZengMDPI AGSensors1424-82202024-11-012421708610.3390/s24217086TEA-GCN: Transformer-Enhanced Adaptive Graph Convolutional Network for Traffic Flow ForecastingXiaxia He0Wenhui Zhang1Xiaoyu Li2Xiaodan Zhang3School of Information Science and Technology, Beijing University of Technology, Beijing 100124, ChinaSchool of Information Engineering, Jiangxi Vocational College of Industry & Enginneering, Nanchang 330013, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100083, ChinaSchool of Information Science and Technology, Beijing University of Technology, Beijing 100124, ChinaTraffic flow forecasting is crucial for improving urban traffic management and reducing resource consumption. Accurate traffic conditions prediction requires capturing the complex spatial-temporal dependencies inherent in traffic data. Traditional spatial-temporal graph modeling methods often rely on fixed road network structures, failing to account for the dynamic spatial correlations that vary over time. To address this, we propose a Transformer-Enhanced Adaptive Graph Convolutional Network (TEA-GCN) that alternately learns temporal and spatial correlations in traffic data layer-by-layer. Specifically, we design an adaptive graph convolutional module to dynamically capture implicit road dependencies at different time levels and a local-global temporal attention module to simultaneously capture long-term and short-term temporal dependencies. Experimental results on two public traffic datasets demonstrate the effectiveness of the proposed model compared to other state-of-the-art traffic flow prediction methods.https://www.mdpi.com/1424-8220/24/21/7086graph convolutional networkstraffic flow forecastingadaptive graph learning |
| spellingShingle | Xiaxia He Wenhui Zhang Xiaoyu Li Xiaodan Zhang TEA-GCN: Transformer-Enhanced Adaptive Graph Convolutional Network for Traffic Flow Forecasting Sensors graph convolutional networks traffic flow forecasting adaptive graph learning |
| title | TEA-GCN: Transformer-Enhanced Adaptive Graph Convolutional Network for Traffic Flow Forecasting |
| title_full | TEA-GCN: Transformer-Enhanced Adaptive Graph Convolutional Network for Traffic Flow Forecasting |
| title_fullStr | TEA-GCN: Transformer-Enhanced Adaptive Graph Convolutional Network for Traffic Flow Forecasting |
| title_full_unstemmed | TEA-GCN: Transformer-Enhanced Adaptive Graph Convolutional Network for Traffic Flow Forecasting |
| title_short | TEA-GCN: Transformer-Enhanced Adaptive Graph Convolutional Network for Traffic Flow Forecasting |
| title_sort | tea gcn transformer enhanced adaptive graph convolutional network for traffic flow forecasting |
| topic | graph convolutional networks traffic flow forecasting adaptive graph learning |
| url | https://www.mdpi.com/1424-8220/24/21/7086 |
| work_keys_str_mv | AT xiaxiahe teagcntransformerenhancedadaptivegraphconvolutionalnetworkfortrafficflowforecasting AT wenhuizhang teagcntransformerenhancedadaptivegraphconvolutionalnetworkfortrafficflowforecasting AT xiaoyuli teagcntransformerenhancedadaptivegraphconvolutionalnetworkfortrafficflowforecasting AT xiaodanzhang teagcntransformerenhancedadaptivegraphconvolutionalnetworkfortrafficflowforecasting |