sAMDGCN: sLSTM-Attention-Based Multi-Head Dynamic Graph Convolutional Network for Traffic Flow Forecasting
Accurate traffic flow prediction plays a vital role in intelligent transportation systems, helping traffic management departments maintain stable traffic order, reduce traffic congestion, and improve road safety. Existing prediction methods focus on dynamic modeling of the spatiotemporal dependencie...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/13/2/185 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588038180438016 |
|---|---|
| author | Shiyuan Zhang Yanni Ju Weishan Kong Hong Qu Liwei Huang |
| author_facet | Shiyuan Zhang Yanni Ju Weishan Kong Hong Qu Liwei Huang |
| author_sort | Shiyuan Zhang |
| collection | DOAJ |
| description | Accurate traffic flow prediction plays a vital role in intelligent transportation systems, helping traffic management departments maintain stable traffic order, reduce traffic congestion, and improve road safety. Existing prediction methods focus on dynamic modeling of the spatiotemporal dependencies of traffic flow, capturing the periodicity and spatial heterogeneity in traffic data. However, they still suffer from a lack of focus on the important local information in long-term predictions, leading to overly smooth results that fail to effectively capture sudden changes in traffic patterns. To address these limitations, we propose the sLSTM-Attention-Based Multi-Head Dynamic Graph Convolutional Network (sAMDGCN) model. Specifically, we extend sLSTM and introduce temporal trend-aware multi-head attention to jointly capture the complex temporal dependencies. We propose a multi-head dynamic graph convolutional network to capture a wider range of dynamic spatial dependencies. To validate the effectiveness of sAMDGCN, we perform extensive experiments on four real-world traffic flow datasets. Experimental results show that our proposed sAMDGCN model outperforms the advanced baseline methods in long-term traffic flow prediction tasks, demonstrating its superior performance in capturing complex and dynamic traffic patterns. |
| format | Article |
| id | doaj-art-06012c4f05f143bca77344e9bd2e1491 |
| institution | Kabale University |
| issn | 2227-7390 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj-art-06012c4f05f143bca77344e9bd2e14912025-01-24T13:39:40ZengMDPI AGMathematics2227-73902025-01-0113218510.3390/math13020185sAMDGCN: sLSTM-Attention-Based Multi-Head Dynamic Graph Convolutional Network for Traffic Flow ForecastingShiyuan Zhang0Yanni Ju1Weishan Kong2Hong Qu3Liwei Huang4School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaDepartment of Road Traffic Management, Sichuan Police College, Luzhou 646000, ChinaSchool of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaAccurate traffic flow prediction plays a vital role in intelligent transportation systems, helping traffic management departments maintain stable traffic order, reduce traffic congestion, and improve road safety. Existing prediction methods focus on dynamic modeling of the spatiotemporal dependencies of traffic flow, capturing the periodicity and spatial heterogeneity in traffic data. However, they still suffer from a lack of focus on the important local information in long-term predictions, leading to overly smooth results that fail to effectively capture sudden changes in traffic patterns. To address these limitations, we propose the sLSTM-Attention-Based Multi-Head Dynamic Graph Convolutional Network (sAMDGCN) model. Specifically, we extend sLSTM and introduce temporal trend-aware multi-head attention to jointly capture the complex temporal dependencies. We propose a multi-head dynamic graph convolutional network to capture a wider range of dynamic spatial dependencies. To validate the effectiveness of sAMDGCN, we perform extensive experiments on four real-world traffic flow datasets. Experimental results show that our proposed sAMDGCN model outperforms the advanced baseline methods in long-term traffic flow prediction tasks, demonstrating its superior performance in capturing complex and dynamic traffic patterns.https://www.mdpi.com/2227-7390/13/2/185traffic flow predictionspatiotemporal dependencysLSTMattentiongraph convolutional network |
| spellingShingle | Shiyuan Zhang Yanni Ju Weishan Kong Hong Qu Liwei Huang sAMDGCN: sLSTM-Attention-Based Multi-Head Dynamic Graph Convolutional Network for Traffic Flow Forecasting Mathematics traffic flow prediction spatiotemporal dependency sLSTM attention graph convolutional network |
| title | sAMDGCN: sLSTM-Attention-Based Multi-Head Dynamic Graph Convolutional Network for Traffic Flow Forecasting |
| title_full | sAMDGCN: sLSTM-Attention-Based Multi-Head Dynamic Graph Convolutional Network for Traffic Flow Forecasting |
| title_fullStr | sAMDGCN: sLSTM-Attention-Based Multi-Head Dynamic Graph Convolutional Network for Traffic Flow Forecasting |
| title_full_unstemmed | sAMDGCN: sLSTM-Attention-Based Multi-Head Dynamic Graph Convolutional Network for Traffic Flow Forecasting |
| title_short | sAMDGCN: sLSTM-Attention-Based Multi-Head Dynamic Graph Convolutional Network for Traffic Flow Forecasting |
| title_sort | samdgcn slstm attention based multi head dynamic graph convolutional network for traffic flow forecasting |
| topic | traffic flow prediction spatiotemporal dependency sLSTM attention graph convolutional network |
| url | https://www.mdpi.com/2227-7390/13/2/185 |
| work_keys_str_mv | AT shiyuanzhang samdgcnslstmattentionbasedmultiheaddynamicgraphconvolutionalnetworkfortrafficflowforecasting AT yanniju samdgcnslstmattentionbasedmultiheaddynamicgraphconvolutionalnetworkfortrafficflowforecasting AT weishankong samdgcnslstmattentionbasedmultiheaddynamicgraphconvolutionalnetworkfortrafficflowforecasting AT hongqu samdgcnslstmattentionbasedmultiheaddynamicgraphconvolutionalnetworkfortrafficflowforecasting AT liweihuang samdgcnslstmattentionbasedmultiheaddynamicgraphconvolutionalnetworkfortrafficflowforecasting |