Traffic Flow Prediction Based on Multi-Spatiotemporal Attention Gated Graph Convolution Network
Accurate prediction of traffic flow plays an important role in ensuring public traffic safety and solving traffic congestion. Because graph convolutional neural network (GCN) can perform effective feature calculation for unstructured data, doing research based on GCN model has become the main way fo...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-01-01
|
| Series: | Journal of Advanced Transportation |
| Online Access: | http://dx.doi.org/10.1155/2022/2723101 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832555204196696064 |
|---|---|
| author | Yun Ge Jian F. Zhai Pei C. Su |
| author_facet | Yun Ge Jian F. Zhai Pei C. Su |
| author_sort | Yun Ge |
| collection | DOAJ |
| description | Accurate prediction of traffic flow plays an important role in ensuring public traffic safety and solving traffic congestion. Because graph convolutional neural network (GCN) can perform effective feature calculation for unstructured data, doing research based on GCN model has become the main way for traffic flow prediction research. However, most of the existing research methods solving this problem are based on combining the graph convolutional neural network and recurrent neural network for traffic prediction. Such research routines have high computational cost and few attentions on impaction of different time and nodes. In order to improve the accuracy of traffic flow prediction, a gated attention graph convolution model based on multiple spatiotemporal channels was proposed in this paper. This model takes multiple time period data as input and extracts the features of each channel by superimposing multiple gated temporal and spatial attention modules. The final feature vector is obtained by means of weighted linear superposition. Experimental results on two sets of data show that the proposed method has good performance in precision and interpretability. |
| format | Article |
| id | doaj-art-cb3af482b68a43da93a02a63a5a4a97f |
| institution | Kabale University |
| issn | 2042-3195 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Advanced Transportation |
| spelling | doaj-art-cb3af482b68a43da93a02a63a5a4a97f2025-02-03T05:49:21ZengWileyJournal of Advanced Transportation2042-31952022-01-01202210.1155/2022/2723101Traffic Flow Prediction Based on Multi-Spatiotemporal Attention Gated Graph Convolution NetworkYun Ge0Jian F. Zhai1Pei C. Su2Department of Computer Teaching and ResearchDepartment of Computer Teaching and ResearchDepartment of Computer Teaching and ResearchAccurate prediction of traffic flow plays an important role in ensuring public traffic safety and solving traffic congestion. Because graph convolutional neural network (GCN) can perform effective feature calculation for unstructured data, doing research based on GCN model has become the main way for traffic flow prediction research. However, most of the existing research methods solving this problem are based on combining the graph convolutional neural network and recurrent neural network for traffic prediction. Such research routines have high computational cost and few attentions on impaction of different time and nodes. In order to improve the accuracy of traffic flow prediction, a gated attention graph convolution model based on multiple spatiotemporal channels was proposed in this paper. This model takes multiple time period data as input and extracts the features of each channel by superimposing multiple gated temporal and spatial attention modules. The final feature vector is obtained by means of weighted linear superposition. Experimental results on two sets of data show that the proposed method has good performance in precision and interpretability.http://dx.doi.org/10.1155/2022/2723101 |
| spellingShingle | Yun Ge Jian F. Zhai Pei C. Su Traffic Flow Prediction Based on Multi-Spatiotemporal Attention Gated Graph Convolution Network Journal of Advanced Transportation |
| title | Traffic Flow Prediction Based on Multi-Spatiotemporal Attention Gated Graph Convolution Network |
| title_full | Traffic Flow Prediction Based on Multi-Spatiotemporal Attention Gated Graph Convolution Network |
| title_fullStr | Traffic Flow Prediction Based on Multi-Spatiotemporal Attention Gated Graph Convolution Network |
| title_full_unstemmed | Traffic Flow Prediction Based on Multi-Spatiotemporal Attention Gated Graph Convolution Network |
| title_short | Traffic Flow Prediction Based on Multi-Spatiotemporal Attention Gated Graph Convolution Network |
| title_sort | traffic flow prediction based on multi spatiotemporal attention gated graph convolution network |
| url | http://dx.doi.org/10.1155/2022/2723101 |
| work_keys_str_mv | AT yunge trafficflowpredictionbasedonmultispatiotemporalattentiongatedgraphconvolutionnetwork AT jianfzhai trafficflowpredictionbasedonmultispatiotemporalattentiongatedgraphconvolutionnetwork AT peicsu trafficflowpredictionbasedonmultispatiotemporalattentiongatedgraphconvolutionnetwork |