Modeling Global Spatial–Temporal Graph Attention Network for Traffic Prediction
Accurate and efficient traffic prediction is the key to the realization of intelligent transportation system (ITS), which helps to alleviate traffic congestion and reduce traffic accidents. Due to the complex dynamic spatial-temporal dependence between traffic networks, traffic prediction is extreme...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2021-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9316302/ |
id |
doaj-e24c9ae305bd464598886b5041b672e4 |
---|---|
record_format |
Article |
spelling |
doaj-e24c9ae305bd464598886b5041b672e42021-03-30T14:48:26ZengIEEEIEEE Access2169-35362021-01-0198581859410.1109/ACCESS.2021.30495569316302Modeling Global Spatial–Temporal Graph Attention Network for Traffic PredictionBin Sun0https://orcid.org/0000-0003-0652-3999Duan Zhao1https://orcid.org/0000-0002-9679-3943Xinguo Shi2Yongxin He3https://orcid.org/0000-0002-3014-0798National and Local Joint Engineering Laboratory of Internet Application Technology on Mine, China University of Mining and Technology, Xuzhou, ChinaNational and Local Joint Engineering Laboratory of Internet Application Technology on Mine, China University of Mining and Technology, Xuzhou, ChinaInformation Center, Shandong Energy Zibo Mining Group Company, Ltd., Zibo, ChinaNational and Local Joint Engineering Laboratory of Internet Application Technology on Mine, China University of Mining and Technology, Xuzhou, ChinaAccurate and efficient traffic prediction is the key to the realization of intelligent transportation system (ITS), which helps to alleviate traffic congestion and reduce traffic accidents. Due to the complex dynamic spatial-temporal dependence between traffic networks, traffic prediction is extremely challenging. In previous studies, convolution neural network (CNN) and graph convolution network (GCN) were used to model spatial correlation. However, the non-Euclidean correlation of road network reduces the effect of convolution operator modeling. In addition, only considering the traffic interaction around the concerned points simplifies the influence of traffic network. In order to address the above problems, this article proposes an end-to-end global spatial-temporal graph attention network (GST-GAT), which uses the “global interaction + node query” to model the dynamic spatial-temporal correlation of traffic. In the encoder, the long short-term memory (LSTM) component flexibly transforms the traffic dynamic spatial-temporal graph into feedforward differentiable features. Global traffic interaction is proposed to summarize traffic network context changes and integrate all node features at each moment through a forward calculation. Then, each node computes the influence of traffic global interaction on a single node in parallel, and the spatial-temporal interaction information is adaptive fused by gating fusion mechanism. Finally, the end-to-end network structure is used to train the rich mixed feature coding to generate the traffic prediction status of each node. Experiments on public transportation data sets show that GST-GAT performs better than previous work in terms of accuracy and inference speed.https://ieeexplore.ieee.org/document/9316302/Intelligent transportation systemglobal spatial-temporal graphtraffic prediction |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Bin Sun Duan Zhao Xinguo Shi Yongxin He |
spellingShingle |
Bin Sun Duan Zhao Xinguo Shi Yongxin He Modeling Global Spatial–Temporal Graph Attention Network for Traffic Prediction IEEE Access Intelligent transportation system global spatial-temporal graph traffic prediction |
author_facet |
Bin Sun Duan Zhao Xinguo Shi Yongxin He |
author_sort |
Bin Sun |
title |
Modeling Global Spatial–Temporal Graph Attention Network for Traffic Prediction |
title_short |
Modeling Global Spatial–Temporal Graph Attention Network for Traffic Prediction |
title_full |
Modeling Global Spatial–Temporal Graph Attention Network for Traffic Prediction |
title_fullStr |
Modeling Global Spatial–Temporal Graph Attention Network for Traffic Prediction |
title_full_unstemmed |
Modeling Global Spatial–Temporal Graph Attention Network for Traffic Prediction |
title_sort |
modeling global spatial–temporal graph attention network for traffic prediction |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2021-01-01 |
description |
Accurate and efficient traffic prediction is the key to the realization of intelligent transportation system (ITS), which helps to alleviate traffic congestion and reduce traffic accidents. Due to the complex dynamic spatial-temporal dependence between traffic networks, traffic prediction is extremely challenging. In previous studies, convolution neural network (CNN) and graph convolution network (GCN) were used to model spatial correlation. However, the non-Euclidean correlation of road network reduces the effect of convolution operator modeling. In addition, only considering the traffic interaction around the concerned points simplifies the influence of traffic network. In order to address the above problems, this article proposes an end-to-end global spatial-temporal graph attention network (GST-GAT), which uses the “global interaction + node query” to model the dynamic spatial-temporal correlation of traffic. In the encoder, the long short-term memory (LSTM) component flexibly transforms the traffic dynamic spatial-temporal graph into feedforward differentiable features. Global traffic interaction is proposed to summarize traffic network context changes and integrate all node features at each moment through a forward calculation. Then, each node computes the influence of traffic global interaction on a single node in parallel, and the spatial-temporal interaction information is adaptive fused by gating fusion mechanism. Finally, the end-to-end network structure is used to train the rich mixed feature coding to generate the traffic prediction status of each node. Experiments on public transportation data sets show that GST-GAT performs better than previous work in terms of accuracy and inference speed. |
topic |
Intelligent transportation system global spatial-temporal graph traffic prediction |
url |
https://ieeexplore.ieee.org/document/9316302/ |
work_keys_str_mv |
AT binsun modelingglobalspatialx2013temporalgraphattentionnetworkfortrafficprediction AT duanzhao modelingglobalspatialx2013temporalgraphattentionnetworkfortrafficprediction AT xinguoshi modelingglobalspatialx2013temporalgraphattentionnetworkfortrafficprediction AT yongxinhe modelingglobalspatialx2013temporalgraphattentionnetworkfortrafficprediction |
_version_ |
1724180496339959808 |