Sequential Graph Neural Network for Urban Road Traffic Speed Prediction
Accurate speed predictions for urban roads are highly important for traffic monitoring and route planning, and also help relieve the pressure of traffic congestion. Many existing studies on traffic speed prediction are based on convolutional neural networks, and these have primarily focused on captu...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8708297/ |
id |
doaj-be69f0d9a27148ccb1bbe7b3676cee9c |
---|---|
record_format |
Article |
spelling |
doaj-be69f0d9a27148ccb1bbe7b3676cee9c2021-03-30T01:32:47ZengIEEEIEEE Access2169-35362020-01-018633496335810.1109/ACCESS.2019.29153648708297Sequential Graph Neural Network for Urban Road Traffic Speed PredictionZhipu Xie0https://orcid.org/0000-0003-0652-0683Weifeng Lv1Shangfo Huang2Zhilong Lu3Bowen Du4Runhe Huang5Key State Laboratory of Software Development Environment, Beihang University, Beijing, ChinaKey State Laboratory of Software Development Environment, Beihang University, Beijing, ChinaKey State Laboratory of Software Development Environment, Beihang University, Beijing, ChinaKey State Laboratory of Software Development Environment, Beihang University, Beijing, ChinaKey State Laboratory of Software Development Environment, Beihang University, Beijing, ChinaHosei University, Tokyo, JapanAccurate speed predictions for urban roads are highly important for traffic monitoring and route planning, and also help relieve the pressure of traffic congestion. Many existing studies on traffic speed prediction are based on convolutional neural networks, and these have primarily focused on capturing the spatial proximity among different road segments. However, the real cause of the spread of traffic congestion is the connectivity of these road segments, rather than their spatial proximity. This makes it very challenging to improve prediction accuracy. Using graph neural networks (GNNs), the connectivity of these road segments can be modeled as a graph in which the properties of road segments and the connections between them are embedded as the properties of the nodes and edges, respectively. This paper describes a novel approach that combines the advantages of sequence-to-sequence (Seq2Seq) models and GNNs. Specifically, the evolution of traffic conditions on road networks is modeled as a sequence of graphs. Thus, the proposed SeqGNN model represents both the inputs and outputs as graph sequences. Finally, the extensive experiments using real-world datasets demonstrate the effectiveness of our approach and its advantages over the state-of-the-art methods.https://ieeexplore.ieee.org/document/8708297/Graph neural networkSeq2Seqtraffic speed prediction |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Zhipu Xie Weifeng Lv Shangfo Huang Zhilong Lu Bowen Du Runhe Huang |
spellingShingle |
Zhipu Xie Weifeng Lv Shangfo Huang Zhilong Lu Bowen Du Runhe Huang Sequential Graph Neural Network for Urban Road Traffic Speed Prediction IEEE Access Graph neural network Seq2Seq traffic speed prediction |
author_facet |
Zhipu Xie Weifeng Lv Shangfo Huang Zhilong Lu Bowen Du Runhe Huang |
author_sort |
Zhipu Xie |
title |
Sequential Graph Neural Network for Urban Road Traffic Speed Prediction |
title_short |
Sequential Graph Neural Network for Urban Road Traffic Speed Prediction |
title_full |
Sequential Graph Neural Network for Urban Road Traffic Speed Prediction |
title_fullStr |
Sequential Graph Neural Network for Urban Road Traffic Speed Prediction |
title_full_unstemmed |
Sequential Graph Neural Network for Urban Road Traffic Speed Prediction |
title_sort |
sequential graph neural network for urban road traffic speed prediction |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
Accurate speed predictions for urban roads are highly important for traffic monitoring and route planning, and also help relieve the pressure of traffic congestion. Many existing studies on traffic speed prediction are based on convolutional neural networks, and these have primarily focused on capturing the spatial proximity among different road segments. However, the real cause of the spread of traffic congestion is the connectivity of these road segments, rather than their spatial proximity. This makes it very challenging to improve prediction accuracy. Using graph neural networks (GNNs), the connectivity of these road segments can be modeled as a graph in which the properties of road segments and the connections between them are embedded as the properties of the nodes and edges, respectively. This paper describes a novel approach that combines the advantages of sequence-to-sequence (Seq2Seq) models and GNNs. Specifically, the evolution of traffic conditions on road networks is modeled as a sequence of graphs. Thus, the proposed SeqGNN model represents both the inputs and outputs as graph sequences. Finally, the extensive experiments using real-world datasets demonstrate the effectiveness of our approach and its advantages over the state-of-the-art methods. |
topic |
Graph neural network Seq2Seq traffic speed prediction |
url |
https://ieeexplore.ieee.org/document/8708297/ |
work_keys_str_mv |
AT zhipuxie sequentialgraphneuralnetworkforurbanroadtrafficspeedprediction AT weifenglv sequentialgraphneuralnetworkforurbanroadtrafficspeedprediction AT shangfohuang sequentialgraphneuralnetworkforurbanroadtrafficspeedprediction AT zhilonglu sequentialgraphneuralnetworkforurbanroadtrafficspeedprediction AT bowendu sequentialgraphneuralnetworkforurbanroadtrafficspeedprediction AT runhehuang sequentialgraphneuralnetworkforurbanroadtrafficspeedprediction |
_version_ |
1724186827491901440 |