File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: A macro–micro spatio-temporal neural network for traffic prediction

TitleA macro–micro spatio-temporal neural network for traffic prediction
Authors
KeywordsAttention mechanism
Graph convolution
Traffic prediction
Urban computing
Issue Date1-Jul-2023
PublisherElsevier
Citation
Transportation Research Part C: Emerging Technologies, 2023, v. 156 How to Cite?
AbstractAccurate traffic prediction is crucial for planning, management and control of intelligent transportation systems. Most state-of-the-art methods for traffic prediction effectively capture complex traffic patterns (e.g. spatial and temporal correlations of traffic data) by employing spatio-temporal neural networks as prediction models, together with graph convolution networks to learn spatial correlations of prediction objects (e.g. traffic states of road segments, as in this study). Such spatial correlations can be regarded as micro correlations. However, there are also macro correlations between regions, each of which is composed of multiple road segments or artificially partitioned areas. Macro correlations represent another type of interaction within road segments, and should be carefully considered when predicting traffic. The diversity of micro spatial correlations and corresponding macro spatial correlations (e.g. correlations based on physical proximity or traffic pattern similarity) further increases the complexity of traffic prediction. We overcome these challenges by developing a macro–micro spatio-temporal neural network model, denoted ‘MMSTNet’. MMSTNet captures spatio-temporal patterns by (a) utilizing a graph convolution network and a spatial attention network to capture micro and macro spatial correlations, respectively; (b) employing a temporal convolution network and a temporal attention network to learn temporal patterns; and (c) integrating hierarchically learned representations based on designed attention mechanisms. We perform evaluations on two real-world datasets and thereby demonstrate that MMSTNet outperforms state-of-the-art models in traffic prediction tasks.
Persistent Identifierhttp://hdl.handle.net/10722/337919
ISSN
2023 Impact Factor: 7.6
2023 SCImago Journal Rankings: 2.860
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorFeng, S-
dc.contributor.authorWei, S-
dc.contributor.authorZhang, J-
dc.contributor.authorLi, Y-
dc.contributor.authorKe, J-
dc.contributor.authorChen, G-
dc.contributor.authorZheng, Y-
dc.contributor.authorYang, H-
dc.date.accessioned2024-03-11T10:24:55Z-
dc.date.available2024-03-11T10:24:55Z-
dc.date.issued2023-07-01-
dc.identifier.citationTransportation Research Part C: Emerging Technologies, 2023, v. 156-
dc.identifier.issn0968-090X-
dc.identifier.urihttp://hdl.handle.net/10722/337919-
dc.description.abstractAccurate traffic prediction is crucial for planning, management and control of intelligent transportation systems. Most state-of-the-art methods for traffic prediction effectively capture complex traffic patterns (e.g. spatial and temporal correlations of traffic data) by employing spatio-temporal neural networks as prediction models, together with graph convolution networks to learn spatial correlations of prediction objects (e.g. traffic states of road segments, as in this study). Such spatial correlations can be regarded as micro correlations. However, there are also macro correlations between regions, each of which is composed of multiple road segments or artificially partitioned areas. Macro correlations represent another type of interaction within road segments, and should be carefully considered when predicting traffic. The diversity of micro spatial correlations and corresponding macro spatial correlations (e.g. correlations based on physical proximity or traffic pattern similarity) further increases the complexity of traffic prediction. We overcome these challenges by developing a macro–micro spatio-temporal neural network model, denoted ‘MMSTNet’. MMSTNet captures spatio-temporal patterns by (a) utilizing a graph convolution network and a spatial attention network to capture micro and macro spatial correlations, respectively; (b) employing a temporal convolution network and a temporal attention network to learn temporal patterns; and (c) integrating hierarchically learned representations based on designed attention mechanisms. We perform evaluations on two real-world datasets and thereby demonstrate that MMSTNet outperforms state-of-the-art models in traffic prediction tasks.-
dc.languageeng-
dc.publisherElsevier-
dc.relation.ispartofTransportation Research Part C: Emerging Technologies-
dc.rightsThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.-
dc.subjectAttention mechanism-
dc.subjectGraph convolution-
dc.subjectTraffic prediction-
dc.subjectUrban computing-
dc.titleA macro–micro spatio-temporal neural network for traffic prediction-
dc.typeArticle-
dc.identifier.doi10.1016/j.trc.2023.104331-
dc.identifier.scopuseid_2-s2.0-85171615699-
dc.identifier.volume156-
dc.identifier.eissn1879-2359-
dc.identifier.isiWOS:001165066900001-
dc.identifier.issnl0968-090X-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats