A clustering based traffic flow prediction method with dynamic spatiotemporal correlation analysis
There are significant spatiotemporal correlations among the traffic flows of neighboring road sections in the road network. Correctly identifying such correlations makes an essential contribution for improving the accuracy of traffic flow prediction. Many efforts have been made by several researcher...
Gespeichert in:
Veröffentlicht in: | Transportation (Dordrecht) 2022-06, Vol.49 (3), p.951-988 |
---|---|
Hauptverfasser: | , , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 988 |
---|---|
container_issue | 3 |
container_start_page | 951 |
container_title | Transportation (Dordrecht) |
container_volume | 49 |
creator | Ryu, Unsok Wang, Jian Pak, Unjin Kwak, Sonil Ri, Kwangchol Jang, Junhyok Sok, Kyongjin |
description | There are significant spatiotemporal correlations among the traffic flows of neighboring road sections in the road network. Correctly identifying such correlations makes an essential contribution for improving the accuracy of traffic flow prediction. Many efforts have been made by several researchers to solve this issue, but they assume that the spatiotemporal correlations among traffic flows are stationary in both time and space, i.e., the degrees to which traffic flows affect each other are fixed. In this study, we propose a clustering based traffic flow prediction method that considers the dynamic nature of spatiotemporal correlations. In order to express the short-term dependence between the target road section and neighboring ones, the spatiotemporal correlation matrices are introduced. The historical traffic data are divided into several clusters according to the similarity between spatiotemporal correlation matrices. The spatiotemporal correlation analysis and the predictor selection based on the mutual information are performed in each cluster, and the multiple prediction models are trained separately. A prediction model corresponding to the cluster to which the current traffic pattern belongs is selected to output the prediction result. Experimental results on real traffic data show that the proposed method achieves good prediction accuracy by distinguishing the heterogeneity of spatiotemporal correlations among the traffic flows. |
doi_str_mv | 10.1007/s11116-021-10200-9 |
format | Article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2667956952</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2667956952</sourcerecordid><originalsourceid>FETCH-LOGICAL-c352t-50c967149ca7b44f87b3a53d07108d666ede8e29afc47bbc5db76444676602973</originalsourceid><addsrcrecordid>eNp9kMtKAzEUhoMoWKsv4CrgOnqSyWWyLMUbFNzoOmSSjJ0yN5OU0rd37AjuPJuzON__c_gQuqVwTwHUQ6LTSAKMEgoMgOgztKBCMaJ5Ic7RAoBrwnlZXqKrlHYAIKigC1StsGv3KYfY9J-4sil4nKOt68bhuh0OeIzBNy43Q4-7kLeDx4cmb7E_9rabmDTa6ZZDNw7RttgNMYbWnnDb2_aYmnSNLmrbpnDzu5fo4-nxff1CNm_Pr-vVhrhCsEwEOC0V5dpZVXFel6oqrCg8KAqll1IGH8rAtK0dV1XlhK-U5JxLJSUwrYolupt7xzh87UPKZjfs4_REMkxKpYXUgk0UmykXh5RiqM0Ym87Go6Fgflya2aWZXJqTS6OnUDGH0vjjKcS_6n9S35j9eCI</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2667956952</pqid></control><display><type>article</type><title>A clustering based traffic flow prediction method with dynamic spatiotemporal correlation analysis</title><source>SpringerNature Journals</source><creator>Ryu, Unsok ; Wang, Jian ; Pak, Unjin ; Kwak, Sonil ; Ri, Kwangchol ; Jang, Junhyok ; Sok, Kyongjin</creator><creatorcontrib>Ryu, Unsok ; Wang, Jian ; Pak, Unjin ; Kwak, Sonil ; Ri, Kwangchol ; Jang, Junhyok ; Sok, Kyongjin</creatorcontrib><description>There are significant spatiotemporal correlations among the traffic flows of neighboring road sections in the road network. Correctly identifying such correlations makes an essential contribution for improving the accuracy of traffic flow prediction. Many efforts have been made by several researchers to solve this issue, but they assume that the spatiotemporal correlations among traffic flows are stationary in both time and space, i.e., the degrees to which traffic flows affect each other are fixed. In this study, we propose a clustering based traffic flow prediction method that considers the dynamic nature of spatiotemporal correlations. In order to express the short-term dependence between the target road section and neighboring ones, the spatiotemporal correlation matrices are introduced. The historical traffic data are divided into several clusters according to the similarity between spatiotemporal correlation matrices. The spatiotemporal correlation analysis and the predictor selection based on the mutual information are performed in each cluster, and the multiple prediction models are trained separately. A prediction model corresponding to the cluster to which the current traffic pattern belongs is selected to output the prediction result. Experimental results on real traffic data show that the proposed method achieves good prediction accuracy by distinguishing the heterogeneity of spatiotemporal correlations among the traffic flows.</description><identifier>ISSN: 0049-4488</identifier><identifier>EISSN: 1572-9435</identifier><identifier>DOI: 10.1007/s11116-021-10200-9</identifier><language>eng</language><publisher>New York: Springer US</publisher><subject>Clustering ; Correlation analysis ; Economic Geography ; Economics ; Economics and Finance ; Engineering Economics ; Heterogeneity ; Innovation/Technology Management ; Logistics ; Marketing ; Matrices ; Organization ; Prediction models ; Regional/Spatial Science ; Roads ; Roads & highways ; Traffic ; Traffic flow ; Traffic information</subject><ispartof>Transportation (Dordrecht), 2022-06, Vol.49 (3), p.951-988</ispartof><rights>The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2021</rights><rights>The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2021.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c352t-50c967149ca7b44f87b3a53d07108d666ede8e29afc47bbc5db76444676602973</citedby><cites>FETCH-LOGICAL-c352t-50c967149ca7b44f87b3a53d07108d666ede8e29afc47bbc5db76444676602973</cites><orcidid>0000-0002-7202-5464</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s11116-021-10200-9$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s11116-021-10200-9$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,780,784,27924,27925,41488,42557,51319</link.rule.ids></links><search><creatorcontrib>Ryu, Unsok</creatorcontrib><creatorcontrib>Wang, Jian</creatorcontrib><creatorcontrib>Pak, Unjin</creatorcontrib><creatorcontrib>Kwak, Sonil</creatorcontrib><creatorcontrib>Ri, Kwangchol</creatorcontrib><creatorcontrib>Jang, Junhyok</creatorcontrib><creatorcontrib>Sok, Kyongjin</creatorcontrib><title>A clustering based traffic flow prediction method with dynamic spatiotemporal correlation analysis</title><title>Transportation (Dordrecht)</title><addtitle>Transportation</addtitle><description>There are significant spatiotemporal correlations among the traffic flows of neighboring road sections in the road network. Correctly identifying such correlations makes an essential contribution for improving the accuracy of traffic flow prediction. Many efforts have been made by several researchers to solve this issue, but they assume that the spatiotemporal correlations among traffic flows are stationary in both time and space, i.e., the degrees to which traffic flows affect each other are fixed. In this study, we propose a clustering based traffic flow prediction method that considers the dynamic nature of spatiotemporal correlations. In order to express the short-term dependence between the target road section and neighboring ones, the spatiotemporal correlation matrices are introduced. The historical traffic data are divided into several clusters according to the similarity between spatiotemporal correlation matrices. The spatiotemporal correlation analysis and the predictor selection based on the mutual information are performed in each cluster, and the multiple prediction models are trained separately. A prediction model corresponding to the cluster to which the current traffic pattern belongs is selected to output the prediction result. Experimental results on real traffic data show that the proposed method achieves good prediction accuracy by distinguishing the heterogeneity of spatiotemporal correlations among the traffic flows.</description><subject>Clustering</subject><subject>Correlation analysis</subject><subject>Economic Geography</subject><subject>Economics</subject><subject>Economics and Finance</subject><subject>Engineering Economics</subject><subject>Heterogeneity</subject><subject>Innovation/Technology Management</subject><subject>Logistics</subject><subject>Marketing</subject><subject>Matrices</subject><subject>Organization</subject><subject>Prediction models</subject><subject>Regional/Spatial Science</subject><subject>Roads</subject><subject>Roads & highways</subject><subject>Traffic</subject><subject>Traffic flow</subject><subject>Traffic information</subject><issn>0049-4488</issn><issn>1572-9435</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>8G5</sourceid><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GNUQQ</sourceid><sourceid>GUQSH</sourceid><sourceid>M2O</sourceid><recordid>eNp9kMtKAzEUhoMoWKsv4CrgOnqSyWWyLMUbFNzoOmSSjJ0yN5OU0rd37AjuPJuzON__c_gQuqVwTwHUQ6LTSAKMEgoMgOgztKBCMaJ5Ic7RAoBrwnlZXqKrlHYAIKigC1StsGv3KYfY9J-4sil4nKOt68bhuh0OeIzBNy43Q4-7kLeDx4cmb7E_9rabmDTa6ZZDNw7RttgNMYbWnnDb2_aYmnSNLmrbpnDzu5fo4-nxff1CNm_Pr-vVhrhCsEwEOC0V5dpZVXFel6oqrCg8KAqll1IGH8rAtK0dV1XlhK-U5JxLJSUwrYolupt7xzh87UPKZjfs4_REMkxKpYXUgk0UmykXh5RiqM0Ym87Go6Fgflya2aWZXJqTS6OnUDGH0vjjKcS_6n9S35j9eCI</recordid><startdate>20220601</startdate><enddate>20220601</enddate><creator>Ryu, Unsok</creator><creator>Wang, Jian</creator><creator>Pak, Unjin</creator><creator>Kwak, Sonil</creator><creator>Ri, Kwangchol</creator><creator>Jang, Junhyok</creator><creator>Sok, Kyongjin</creator><general>Springer US</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7ST</scope><scope>7WY</scope><scope>7WZ</scope><scope>7XB</scope><scope>87Z</scope><scope>88I</scope><scope>8BJ</scope><scope>8FD</scope><scope>8FE</scope><scope>8FG</scope><scope>8FK</scope><scope>8FL</scope><scope>8G5</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>ATCPS</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BEZIV</scope><scope>BGLVJ</scope><scope>BHPHI</scope><scope>C1K</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FQK</scope><scope>FR3</scope><scope>FRNLG</scope><scope>F~G</scope><scope>GNUQQ</scope><scope>GUQSH</scope><scope>HCIFZ</scope><scope>JBE</scope><scope>K60</scope><scope>K6~</scope><scope>KR7</scope><scope>L.-</scope><scope>L6V</scope><scope>M0C</scope><scope>M2O</scope><scope>M2P</scope><scope>M7S</scope><scope>MBDVC</scope><scope>PATMY</scope><scope>PQBIZ</scope><scope>PQBZA</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PTHSS</scope><scope>PYCSY</scope><scope>Q9U</scope><scope>SOI</scope><orcidid>https://orcid.org/0000-0002-7202-5464</orcidid></search><sort><creationdate>20220601</creationdate><title>A clustering based traffic flow prediction method with dynamic spatiotemporal correlation analysis</title><author>Ryu, Unsok ; Wang, Jian ; Pak, Unjin ; Kwak, Sonil ; Ri, Kwangchol ; Jang, Junhyok ; Sok, Kyongjin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c352t-50c967149ca7b44f87b3a53d07108d666ede8e29afc47bbc5db76444676602973</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Clustering</topic><topic>Correlation analysis</topic><topic>Economic Geography</topic><topic>Economics</topic><topic>Economics and Finance</topic><topic>Engineering Economics</topic><topic>Heterogeneity</topic><topic>Innovation/Technology Management</topic><topic>Logistics</topic><topic>Marketing</topic><topic>Matrices</topic><topic>Organization</topic><topic>Prediction models</topic><topic>Regional/Spatial Science</topic><topic>Roads</topic><topic>Roads & highways</topic><topic>Traffic</topic><topic>Traffic flow</topic><topic>Traffic information</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Ryu, Unsok</creatorcontrib><creatorcontrib>Wang, Jian</creatorcontrib><creatorcontrib>Pak, Unjin</creatorcontrib><creatorcontrib>Kwak, Sonil</creatorcontrib><creatorcontrib>Ri, Kwangchol</creatorcontrib><creatorcontrib>Jang, Junhyok</creatorcontrib><creatorcontrib>Sok, Kyongjin</creatorcontrib><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>Environment Abstracts</collection><collection>Access via ABI/INFORM (ProQuest)</collection><collection>ABI/INFORM Global (PDF only)</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>ABI/INFORM Global (Alumni Edition)</collection><collection>Science Database (Alumni Edition)</collection><collection>International Bibliography of the Social Sciences (IBSS)</collection><collection>Technology Research Database</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ABI/INFORM Collection (Alumni Edition)</collection><collection>Research Library (Alumni Edition)</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>Agricultural & Environmental Science Collection</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Business Premium Collection</collection><collection>Technology Collection</collection><collection>Natural Science Collection</collection><collection>Environmental Sciences and Pollution Management</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>International Bibliography of the Social Sciences</collection><collection>Engineering Research Database</collection><collection>Business Premium Collection (Alumni)</collection><collection>ABI/INFORM Global (Corporate)</collection><collection>ProQuest Central Student</collection><collection>Research Library Prep</collection><collection>SciTech Premium Collection</collection><collection>International Bibliography of the Social Sciences</collection><collection>ProQuest Business Collection (Alumni Edition)</collection><collection>ProQuest Business Collection</collection><collection>Civil Engineering Abstracts</collection><collection>ABI/INFORM Professional Advanced</collection><collection>ProQuest Engineering Collection</collection><collection>ABI/INFORM Global</collection><collection>Research Library</collection><collection>Science Database</collection><collection>Engineering Database</collection><collection>Research Library (Corporate)</collection><collection>Environmental Science Database</collection><collection>ProQuest One Business</collection><collection>ProQuest One Business (Alumni)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>Engineering Collection</collection><collection>Environmental Science Collection</collection><collection>ProQuest Central Basic</collection><collection>Environment Abstracts</collection><jtitle>Transportation (Dordrecht)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Ryu, Unsok</au><au>Wang, Jian</au><au>Pak, Unjin</au><au>Kwak, Sonil</au><au>Ri, Kwangchol</au><au>Jang, Junhyok</au><au>Sok, Kyongjin</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A clustering based traffic flow prediction method with dynamic spatiotemporal correlation analysis</atitle><jtitle>Transportation (Dordrecht)</jtitle><stitle>Transportation</stitle><date>2022-06-01</date><risdate>2022</risdate><volume>49</volume><issue>3</issue><spage>951</spage><epage>988</epage><pages>951-988</pages><issn>0049-4488</issn><eissn>1572-9435</eissn><abstract>There are significant spatiotemporal correlations among the traffic flows of neighboring road sections in the road network. Correctly identifying such correlations makes an essential contribution for improving the accuracy of traffic flow prediction. Many efforts have been made by several researchers to solve this issue, but they assume that the spatiotemporal correlations among traffic flows are stationary in both time and space, i.e., the degrees to which traffic flows affect each other are fixed. In this study, we propose a clustering based traffic flow prediction method that considers the dynamic nature of spatiotemporal correlations. In order to express the short-term dependence between the target road section and neighboring ones, the spatiotemporal correlation matrices are introduced. The historical traffic data are divided into several clusters according to the similarity between spatiotemporal correlation matrices. The spatiotemporal correlation analysis and the predictor selection based on the mutual information are performed in each cluster, and the multiple prediction models are trained separately. A prediction model corresponding to the cluster to which the current traffic pattern belongs is selected to output the prediction result. Experimental results on real traffic data show that the proposed method achieves good prediction accuracy by distinguishing the heterogeneity of spatiotemporal correlations among the traffic flows.</abstract><cop>New York</cop><pub>Springer US</pub><doi>10.1007/s11116-021-10200-9</doi><tpages>38</tpages><orcidid>https://orcid.org/0000-0002-7202-5464</orcidid></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0049-4488 |
ispartof | Transportation (Dordrecht), 2022-06, Vol.49 (3), p.951-988 |
issn | 0049-4488 1572-9435 |
language | eng |
recordid | cdi_proquest_journals_2667956952 |
source | SpringerNature Journals |
subjects | Clustering Correlation analysis Economic Geography Economics Economics and Finance Engineering Economics Heterogeneity Innovation/Technology Management Logistics Marketing Matrices Organization Prediction models Regional/Spatial Science Roads Roads & highways Traffic Traffic flow Traffic information |
title | A clustering based traffic flow prediction method with dynamic spatiotemporal correlation analysis |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T14%3A52%3A57IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20clustering%20based%20traffic%20flow%20prediction%20method%20with%20dynamic%20spatiotemporal%20correlation%20analysis&rft.jtitle=Transportation%20(Dordrecht)&rft.au=Ryu,%20Unsok&rft.date=2022-06-01&rft.volume=49&rft.issue=3&rft.spage=951&rft.epage=988&rft.pages=951-988&rft.issn=0049-4488&rft.eissn=1572-9435&rft_id=info:doi/10.1007/s11116-021-10200-9&rft_dat=%3Cproquest_cross%3E2667956952%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2667956952&rft_id=info:pmid/&rfr_iscdi=true |