In EDS ansehen

i-CLTP: Integrated contrastive learning with transformer framework for traffic state prediction and network-wide analysis

Gespeichert in:
Bibliographische Detailangaben
Titel: i-CLTP: Integrated contrastive learning with transformer framework for traffic state prediction and network-wide analysis
Autoren: Jia, Ruo, 1993, Gao, Kun, 1993, Liu, Yang, 1991, Yu, Bo, Ma, Xiaolei, Ma, Zhenliang
Quelle: Digitala verktyg för hållbar planering och hantering av delad mikromobilitet med hjälp av Big Data Eldrivna multimodala transportsystem för att stärka urban tillgänglighet och konnektivitet (eMATS) Transportation Research, Part C: Emerging Technologies. 171
Schlagwörter: Soft clustering, Traffic state prediction, Fundamental diagram, Transformer, Contrastive learning
Beschreibung: Traffic state predictions are critical for the traffic management and control of transport systems. This study introduces an innovative contrastive learning framework coupled with a transformer architecture for spatiotemporal traffic state prediction, designed to capture the spatio-temporal heterogeneity inherent in traffic. The transformer structure functions as the upper level of the prediction framework to minimize the prediction errors between the input and predicted output. Based on the self-supervised contrastive learning, the lower level in the framework is proposed to discern the spatio-temporal heterogeneity and embed the latent characteristic of traffic flow by regenerating the augmentation features. Then, a soft clustering problem is applied between the upper level and lower level to category the types of traffic flow characteristics by minimizing the joint loss across each cluster. Subsequently, the proposed model is evaluated through a real-world highway traffic flow dataset for bench marking against several latest existing models. The experimental results affirm that the proposed model considerably enhances traffic state prediction accuracy. In terms of precision metrics, the model records a Mean Absolute Error of 13.31 and a Mean Absolute Percentage Error of 7.85%, reflecting marked improvements of 2.0% and 14.5% respectively over the latest and most competitive baseline model. Furthermore, the analysis reveals that capacity of the proposed method to learn the cluster patterns of spatio-temporal traffic dynamics reflected by calibrated fundamental diagrams.
Dateibeschreibung: electronic
Zugangs-URL: https://research.chalmers.se/publication/544528
https://research.chalmers.se/publication/544528/file/544528_Fulltext.pdf
Datenbank: SwePub
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://research.chalmers.se/publication/544528#
    Name: EDS - SwePub (s4221598)
    Category: fullText
    Text: View record in SwePub
  – Url: https://resolver.ebscohost.com/openurl?sid=EBSCO:edsswe&genre=article&issn=0968090X&ISBN=&volume=171&issue=&date=20250101&spage=&pages=&title=Digitala verktyg för hållbar planering och hantering av delad mikromobilitet med hjälp av Big Data Eldrivna multimodala transportsystem för att stärka urban tillgänglighet och konnektivitet (eMATS) Transportation Research, Part C: Emerging Technologies&atitle=i-CLTP%3A%20Integrated%20contrastive%20learning%20with%20transformer%20framework%20for%20traffic%20state%20prediction%20and%20network-wide%20analysis&aulast=Jia%2C%20Ruo&id=DOI:10.1016/j.trc.2024.104979
    Name: Full Text Finder
    Category: fullText
    Text: Full Text Finder
    Icon: https://imageserver.ebscohost.com/branding/images/FTF.gif
    MouseOverText: Full Text Finder
  – Url: https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=EBSCO&SrcAuth=EBSCO&DestApp=WOS&ServiceName=TransferToWoS&DestLinkType=GeneralSearchSummary&Func=Links&author=Jia%20R
    Name: ISI
    Category: fullText
    Text: Nájsť tento článok vo Web of Science
    Icon: https://imagesrvr.epnet.com/ls/20docs.gif
    MouseOverText: Nájsť tento článok vo Web of Science
Header DbId: edsswe
DbLabel: SwePub
An: edsswe.oai.research.chalmers.se.48c6b9f0.0a40.4f6e.b281.b064c19fb9c4
RelevancyScore: 1065
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 1064.736328125
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: i-CLTP: Integrated contrastive learning with transformer framework for traffic state prediction and network-wide analysis
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Jia%2C+Ruo%22">Jia, Ruo</searchLink>, 1993<br /><searchLink fieldCode="AR" term="%22Gao%2C+Kun%22">Gao, Kun</searchLink>, 1993<br /><searchLink fieldCode="AR" term="%22Liu%2C+Yang%22">Liu, Yang</searchLink>, 1991<br /><searchLink fieldCode="AR" term="%22Yu%2C+Bo%22">Yu, Bo</searchLink><br /><searchLink fieldCode="AR" term="%22Ma%2C+Xiaolei%22">Ma, Xiaolei</searchLink><br /><searchLink fieldCode="AR" term="%22Ma%2C+Zhenliang%22">Ma, Zhenliang</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <i>Digitala verktyg för hållbar planering och hantering av delad mikromobilitet med hjälp av Big Data Eldrivna multimodala transportsystem för att stärka urban tillgänglighet och konnektivitet (eMATS) Transportation Research, Part C: Emerging Technologies</i>. 171
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Soft+clustering%22">Soft clustering</searchLink><br /><searchLink fieldCode="DE" term="%22Traffic+state+prediction%22">Traffic state prediction</searchLink><br /><searchLink fieldCode="DE" term="%22Fundamental+diagram%22">Fundamental diagram</searchLink><br /><searchLink fieldCode="DE" term="%22Transformer%22">Transformer</searchLink><br /><searchLink fieldCode="DE" term="%22Contrastive+learning%22">Contrastive learning</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: Traffic state predictions are critical for the traffic management and control of transport systems. This study introduces an innovative contrastive learning framework coupled with a transformer architecture for spatiotemporal traffic state prediction, designed to capture the spatio-temporal heterogeneity inherent in traffic. The transformer structure functions as the upper level of the prediction framework to minimize the prediction errors between the input and predicted output. Based on the self-supervised contrastive learning, the lower level in the framework is proposed to discern the spatio-temporal heterogeneity and embed the latent characteristic of traffic flow by regenerating the augmentation features. Then, a soft clustering problem is applied between the upper level and lower level to category the types of traffic flow characteristics by minimizing the joint loss across each cluster. Subsequently, the proposed model is evaluated through a real-world highway traffic flow dataset for bench marking against several latest existing models. The experimental results affirm that the proposed model considerably enhances traffic state prediction accuracy. In terms of precision metrics, the model records a Mean Absolute Error of 13.31 and a Mean Absolute Percentage Error of 7.85%, reflecting marked improvements of 2.0% and 14.5% respectively over the latest and most competitive baseline model. Furthermore, the analysis reveals that capacity of the proposed method to learn the cluster patterns of spatio-temporal traffic dynamics reflected by calibrated fundamental diagrams.
– Name: Format
  Label: File Description
  Group: SrcInfo
  Data: electronic
– Name: URL
  Label: Access URL
  Group: URL
  Data: <link linkTarget="URL" linkTerm="https://research.chalmers.se/publication/544528" linkWindow="_blank">https://research.chalmers.se/publication/544528</link><br /><link linkTarget="URL" linkTerm="https://research.chalmers.se/publication/544528/file/544528_Fulltext.pdf" linkWindow="_blank">https://research.chalmers.se/publication/544528/file/544528_Fulltext.pdf</link>
PLink https://erproxy.cvtisr.sk/sfx/access?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsswe&AN=edsswe.oai.research.chalmers.se.48c6b9f0.0a40.4f6e.b281.b064c19fb9c4
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1016/j.trc.2024.104979
    Languages:
      – Text: English
    Subjects:
      – SubjectFull: Soft clustering
        Type: general
      – SubjectFull: Traffic state prediction
        Type: general
      – SubjectFull: Fundamental diagram
        Type: general
      – SubjectFull: Transformer
        Type: general
      – SubjectFull: Contrastive learning
        Type: general
    Titles:
      – TitleFull: i-CLTP: Integrated contrastive learning with transformer framework for traffic state prediction and network-wide analysis
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Jia, Ruo
      – PersonEntity:
          Name:
            NameFull: Gao, Kun
      – PersonEntity:
          Name:
            NameFull: Liu, Yang
      – PersonEntity:
          Name:
            NameFull: Yu, Bo
      – PersonEntity:
          Name:
            NameFull: Ma, Xiaolei
      – PersonEntity:
          Name:
            NameFull: Ma, Zhenliang
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 0968090X
            – Type: issn-locals
              Value: SWEPUB_FREE
            – Type: issn-locals
              Value: CTH_SWEPUB
          Numbering:
            – Type: volume
              Value: 171
          Titles:
            – TitleFull: Digitala verktyg för hållbar planering och hantering av delad mikromobilitet med hjälp av Big Data Eldrivna multimodala transportsystem för att stärka urban tillgänglighet och konnektivitet (eMATS) Transportation Research, Part C: Emerging Technologies
              Type: main
ResultId 1