Please use this identifier to cite or link to this item: https://research.matf.bg.ac.rs/handle/123456789/1292
DC FieldValueLanguage
dc.contributor.authorPetrović, Andrijaen_US
dc.contributor.authorRadovanović, Sandroen_US
dc.contributor.authorNikolić, Mladenen_US
dc.contributor.authorDelibašić, Borisen_US
dc.contributor.authorJovanović, Milošen_US
dc.date.accessioned2024-06-03T16:38:20Z-
dc.date.available2024-06-03T16:38:20Z-
dc.date.issued2023-01-01-
dc.identifier.issn15684946-
dc.identifier.urihttps://research.matf.bg.ac.rs/handle/123456789/1292-
dc.description.abstractCurrently, one of the biggest challenges in modern traffic engineering is related to traffic state estimation (TSE). Although many machine learning and domain models can be used for TSE, they do not consider the sparsity and spatial dependence of traffic state variables. In this paper, we propose a hybrid soft computing model of two Gaussian conditional random field (GCRF) models for the inference of traffic speed, which is a relevant variable for TSE and travel information systems. The proposed model can infer the traffic state variables in large-scale networks whose nodes are geographically dispersed. Moreover, by combining a Gaussian conditional random field binary classification model (GCRFBC), which classifies traffic regimes as free-flow or potentially congested, and a regression GCRF model for the prediction of traffic speed in potentially congested traffic regimes, the model addresses two specifics of the problem: sparsity in traffic data, and the fact that observations are not independent. The proposed model was tested on two large-scale real-world networks in Serbia, namely an arterial E70-E75 335 km long highway stretch and the major ski resort Kopaonik with 55 km of ski slopes. In addition, the proposed model showed better prediction performance than several other unstructured and structured models.en_US
dc.language.isoenen_US
dc.publisherElsevieren_US
dc.relation.ispartofApplied Soft Computingen_US
dc.rightsAttribution-NonCommercial-NoDerivs 3.0 United States*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/us/*
dc.subjectClassificationen_US
dc.subjectConditional random fieldsen_US
dc.subjectLarge-scale networksen_US
dc.subjectStructured regressionen_US
dc.subjectTraffic state estimationen_US
dc.titleStructured prediction of sparse dependent variables for traffic state estimation in large-scale networksen_US
dc.typeArticleen_US
dc.identifier.doi10.1016/j.asoc.2022.109893-
dc.identifier.scopus2-s2.0-85144626359-
dc.identifier.isi000993713200001-
dc.identifier.urlhttps://api.elsevier.com/content/abstract/scopus_id/85144626359-
dc.contributor.affiliationInformatics and Computer Scienceen_US
dc.relation.issn1568-4946en_US
dc.description.rankM21aen_US
dc.relation.firstpageArticle no. 109893en_US
dc.relation.volume133en_US
item.fulltextWith Fulltext-
item.languageiso639-1en-
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
item.cerifentitytypePublications-
item.grantfulltextembargo_20250131-
item.openairetypeArticle-
crisitem.author.deptInformatics and Computer Science-
Appears in Collections:Research outputs
Files in This Item:
File Description SizeFormat Existing users please
AppliedSoftComputing202301.pdf1.53 MBAdobe PDF
Embargoed until January 31, 2025    Request a copy
Show simple item record

Page view(s)

11
checked on Dec 24, 2024

Google ScholarTM

Check

Altmetric

Altmetric


This item is licensed under a Creative Commons License Creative Commons