On the imputation of missing data for road traffic forecasting: New insights and novel techniques: New insights and novel techniques

Simple item page
dc.contributor.authorLaña, Ibai
dc.contributor.authorOlabarrieta, Ignacio (Iñaki)
dc.contributor.authorVélez, Manuel
dc.contributor.authorDel Ser, Javier
dc.contributor.institutionIA
dc.date.issued2018-05
dc.descriptionPublisher Copyright: © 2018 Elsevier Ltd
dc.description.abstractVehicle flow forecasting is of crucial importance for the management of road traffic in complex urban networks, as well as a useful input for route planning algorithms. In general traffic predictive models rely on data gathered by different types of sensors placed on roads, which occasionally produce faulty readings due to several causes, such as malfunctioning hardware or transmission errors. Filling in those gaps is relevant for constructing accurate forecasting models, a task which is engaged by diverse strategies, from a simple null value imputation to complex spatio-temporal context imputation models. This work elaborates on two machine learning approaches to update missing data with no gap length restrictions: a spatial context sensing model based on the information provided by surrounding sensors, and an automated clustering analysis tool that seeks optimal pattern clusters in order to impute values. Their performance is assessed and compared to other common techniques and different missing data generation models over real data captured from the city of Madrid (Spain). The newly presented methods are found to be fairly superior when portions of missing data are large or very abundant, as occurs in most practical cases.en
dc.description.statusPeer reviewed
dc.format.extent16
dc.format.extent2412545
dc.identifier.citationLaña , I , Olabarrieta , I , Vélez , M & Del Ser , J 2018 , ' On the imputation of missing data for road traffic forecasting: New insights and novel techniques : New insights and novel techniques ' , Transportation Research Part C: Emerging Technologies , vol. 90 , pp. 18-33 . https://doi.org/10.1016/j.trc.2018.02.021
dc.identifier.doi10.1016/j.trc.2018.02.021
dc.identifier.issn0968-090X
dc.identifier.otherresearchoutputwizard: 11556/523
dc.identifier.urlhttp://www.scopus.com/inward/record.url?scp=85043226955&partnerID=8YFLogxK
dc.language.isoeng
dc.relation.ispartofTransportation Research Part C: Emerging Technologies
dc.rightsinfo:eu-repo/semantics/restrictedAccess
dc.subject.keywordsTraffic forecasting
dc.subject.keywordsMissing data
dc.subject.keywordsCluster analysis
dc.subject.keywordsData imputation
dc.subject.keywordsTraffic forecasting
dc.subject.keywordsMissing data
dc.subject.keywordsCluster analysis
dc.subject.keywordsData imputation
dc.subject.keywordsCivil and Structural Engineering
dc.subject.keywordsAutomotive Engineering
dc.subject.keywordsTransportation
dc.subject.keywordsManagement Science and Operations Research
dc.subject.keywordsProject ID
dc.subject.keywordsinfo:eu-repo/grantAgreement/EC/H2020/691735/EU/REnaissance of Places with Innovative Citizenship and TEchnolgy/REPLICATE
dc.subject.keywordsinfo:eu-repo/grantAgreement/EC/H2020/691735/EU/REnaissance of Places with Innovative Citizenship and TEchnolgy/REPLICATE
dc.subject.keywordsFunding Info
dc.subject.keywordsThis work has been supported by the Basque Government through the ELKARTEK program (Ref. KK-2015/0000080 and the_x000D_ BID3ABI project), as well as by the H2020 programme of the European Commission (Grant No. 691735).
dc.subject.keywordsThis work has been supported by the Basque Government through the ELKARTEK program (Ref. KK-2015/0000080 and the_x000D_ BID3ABI project), as well as by the H2020 programme of the European Commission (Grant No. 691735).
dc.titleOn the imputation of missing data for road traffic forecasting: New insights and novel techniques: New insights and novel techniquesen
dc.typejournal article
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
main_.pdf
Size:
2.3 MB
Format:
Adobe Portable Document Format
Download