Transfer Learning and Online Learning for Traffic Forecasting under Different Data Availability Conditions: Alternatives and Pitfalls

Simple item page
dc.contributor.authorManibardo, Eric L.
dc.contributor.authorLaña, Ibai
dc.contributor.authorDel Ser, Javier
dc.contributor.institutionIA
dc.date.issued2020-09-20
dc.descriptionPublisher Copyright: © 2020 IEEE.
dc.description.abstractThis work aims at unveiling the potential of Transfer Learning (TL) for developing a traffic flow forecasting model in scenarios of absent data. Knowledge transfer from high-quality predictive models becomes feasible under the TL paradigm, enabling the generation of new proper models with few data. In order to explore this capability, we identify three different levels of data absent scenarios, where TL techniques are applied among Deep Learning (DL) methods for traffic forecasting. Then, traditional batch learning is compared against TL based models using real traffic flow data, collected by deployed loops managed by the City Council of Madrid (Spain). In addition, we apply Online Learning (OL) techniques, where model receives an update after each prediction, in order to adapt to traffic flow trend changes and incrementally learn from new incoming traffic data. The obtained experimental results shed light on the advantages of transfer and online learning for traffic flow forecasting, and draw practical insights on their interplay with the amount of available training data at the location of interest.en
dc.description.sponsorshipThe authors thank the Basque Government for its support through the Consolidated Research Group MATHMODE (IT1294-19), EMAITEK and ELKARTEK programs, as well as the Spanish Centro para el Desarrollo Tecnologico Industrial (CDTI, Ministry of Science and Innovation) through the “Red Cervera” Programme (AI4ES project). Eric L. Manibardo receives funding support from the Basque Government through its BIKAINTEK PhD support program (grant no. 48AFW22019-00002).
dc.description.statusPeer reviewed
dc.format.extent6
dc.identifier.citationManibardo , E L , Laña , I & Del Ser , J 2020 , Transfer Learning and Online Learning for Traffic Forecasting under Different Data Availability Conditions : Alternatives and Pitfalls . in 2020 IEEE 23rd International Conference on Intelligent Transportation Systems, ITSC 2020 . , 9294557 , 2020 IEEE 23rd International Conference on Intelligent Transportation Systems, ITSC 2020 , Institute of Electrical and Electronics Engineers Inc. , pp. 1-6 , 23rd IEEE International Conference on Intelligent Transportation Systems, ITSC 2020 , Rhodes , Greece , 20/09/20 . https://doi.org/10.1109/ITSC45102.2020.9294557
dc.identifier.citationconference
dc.identifier.doi10.1109/ITSC45102.2020.9294557
dc.identifier.isbn978-1-7281-4150-3
dc.identifier.isbn9781728141497
dc.identifier.isbn978-1-7281-4149-7
dc.identifier.otherresearchoutputwizard: 11556/1070
dc.identifier.urlhttp://www.scopus.com/inward/record.url?scp=85099666563&partnerID=8YFLogxK
dc.language.isoeng
dc.publisherInstitute of Electrical and Electronics Engineers Inc.
dc.relation.ispartof2020 IEEE 23rd International Conference on Intelligent Transportation Systems, ITSC 2020
dc.relation.ispartofseries2020 IEEE 23rd International Conference on Intelligent Transportation Systems, ITSC 2020
dc.relation.projectIDCentro para el Desarrollo Tecnológico Industrial, CDTI
dc.relation.projectIDEusko Jaurlaritza, IT1294-19
dc.relation.projectIDMinisterio de Ciencia e Innovación, MICINN, 48AFW22019-00002
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subject.keywordsPredictive models
dc.subject.keywordsData models
dc.subject.keywordsForecasting
dc.subject.keywordsTask analysis
dc.subject.keywordsRoads
dc.subject.keywordsTraining
dc.subject.keywordsAdaptation models
dc.subject.keywordsPredictive models
dc.subject.keywordsData models
dc.subject.keywordsForecasting
dc.subject.keywordsTask analysis
dc.subject.keywordsRoads
dc.subject.keywordsTraining
dc.subject.keywordsAdaptation models
dc.subject.keywordsArtificial Intelligence
dc.subject.keywordsDecision Sciences (miscellaneous)
dc.subject.keywordsInformation Systems and Management
dc.subject.keywordsModeling and Simulation
dc.subject.keywordsEducation
dc.subject.keywordsSDG 11 - Sustainable Cities and Communities
dc.titleTransfer Learning and Online Learning for Traffic Forecasting under Different Data Availability Conditions: Alternatives and Pitfallsen
dc.typeconference output
Files