Show simple item record

dc.contributor.authorManibardo, Eric L.
dc.contributor.authorLana, Ibai
dc.contributor.authorDel Ser, Javier
dc.date.accessioned2021-01-29T10:10:40Z
dc.date.available2021-01-29T10:10:40Z
dc.date.issued2020
dc.identifier.citationManibardo, Eric L., Ibai Lana, and Javier Del Ser. “Transfer Learning and Online Learning for Traffic Forecasting Under Different Data Availability Conditions: Alternatives and Pitfalls.” 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC) (September 20, 2020). doi:10.1109/itsc45102.2020.9294557.en
dc.identifier.isbn978-1-7281-4150-3en
dc.identifier.urihttp://hdl.handle.net/11556/1070
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.language.isoengen
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en
dc.titleTransfer Learning and Online Learning for Traffic Forecasting under Different Data Availability Conditions: Alternatives and Pitfallsen
dc.typeconferenceObjecten
dc.identifier.doi10.1109/itsc45102.2020.9294557en
dc.rights.accessRightsembargoedAccessen
dc.subject.keywordsPredictive modelsen
dc.subject.keywordsData modelsen
dc.subject.keywordsForecastingen
dc.subject.keywordsTask analysisen
dc.subject.keywordsRoadsen
dc.subject.keywordsTrainingen
dc.subject.keywordsAdaptation modelsen
dc.page.final6en
dc.page.initial1en
dc.identifier.esbn978-1-7281-4149-7en
dc.conference.title23rd IEEE International Conference on Intelligent Transportation Systems, ITSC 2020; Rhodes; Greece; 20 September 2020 through 23 September 2020en


Files in this item

FilesSizeFormatView

There are no files associated with this item.

    Show simple item record