Show simple item record

On the use of the angle of incidence in support vector regression surrogate models for practical reflectarray design

dc.contributor.authorRodríguez Prado, Daniel 
dc.contributor.authorLópez Fernandez, Jesús Alberto 
dc.contributor.authorArrebola Baena, Manuel 
dc.contributor.authorGoussetis, George
dc.date.accessioned2021-02-05T10:56:01Z
dc.date.available2021-02-05T10:56:01Z
dc.date.issued2021
dc.identifier.citationIEEE Transactions on Antennas and Propagation; doi: 10.1109/TAP.2020.3015707.
dc.identifier.issn0018-926X
dc.identifier.issn1558-2221
dc.identifier.urihttp://hdl.handle.net/10651/57773
dc.description.abstractA common approach in the literature when obtaining surrogate models of reflectarray unit cells is to include, among other variables, the angles of incidence as input variables to the model. In this work, we use support vector regression (SVR) to compare this approach with a new strategy which consists in grouping the refletarray elements under a small set of angles of incidence and train surrogate models per angle of incidence pair. In this case, the dimensionality of the SVR decreases in two with regard to the former approach. In both cases, two geometrical variables are considered for reflectarray design, obtaining 4D and 2D SVRs, respectively. In contrast to the common approach in the literature, the comparison between the 4D and 2D SVRs shows that a proper discretization of the angles of incidence is more competitive than introducing the angles as input variables in the SVR. The 2D SVR offers a shorter training time, faster reflectarray analysis, and a similar accuracy than the 4D SVR, making it more suitable for design and optimization procedures.spa
dc.description.sponsorshipThis work was supported in part by the European Commission under H2020 project REVOLVE (MSCA-ITN-2016-722840); by the Ministerio de Ciencia, Innovación y Universidades under projects TEC2017-86619-R (ARTEINE) and IJC2018-035696-I; by the Ministerio de Economía, Industria y Competitividad under project TEC2016-75103-C2-1-R (MYRADA); by the Gobierno del Principado de Asturias/FEDER under Project GRUPIN-IDI/2018/000191; by Ministerio de Educación, Cultura y Deporte / Programa de Movilidad “Salvador de Madariaga” (Ref. PRX18/00424).spa
dc.language.isoengspa
dc.publisherIEEEspa
dc.relation.ispartofIEEE Transactions on Antennas and Propagationspa
dc.rightsAtribución 4.0 Internacional*
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/*
dc.subjectMachine learningspa
dc.subjectsurrogate modelspa
dc.subjectsupport vector regression (SVR)spa
dc.subjectangle of incidencespa
dc.subjectreflectarray antennaspa
dc.titleOn the use of the angle of incidence in support vector regression surrogate models for practical reflectarray designspa
dc.typeinfo:eu-repo/semantics/articlespa
dc.type.dcmitextspa
dc.relation.projectIDMSCA-ITN-2016-722840spa
dc.relation.projectIDTEC2017-86619-Rspa
dc.relation.projectIDIJC2018-035696-Ispa
dc.relation.projectIDTEC2016-75103-C2-1-Rspa
dc.relation.projectIDGRUPIN-IDI/2018/000191spa
dc.relation.projectIDPRX18/00424spa
dc.relation.publisherversionhttps://www.doi.org/10.1109/TAP.2020.3015707
dc.rights.accessRightsinfo:eu-repo/semantics/openAccessspa


Files in this item

untranslated

This item appears in the following Collection(s)

Show simple item record

Atribución 4.0 Internacional
This item is protected with a Creative Commons License