Ensembling Multiple Radio Maps with Dynamic Noise in Fingerprint-based Indoor Positioning
Ver/ Abrir
Impacto
Scholar |
Otros documentos de la autoría: Torres-Sospedra, Joaquín; Aranda Polo, Fernando Jesús; Álvarez, Fernando J.; Quezada Gaibor, Darwin; Silva, Ivo; Pendão, Cristiano; Moreira, Adriano
Metadatos
Mostrar el registro completo del ítemcomunitat-uji-handle:10234/9
comunitat-uji-handle2:10234/43662
comunitat-uji-handle3:10234/159451
comunitat-uji-handle4:
INVESTIGACIONMetadatos
Título
Ensembling Multiple Radio Maps with Dynamic Noise in Fingerprint-based Indoor PositioningAutoría
Fecha de publicación
2021-06-15Editor
Institute of Electrical and Electronics Engineers; IEEEISBN
978-1-7281-8964-2Cita bibliográfica
J. Torres-Sospedra et al., "Ensembling Multiple Radio Maps with Dynamic Noise in Fingerprint-based Indoor Positioning," 2021 IEEE 93rd Vehicular Technology Conference (VTC2021-Spring), 2021, pp. 1-5, doi: 10.1109/VTC2021-Spring51267.2021.9448947.Tipo de documento
info:eu-repo/semantics/conferenceObjectVersión de la editorial
https://ieeexplore.ieee.org/xpl/conhome/9448628/proceedingVersión
info:eu-repo/semantics/submittedVersionPalabras clave / Materias
Resumen
Fingerprint-based indoor positioning is widely used
in many contexts, including pedestrian and autonomous vehicles
navigation. Many approaches have used traditional Machine
Learning models to deal with fingerprinting, ... [+]
Fingerprint-based indoor positioning is widely used
in many contexts, including pedestrian and autonomous vehicles
navigation. Many approaches have used traditional Machine
Learning models to deal with fingerprinting, being k-NN the
most common used one. However, the reference data (or radio
map) is generally limited, as data collection is a very demanding
task, which degrades overall accuracy. In this work, we propose
a novel approach to add random noise to the radio map which
will be used in combination with an ensemble model. Instead
of augmenting the radio map, we create n noisy versions of
the same size, i.e. our proposed Indoor Positioning model will
combine n estimations obtained by independent estimators built
with the n noisy radio maps. The empirical results have shown
that our proposed approach improves the baseline method results
in around 10% on average [-]
Descripción
Ponencia presentada en 2021 IEEE 93rd Vehicular Technology Conference (VTC2021-Spring), 25-28 April 2021
Entidad financiadora
Ministerio de Ciencia, Innovación y Universidades (Spain) | Ministerio de Economía y Competitividad | European Union’s Horizon 2020 Research | Fundaçao para a Ciência e Tecnologia
Código del proyecto o subvención
PTQ2018-009981 | RTI2018-095168-B-C54 | TEC2017-90808-REDT | UIDB/00319/2020 | PD/BD/137401/2018
Proyecto de investigación
info:eu-repo/grantAgreement/EC/H2020/813278Derechos de acceso
http://rightsstatements.org/vocab/InC/1.0/
info:eu-repo/semantics/openAccess
info:eu-repo/semantics/openAccess