Mostrar el registro sencillo del ítem
Transfer Learning for Convolutional Indoor Positioning Systems
dc.contributor.author | Klus, Roman | |
dc.contributor.author | Klus, Lucie | |
dc.contributor.author | Talvitie, Jukka | |
dc.contributor.author | Pihlajasalo, Jaakko | |
dc.contributor.author | Torres-Sospedra, Joaquín | |
dc.contributor.author | Valkama, Mikko | |
dc.date.accessioned | 2022-04-13T07:53:58Z | |
dc.date.available | 2022-04-13T07:53:58Z | |
dc.date.issued | 2021-11-29 | |
dc.identifier.citation | KLUS, Roman, et al. Transfer Learning for Convolutional Indoor Positioning Systems. En 2021 International Conference on Indoor Positioning and Indoor Navigation (IPIN). IEEE, 2022. p. 1-8. | ca_CA |
dc.identifier.uri | http://hdl.handle.net/10234/197333 | |
dc.description | Ponencia presentada en la 2021 International Conference on Indoor Positioning and Indoor Navigation (IPIN), 29 Nov.-2 Dec. 2021, Lloret de Mar (Spain) | ca_CA |
dc.description.abstract | Fingerprinting is a widely used technique in indoor positioning, mainly due to its simplicity. Usually, this technique is used with the deterministic k - Nearest Neighbors (k-NN) algorithm. Utilizing a neural network model for fingerprinting positioning purposes can greatly improve the prediction speed compared to the k-NN approach, but requires a voluminous training dataset to achieve comparable performance. In many indoor positioning datasets, the number of samples is only at a level of hundreds, which results in poor performance of the neural network solution. In this work, we develop a novel algorithm based on a transfer learning approach, which combines samples from 15 different Wi-Fi RSS indoor positioning datasets, to train a single convolutional neural network model, which learns the common patterns in the combined data. The proposed model is then fine-tuned to optimally fit the individual databases. We show that the proposed solution reduces the positioning error by up to 25% compared to the benchmark model while reducing the number of outlier predictions. | ca_CA |
dc.format.extent | 8 p. | ca_CA |
dc.format.mimetype | application/pdf | ca_CA |
dc.language.iso | eng | ca_CA |
dc.publisher | IEEE | ca_CA |
dc.relation.isPartOf | 2021 International Conference on Indoor Positioning and Indoor Navigation (IPIN) | ca_CA |
dc.rights | © Copyright 2022 IEEE - All rights reserved. | ca_CA |
dc.rights.uri | http://rightsstatements.org/vocab/InC/1.0/ | ca_CA |
dc.subject | artificial neural network | ca_CA |
dc.subject | WLAN | ca_CA |
dc.subject | convolutional neural network | ca_CA |
dc.subject | deep learning | ca_CA |
dc.subject | fingerprinting | ca_CA |
dc.subject | indoor positioning | ca_CA |
dc.subject | machine learning | ca_CA |
dc.subject | transfer learning | ca_CA |
dc.title | Transfer Learning for Convolutional Indoor Positioning Systems | ca_CA |
dc.type | info:eu-repo/semantics/conferenceObject | ca_CA |
dc.identifier.doi | 10.1109/IPIN51156.2021.9662544 | |
dc.rights.accessRights | info:eu-repo/semantics/openAccess | ca_CA |
dc.type.version | info:eu-repo/semantics/submittedVersion | ca_CA |