Autoencoder extreme learning machine for fingerprint-based positioning: A good weight initialization is decisive
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Outros Autores: | , , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | https://hdl.handle.net/1822/87189 |
Resumo: | Indoor positioning based on machine-learning (ML) models has attracted widespread interest in the last few years, given its high performance and usability. Supervised, semisupervised, and unsupervised models have thus been widely used in this field, not only to estimate the user position, but also to compress, clean, and denoise fingerprinting datasets. Some scholars have focused on developing, improving, and optimizing ML models to provide accurate solutions to the end user. This article introduces a novel method to initialize the input weights in autoencoder extreme learning machine (AE-ELM), namely factorized input data (FID), which is based on the normalized form of the orthogonal component of the input data. AE-ELM with FID weight initialization is used to efficiently reduce the radio map. Once the dimensionality of the dataset is reduced, we use k -nearest neighbors to perform the position estimation. This research work includes a comparative analysis with several traditional ways to initialize the input weights in AE-ELM, showing that FID provide a significantly better reconstruction error. Finally, we perform an assessment with 13 indoor positioning datasets collected from different buildings and in different countries. We show that the dimensionality of the datasets can be reduced more than 11 times on average, while the positioning error suffers only a small increment of 15% (on average) in comparison to the baseline. |
id |
RCAP_a7dc0d6af741f69518351cf76af62cae |
---|---|
oai_identifier_str |
oai:repositorium.sdum.uminho.pt:1822/87189 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Autoencoder extreme learning machine for fingerprint-based positioning: A good weight initialization is decisiveAutoencoderExtreme learning machineIndoor positioningSingular value decompositionWeight initializationWi-Fi fingerprintingEngenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e InformáticaIndoor positioning based on machine-learning (ML) models has attracted widespread interest in the last few years, given its high performance and usability. Supervised, semisupervised, and unsupervised models have thus been widely used in this field, not only to estimate the user position, but also to compress, clean, and denoise fingerprinting datasets. Some scholars have focused on developing, improving, and optimizing ML models to provide accurate solutions to the end user. This article introduces a novel method to initialize the input weights in autoencoder extreme learning machine (AE-ELM), namely factorized input data (FID), which is based on the normalized form of the orthogonal component of the input data. AE-ELM with FID weight initialization is used to efficiently reduce the radio map. Once the dimensionality of the dataset is reduced, we use k -nearest neighbors to perform the position estimation. This research work includes a comparative analysis with several traditional ways to initialize the input weights in AE-ELM, showing that FID provide a significantly better reconstruction error. Finally, we perform an assessment with 13 indoor positioning datasets collected from different buildings and in different countries. We show that the dimensionality of the datasets can be reduced more than 11 times on average, while the positioning error suffers only a small increment of 15% (on average) in comparison to the baseline.IEEEUniversidade do MinhoGaibor, Darwin P. QuezadaKlus, LucieKlus, RomanLohan, Elena SimonaNurmi, JariValkama, MikkoHuerta, JoaquínTorres-Sospedra, Joaquín2023-07-272023-07-27T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/1822/87189engD. P. Q. Gaibor et al., "Autoencoder extreme learning machine for fingerprint-based positioning: A good weight initialization is decisive," in IEEE Journal of Indoor and Seamless Positioning and Navigation, vol. 1, pp. 53-68, 2023, doi: 10.1109/JISPIN.2023.3299433.2832-732210.1109/JISPIN.2023.3299433https://ieeexplore.ieee.org/document/10195972info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-12-23T01:39:12Zoai:repositorium.sdum.uminho.pt:1822/87189Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T22:37:54.297008Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Autoencoder extreme learning machine for fingerprint-based positioning: A good weight initialization is decisive |
title |
Autoencoder extreme learning machine for fingerprint-based positioning: A good weight initialization is decisive |
spellingShingle |
Autoencoder extreme learning machine for fingerprint-based positioning: A good weight initialization is decisive Gaibor, Darwin P. Quezada Autoencoder Extreme learning machine Indoor positioning Singular value decomposition Weight initialization Wi-Fi fingerprinting Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática |
title_short |
Autoencoder extreme learning machine for fingerprint-based positioning: A good weight initialization is decisive |
title_full |
Autoencoder extreme learning machine for fingerprint-based positioning: A good weight initialization is decisive |
title_fullStr |
Autoencoder extreme learning machine for fingerprint-based positioning: A good weight initialization is decisive |
title_full_unstemmed |
Autoencoder extreme learning machine for fingerprint-based positioning: A good weight initialization is decisive |
title_sort |
Autoencoder extreme learning machine for fingerprint-based positioning: A good weight initialization is decisive |
author |
Gaibor, Darwin P. Quezada |
author_facet |
Gaibor, Darwin P. Quezada Klus, Lucie Klus, Roman Lohan, Elena Simona Nurmi, Jari Valkama, Mikko Huerta, Joaquín Torres-Sospedra, Joaquín |
author_role |
author |
author2 |
Klus, Lucie Klus, Roman Lohan, Elena Simona Nurmi, Jari Valkama, Mikko Huerta, Joaquín Torres-Sospedra, Joaquín |
author2_role |
author author author author author author author |
dc.contributor.none.fl_str_mv |
Universidade do Minho |
dc.contributor.author.fl_str_mv |
Gaibor, Darwin P. Quezada Klus, Lucie Klus, Roman Lohan, Elena Simona Nurmi, Jari Valkama, Mikko Huerta, Joaquín Torres-Sospedra, Joaquín |
dc.subject.por.fl_str_mv |
Autoencoder Extreme learning machine Indoor positioning Singular value decomposition Weight initialization Wi-Fi fingerprinting Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática |
topic |
Autoencoder Extreme learning machine Indoor positioning Singular value decomposition Weight initialization Wi-Fi fingerprinting Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática |
description |
Indoor positioning based on machine-learning (ML) models has attracted widespread interest in the last few years, given its high performance and usability. Supervised, semisupervised, and unsupervised models have thus been widely used in this field, not only to estimate the user position, but also to compress, clean, and denoise fingerprinting datasets. Some scholars have focused on developing, improving, and optimizing ML models to provide accurate solutions to the end user. This article introduces a novel method to initialize the input weights in autoencoder extreme learning machine (AE-ELM), namely factorized input data (FID), which is based on the normalized form of the orthogonal component of the input data. AE-ELM with FID weight initialization is used to efficiently reduce the radio map. Once the dimensionality of the dataset is reduced, we use k -nearest neighbors to perform the position estimation. This research work includes a comparative analysis with several traditional ways to initialize the input weights in AE-ELM, showing that FID provide a significantly better reconstruction error. Finally, we perform an assessment with 13 indoor positioning datasets collected from different buildings and in different countries. We show that the dimensionality of the datasets can be reduced more than 11 times on average, while the positioning error suffers only a small increment of 15% (on average) in comparison to the baseline. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-07-27 2023-07-27T00:00:00Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://hdl.handle.net/1822/87189 |
url |
https://hdl.handle.net/1822/87189 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
D. P. Q. Gaibor et al., "Autoencoder extreme learning machine for fingerprint-based positioning: A good weight initialization is decisive," in IEEE Journal of Indoor and Seamless Positioning and Navigation, vol. 1, pp. 53-68, 2023, doi: 10.1109/JISPIN.2023.3299433. 2832-7322 10.1109/JISPIN.2023.3299433 https://ieeexplore.ieee.org/document/10195972 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
IEEE |
publisher.none.fl_str_mv |
IEEE |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799134937967755264 |