Please use this identifier to cite or link to this item:

TitleAutoencoder extreme learning machine for fingerprint-based positioning: A good weight initialization is decisive
Author(s)Gaibor, Darwin P. Quezada
Klus, Lucie
Klus, Roman
Lohan, Elena Simona
Nurmi, Jari
Valkama, Mikko
Huerta, Joaquín
Torres-Sospedra, Joaquín
Extreme learning machine
Indoor positioning
Singular value decomposition
Weight initialization
Wi-Fi fingerprinting
Issue date27-Jul-2023
JournalIEEE Journal of Indoor and Seamless Positioning and Navigation
CitationD. 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.
Abstract(s)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.
Publisher version
AccessOpen access
Appears in Collections:CAlg - Artigos em revistas internacionais / Papers in international journals

This item is licensed under a Creative Commons License Creative Commons

Partilhe no FacebookPartilhe no TwitterPartilhe no DeliciousPartilhe no LinkedInPartilhe no DiggAdicionar ao Google BookmarksPartilhe no MySpacePartilhe no Orkut
Exporte no formato BibTex mendeley Exporte no formato Endnote Adicione ao seu ORCID