Indoor Millimeter Wave Localization Using Multiple Self-Supervised Tiny Neural Networks
IEEE Communications Letters · 2024-05 · 28 (5) · 1034-1038
DOI: 10.1109/lcomm.2024.3376150 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Communications Letters, 2024-05. Verfasst von Anish Shastri und 2 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 15 Literaturangaben. Gefördert von: European Commission’s Horizon 2020 Framework Program under the Marie Skłodowska-Curie Action MINTS.
Abstract (Originalsprache)
We consider the localization of a mobile mmw client in a large indoor environment using multilayer perceptron neural networks (NNs). Instead of training and deploying a single deep model, we proceed by choosing among multiple tiny NNs trained in a self-supervised manner. The main challenge is then to determine and switch to the best NN among the available ones, as an incorrect NN will fail to localize the client. In order to preserve the localization accuracy, we propose two switching schemes: one based on the innovation measured by a Kalman filter, and one based on the statistical distribution of the training data. We analyze the proposed schemes via simulations, showing that our approach outperforms both geometric localization schemes and the use of a single NN.
Förderung
- European Commission’s Horizon 2020 Framework Program under the Marie Skłodowska-Curie Action MINTS
Zitieren
APA
Shastri, A., Garcia-Saavedra, A., & Casari, P. (2024). Indoor Millimeter Wave Localization Using Multiple Self-Supervised Tiny Neural Networks. IEEE Communications Letters, 28(5), 1034-1038. https://doi.org/10.1109/lcomm.2024.3376150
Vancouver
Shastri A, Garcia-Saavedra A, Casari P. Indoor Millimeter Wave Localization Using Multiple Self-Supervised Tiny Neural Networks. IEEE Communications Letters. 2024;28(5):1034-1038. doi:10.1109/lcomm.2024.3376150
BibTeX
@article{Shastri2024,
author = {Shastri, Anish and Garcia-Saavedra, Andres and Casari, Paolo},
title = {Indoor Millimeter Wave Localization Using Multiple Self-Supervised Tiny Neural Networks},
journal = {IEEE Communications Letters},
year = {2024},
volume = {28},
number = {5},
pages = {1034--1038},
doi = {10.1109/lcomm.2024.3376150}
}
EUVIMED