EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Reducing Data Collection in Indoor Positioning Through Path Loss-Guided Neural Network Regularization

Giuseppe Lombardi, Antonino Crivello, Paolo Barsocchi, Stefano Chessa, Francesco Furfari

IEEE Journal of Indoor and Seamless Positioning and Navigation · 2026 · 4 · 248-259

DOI: 10.1109/jispin.2026.3743080 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Journal of Indoor and Seamless Positioning and Navigation, 2026. Verfasst von Giuseppe Lombardi und 4 weiteren Autor:innen. Die Arbeit nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union—Next Generation EU, The National Recovery and Resilience Plan, Investment Partenariato Esteso PE8 “Conseguenze e sfide dell'invecchiamento,”.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this article, we propose a novel framework following the physics-informed neural network (PINN) paradigm for directly estimating indoor positions, a method that, to the best of authors' knowledge, has not been previously explored. Training is performed on a public bluetooth low energy dataset that includes a variety of indoor scenarios, including line-of-sight and nonline-of-sight conditions caused by human body signal attenuation. The integration of physics-compliant synthetic data during the training phase significantly reduces dependence on largescale real-world datasets, enabling the use of a simple multilayer perceptron architecture. Our results demonstrate that combining PINNs with real-world measurements enhances model generalization without compromising accuracy.

Förderung

  • European Union—Next Generation EU
  • The National Recovery and Resilience Plan, Investment Partenariato Esteso PE8 “Conseguenze e sfide dell'invecchiamento,”

Zitieren

APA

Lombardi, G., Crivello, A., Barsocchi, P., Chessa, S., & Furfari, F. (2026). Reducing Data Collection in Indoor Positioning Through Path Loss-Guided Neural Network Regularization. IEEE Journal of Indoor and Seamless Positioning and Navigation, 4, 248-259. https://doi.org/10.1109/jispin.2026.3743080

Vancouver

Lombardi G, Crivello A, Barsocchi P, Chessa S, Furfari F. Reducing Data Collection in Indoor Positioning Through Path Loss-Guided Neural Network Regularization. IEEE Journal of Indoor and Seamless Positioning and Navigation. 2026;4:248-259. doi:10.1109/jispin.2026.3743080

BibTeX
@article{Lombardi2026,
  author = {Lombardi, Giuseppe and Crivello, Antonino and Barsocchi, Paolo and Chessa, Stefano and Furfari, Francesco},
  title = {Reducing Data Collection in Indoor Positioning Through Path Loss-Guided Neural Network Regularization},
  journal = {IEEE Journal of Indoor and Seamless Positioning and Navigation},
  year = {2026},
  volume = {4},
  pages = {248--259},
  doi = {10.1109/jispin.2026.3743080}
}
Kostenlos starten →