EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Range-Free Positioning in NB-IoT Networks by Machine Learning: Beyond W$k$NN

Luca De Nardis, Marco Savelli, Giuseppe Caso, Federico Ferretti, Lorenzo Tonelli, Nadir Bouzar, Anna Brunstrom, Özgü Alay, Marco Neri, Fouzia Elbahhar Bokour, Maria-Gabriella Di Benedetto

IEEE Journal of Indoor and Seamless Positioning and Navigation · 2025 · 3 · 53-69

DOI: 10.1109/jispin.2025.3558465 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Journal of Indoor and Seamless Positioning and Navigation, 2025. Verfasst von Luca De Nardis und 10 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 79 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union - Next Generation EU, Italian National Recovery and Resilience Plan, Mission 4.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Existing proposals for positioning in narrowband Internet of Things (NB-IoT) networks based on range estimation are characterized by either low accuracy or lack of compliance with 3GPP standards. While range-free approaches taking advantage of machine learning (ML) have been recently proposed as a potential way forward, their evaluation has been carried out only in simulated environments, with the exception of weighted $k$ nearest neighbors (W $k$ NN), recently tested on experimental data. This work investigates five ML strategies for range-free positioning in NB-IoT networks, based on W $k$ NN and its combination with preprocessing and classification algorithms as well as on artificial neural networks (ANNs). The strategies are evaluated on experimental data and are compared based on a set of key performance indicators measuring both positioning performance and processing load. Two different datasets taken at different times and locations were adopted, enabling the validation of strategies optimized on one testbed on the other, as well as the study of the impact of dataset features on performance. Results show that range-free positioning using ML is a viable solution in commercial NB-IoT networks, and that W $k$ NN and ANNs are at the two extremes in terms of a performance/complexity tradeoff; intermediate tradeoffs can be achieved by combining W $k$ NN with preprocessing techniques and classification models.

Förderung

  • European Union - Next Generation EU
  • Italian National Recovery and Resilience Plan
  • Mission 4
  • Component 2
  • Investment 1.3
  • Telecommunications of the Future
  • Sapienza Università di Roma
  • Giuseppe Caso

Zitieren

APA

Nardis, L. D., Savelli, M., Caso, G., Ferretti, F., Tonelli, L., Bouzar, N., Brunstrom, A., Alay, Ö., Neri, M., Bokour, F. E., & Benedetto, M. D. (2025). Range-Free Positioning in NB-IoT Networks by Machine Learning: Beyond W$k$NN. IEEE Journal of Indoor and Seamless Positioning and Navigation, 3, 53-69. https://doi.org/10.1109/jispin.2025.3558465

Vancouver

Nardis LD, Savelli M, Caso G, Ferretti F, Tonelli L, Bouzar N, et al. Range-Free Positioning in NB-IoT Networks by Machine Learning: Beyond W$k$NN. IEEE Journal of Indoor and Seamless Positioning and Navigation. 2025;3:53-69. doi:10.1109/jispin.2025.3558465

BibTeX
@article{Nardis2025,
  author = {Nardis, Luca De and Savelli, Marco and Caso, Giuseppe and Ferretti, Federico and Tonelli, Lorenzo and Bouzar, Nadir and Brunstrom, Anna and Alay, Özgü and Neri, Marco and Bokour, Fouzia Elbahhar and Benedetto, Maria-Gabriella Di},
  title = {Range-Free Positioning in NB-IoT Networks by Machine Learning: Beyond W$k$NN},
  journal = {IEEE Journal of Indoor and Seamless Positioning and Navigation},
  year = {2025},
  volume = {3},
  pages = {53--69},
  doi = {10.1109/jispin.2025.3558465}
}
Kostenlos starten →