EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Wi-Fi RSS Fingerprinting-Based Indoor Localization in Large Multi-Floor Buildings

Inoj Neupane, Seyed Shahrestani, Chun Ruan

Electronics · 30.12.2025 · 15 (1) · 183

DOI: 10.3390/electronics15010183 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 30.12.2025. Verfasst von Inoj Neupane und 2 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 92 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Australian Research Training Programme (RTP) Post-graduate Research Scholarship Award, waiver on my Principal Supervisor, Australian Government.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Location estimation is significant in this era of the Internet of Things (IoT). Satellite and cellular signals are often blocked indoors, prompting researchers to explore alternative wireless technologies for indoor positioning. Among these, Wi-Fi Received Signal Strength (RSS) with fingerprinting is dominant in large, multi-floor buildings due to its existing infrastructure, acceptable accuracy, low cost, easy deployment, and scalability. This study aims to systematically search and review the literature on the use of real Wi-Fi RSS fingerprints for indoor localization or positioning in large, multi-floor buildings, in accordance with PRISMA guidelines, to identify current trends, performance, and gaps. Our findings highlight three main public datasets in this fields (covering areas over 10,000 sq.m). Recent trends indicate the widespread adoption of Deep Learning (DL) techniques, particularly Convolutional Neural Networks (CNNs) and Stacked Autoencoders (SAEs). While buildings (in the same vicinity) and their respective floors are accurately identified, the maximum average error remains around 7 m. A notable gap is the lack of public datasets with detailed room or zone information. This review intends to serve as a guide for future researchers looking to improve indoor location estimation in large, multi-floor structures such as universities, hospitals, and malls.

Förderung

  • Australian Research Training Programme (RTP) Post-graduate Research Scholarship Award
  • waiver on my Principal Supervisor
  • Australian Government

Zitieren

APA

Neupane, I., Shahrestani, S., & Ruan, C. (2025). Wi-Fi RSS Fingerprinting-Based Indoor Localization in Large Multi-Floor Buildings. Electronics, 15(1), 183. https://doi.org/10.3390/electronics15010183

Vancouver

Neupane I, Shahrestani S, Ruan C. Wi-Fi RSS Fingerprinting-Based Indoor Localization in Large Multi-Floor Buildings. Electronics. 2025;15(1):183. doi:10.3390/electronics15010183

BibTeX
@article{Neupane2025,
  author = {Neupane, Inoj and Shahrestani, Seyed and Ruan, Chun},
  title = {Wi-Fi RSS Fingerprinting-Based Indoor Localization in Large Multi-Floor Buildings},
  journal = {Electronics},
  year = {2025},
  volume = {15},
  number = {1},
  pages = {183},
  doi = {10.3390/electronics15010183}
}
Kostenlos starten →