EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine Learning Models for Indoor Positioning Using Bluetooth RSSI and Video Data: A Case Study

Tomás Mamede, Nuno Silva, Eduardo R B Marques, Luís M B Lopes iD

Sensors · 29.10.2025 · 25 (21) · 6640

DOI: 10.3390/s25216640 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 29.10.2025. Verfasst von Tomás Mamede und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Faculty of Sciences, University of Porto, Rua do Campo Alegre 1055, 4169-007 Porto, Portugal. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Portugal 2020, COMPETE 2020, Fundação para a Ciência e Tecnologia.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Indoor Positioning Systems (IPSs) are essential for applications requiring accurate location awareness in indoor environments. However, achieving high precision remains challenging due to signal interference and environmental variability. This study proposes a multimodal IPS that integrates Bluetooth Received Signal Strength Indicator (RSSI) measurements and video imagery using machine learning (ML) and ensemble learning techniques. The system was implemented and deployed in the Hall of Biodiversity at the Natural History and Science Museum of the University of Porto. The venue presented significant deployment issues, namely restrictions on beacon placement and lighting conditions. We trained independent ML models on RSSI and video datasets, and combined them through ensemble learning methods. The experimental results from test scenarios, which included simulated visitor trajectories, showed that ensemble models consistently outperformed the RSSI-based and video-based models. These findings demonstrate that the use of multimodal data can significantly improve IPS accuracy despite constraints such as multipath interference, low lighting, and limited beacon infrastructure. Overall, they highlight the potential of multimodal data for deployments in complex indoor environments.

Schlagwörter

Stichwörter der Autor:innen

ensemble learningindoor positioning systemmachine learningmultimodal data

Autor:innen und Institutionen

  • Department of Computer Science, Faculty of Sciences, University of Porto, Rua do Campo Alegre 1055, 4169-007 Porto, Portugal.
  • INESC TEC, Campus da Faculdade de Engenharia da Universidade do Porto, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal.

ORCID-Profile: Luís M B Lopes

Förderung

  • Portugal 2020
  • COMPETE 2020
  • Fundação para a Ciência e Tecnologia
  • Google Cloud Research Credits program

Zitieren

APA

Mamede, T., Silva, N., Marques, E. R. B., & Lopes, L. M. B. (2025). Machine Learning Models for Indoor Positioning Using Bluetooth RSSI and Video Data: A Case Study. Sensors, 25(21), 6640. https://doi.org/10.3390/s25216640

Vancouver

Mamede T, Silva N, Marques ERB, Lopes LMB. Machine Learning Models for Indoor Positioning Using Bluetooth RSSI and Video Data: A Case Study. Sensors. 2025;25(21):6640. doi:10.3390/s25216640

BibTeX
@article{Mamede2025,
  author = {Mamede, Tomás and Silva, Nuno and Marques, Eduardo R B and Lopes, Luís M B},
  title = {Machine Learning Models for Indoor Positioning Using Bluetooth RSSI and Video Data: A Case Study},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {21},
  pages = {6640},
  doi = {10.3390/s25216640}
}
Kostenlos starten →