A Precise and Scalable Indoor Positioning System Using Cross-Modal Knowledge Distillation
Sensors · 16.11.2024 · 24 (22) · 7322
DOI: 10.3390/s24227322 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 16.11.2024. Verfasst von Hamada Rizk und 3 weiteren Autor:innen. Beteiligte Einrichtung: Computers & Control Engineering Department, Tanta University, Tanta 31527, Egypt. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Prince Sattam Bin Abdulaziz University (PSAU).
Abstract (Originalsprache)
User location has emerged as a pivotal factor in human-centered environments, driving applications like tracking, navigation, healthcare, and emergency response that align with Sustainable Development Goals (SDGs). However, accurate indoor localization remains challenging due to the limitations of GPS in indoor settings, where signal interference and reflections disrupt satellite connections. While Received Signal Strength Indicator (RSSI) methods are commonly employed, they are affected by environmental noise, multipath fading, and signal interference. Round-Trip Time (RTT)-based localization techniques provide a more resilient alternative but are not universally supported across access points due to infrastructure limitations. To address these challenges, we introduce DistilLoc: a cross-knowledge distillation framework that transfers knowledge from an RTT-based teacher model to an RSSI-based student model. By applying a teacher–student architecture, where the RTT model (teacher) trains the RSSI model (student), DistilLoc enhances RSSI-based localization with the accuracy and robustness of RTT without requiring RTT data during deployment. At the core of DistilLoc, the FNet architecture is employed for its computational efficiency and capacity to capture complex relationships among RSSI signals from multiple access points. This enables the student model to learn a robust mapping from RSSI measurements to precise location estimates, reducing computational demands while improving scalability. Evaluation in two cluttered indoor environments of varying sizes using Android devices and Google WiFi access points, DistilLoc achieved sub-meter localization accuracy, with median errors of 0.42 m and 0.32 m, respectively, demonstrating improvements of 267% over conventional RSSI methods and 496% over multilateration-based approaches. These results validate DistilLoc as a scalable, accurate solution for indoor localization, enabling intelligent, resource-efficient urban environments that contribute to SDG 9 (Industry, Innovation, and Infrastructure) and SDG 11 (Sustainable Cities and Communities).
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Computers & Control Engineering Department, Tanta University, Tanta 31527, Egypt.
- Graduate School of Information Science and Technology, Osaka University, Osaka 565-0871, Japan.
- Faculty of Computer Engineering & Sciences, Prince Sattam Bin Abdelaziz University, Al-Kharj 16278, Saudi Arabia.
- Faculty of Engineering, Tanta University, Tanta 31527, Egypt.
- Department of Communications Engineering, University of Bremen, 28725 Bremen, Germany.
ORCID-Profile: Ahmed Elmogy
Förderung
- Prince Sattam Bin Abdulaziz University (PSAU)
Zitieren
APA
Rizk, H., Elmogy, A., Rihan, M., & Yamaguchi, H. (2024). A Precise and Scalable Indoor Positioning System Using Cross-Modal Knowledge Distillation. Sensors, 24(22), 7322. https://doi.org/10.3390/s24227322
Vancouver
Rizk H, Elmogy A, Rihan M, Yamaguchi H. A Precise and Scalable Indoor Positioning System Using Cross-Modal Knowledge Distillation. Sensors. 2024;24(22):7322. doi:10.3390/s24227322
BibTeX
@article{Rizk2024,
author = {Rizk, Hamada and Elmogy, Ahmed and Rihan, Mohamed and Yamaguchi, Hirozumi},
title = {A Precise and Scalable Indoor Positioning System Using Cross-Modal Knowledge Distillation},
journal = {Sensors},
year = {2024},
volume = {24},
number = {22},
pages = {7322},
doi = {10.3390/s24227322}
}
EUVIMED