Adaptive and Efficient Sample Selection for Domain Incremental 5G Indoor Localization in Dynamic Multipath Environments
IEEE Journal of Indoor and Seamless Positioning and Navigation · 2026 · 4 · 23-40
DOI: 10.1109/jispin.2025.3648680 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Journal of Indoor and Seamless Positioning and Navigation, 2026. Verfasst von Nisha L. Raichur und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: German Federal Ministry for Transport, Deutsches Zentrum für Luft- und Raumfahrt, Federal Agency for Cartography and Geodesy.
Abstract (Originalsprache)
Indoor positioning based on 5G data has achieved high accuracy through the adoption of recent machine learning (ML) techniques. However, the performance of learning-based methods degrades significantly when environmental conditions change, thereby hindering their applicability to new scenarios. Acquiring new training data for each environmental change and fine-tuning ML models is both time-consuming and resource-intensive. This article introduces a domain incremental learning (DIL) approach for dynamic 5G indoor localization, called 5G-DIL, enabling rapid adaptation to environmental changes. We present a novel similarity-aware sampling technique based on the Chebyshev distance, designed to efficiently select specific exemplars from the previous environment while training only on the modified regions of the new environment. This avoids the need to train on the entire region, significantly reducing the time and resources required for adaptation without compromising localization accuracy. This approach requires as few as 50 exemplars from adaptation domains, significantly reducing training time while maintaining high positioning accuracy in previous environments. Comparative evaluations against state-of-the-art DIL techniques on a challenging real-world indoor dataset demonstrate the effectiveness of the proposed sample selection method. Our approach is adaptable to real-world nonline-of-sight propagation scenarios and achieves an mean absolute error positioning error of 0.261 m, even under dynamic environmental conditions.
Förderung
- German Federal Ministry for Transport
- Deutsches Zentrum für Luft- und Raumfahrt
- Federal Agency for Cartography and Geodesy
Zitieren
APA
Raichur, N. L., Heublein, L., Pahl, J., Seuß, D., Mutschler, C., & Ott, F. (2026). Adaptive and Efficient Sample Selection for Domain Incremental 5G Indoor Localization in Dynamic Multipath Environments. IEEE Journal of Indoor and Seamless Positioning and Navigation, 4, 23-40. https://doi.org/10.1109/jispin.2025.3648680
Vancouver
Raichur NL, Heublein L, Pahl J, Seuß D, Mutschler C, Ott F. Adaptive and Efficient Sample Selection for Domain Incremental 5G Indoor Localization in Dynamic Multipath Environments. IEEE Journal of Indoor and Seamless Positioning and Navigation. 2026;4:23-40. doi:10.1109/jispin.2025.3648680
BibTeX
@article{Raichur2026,
author = {Raichur, Nisha L. and Heublein, Lucas and Pahl, Jaspar and Seuß, Dominik and Mutschler, Christopher and Ott, Felix},
title = {Adaptive and Efficient Sample Selection for Domain Incremental 5G Indoor Localization in Dynamic Multipath Environments},
journal = {IEEE Journal of Indoor and Seamless Positioning and Navigation},
year = {2026},
volume = {4},
pages = {23--40},
doi = {10.1109/jispin.2025.3648680}
}
EUVIMED