PrivEdge-Loc: Edge-Efficient and Privacy-Preserving Indoor Localization for Multi-Band Networks
IEEE Access · 2026 · 14 · 93978-93988
DOI: 10.1109/access.2026.3702124 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Hemant Miranka und 6 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Telecom Technology Development Fund (TTDF), Department of Telecommunication (DoT), Government of India.
Abstract (Originalsprache)
In this paper, we introduce a new, lightweight, and secure solution, PrivEdge-Loc, which is particularly suitable for multi-band indoor localization in IoT networks. Unlike traditional federated learning, which requires substantial computational power in edge computing, Split Learning greatly reduces this necessity in our solution. Split Learning is a novel machine learning paradigm in which the neural network is split into two parts: one on the edge device and the other. By offloading heavy computation to the server, the edge nodes only need to send low-dimensional compressed data to the server for processing, ensuring that the privacy of raw Channel State Information (CSI) is architecturally protected against eavesdropping. To tackle the statistical heterogeneity in multi-frequency environments, the server leverages a differentiable gating network within a dynamic Mixture of Experts (MoE) architecture. This enables the server to dynamically route incoming features to frequency-specific experts without requiring explicit band identification. Additionally, the representational power of the student experts is further enhanced through Hint-Based Knowledge Distillation (HKD), which actively aligns the student experts’ intermediate latent space with that of the pre-trained teacher models. Our proposed PrivEdge-Loc is evaluated using a non-IID dataset with 3 frequency bands: 2.4 GHz, 3.5 GHz, and 5.0 GHz. Our framework achieves a highly competitive Mean Absolute Error (MAE) of 0.194 meters. The proposed framework provides a highly scalable, secure, and feasible alternative to computation-intensive federated baselines for data-sensitive, multi-tenant deployments.
Förderung
- Telecom Technology Development Fund (TTDF), Department of Telecommunication (DoT), Government of India
Zitieren
APA
Miranka, H., Tehariya, S. K., Awasthi, A., Mayudu, B. P., Peram, S. R., Battula, R. B., & Mishra, B. (2026). PrivEdge-Loc: Edge-Efficient and Privacy-Preserving Indoor Localization for Multi-Band Networks. IEEE Access, 14, 93978-93988. https://doi.org/10.1109/access.2026.3702124
Vancouver
Miranka H, Tehariya SK, Awasthi A, Mayudu BP, Peram SR, Battula RB, et al. PrivEdge-Loc: Edge-Efficient and Privacy-Preserving Indoor Localization for Multi-Band Networks. IEEE Access. 2026;14:93978-93988. doi:10.1109/access.2026.3702124
BibTeX
@article{Miranka2026,
author = {Miranka, Hemant and Tehariya, Sanjay Kumar and Awasthi, Avinash and Mayudu, B. Prema and Peram, Subba Rao and Battula, Ramesh Babu and Mishra, Bharavi},
title = {PrivEdge-Loc: Edge-Efficient and Privacy-Preserving Indoor Localization for Multi-Band Networks},
journal = {IEEE Access},
year = {2026},
volume = {14},
pages = {93978--93988},
doi = {10.1109/access.2026.3702124}
}
EUVIMED