EUVIMEDOpdag EUVIMED
Open access · CC BY-NC-ND 4.0

UE-GLoc: Uncertainty-Aware Graph Neural Networks for Robust and Accurate WiFi Indoor Localization

Yixue Guo, Fangming Guo, Kehan Guo, Song Xie, Xianlei Long, Ronghua Yang, Leilei Li, Fuqiang Gu

ACM Transactions on Sensor Networks · 2026-07-31 · 22 (4) · 1-23

DOI: 10.1145/3820501 ↗

At a glance

Journal article in ACM Transactions on Sensor Networks, published online on 2026-07-21. Written by Yixue Guo and 7 co-authors. 61 references. The full text is freely available (open access, CC BY-NC-ND 4.0). Funded by: National Natural Science Foundation of China, National Key Research and Development Program for Young Scientists, Xiaomi Young Talents Program, and China Postdoctoral Science Foundation.

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

WiFi fingerprinting is a cost-effective solution for indoor localization, but traditional methods struggle with environmental variability and limited adaptability. Recent deep learning approaches, especially Graph Neural Networks (GNNs), improve accuracy by modeling spatial relationships, yet often lack robustness to uncertainty and long-range dependencies. This article presents UE-GLoc, a GNN-based localization framework that integrates an environmental uncertainty estimation (EUE) and a graph outer attention (GOA) mechanism. By capturing both local and global dependencies, UE-GLoc blue aims to enhance feature representation and blue improve model reliability under varying conditions. Experiments on public datasets show that UE-GLoc achieves higher accuracy and generally better performance compared to several state-of-the-art methods, with potential adaptability to new environments.

Funding

  • National Natural Science Foundation of China
  • National Key Research and Development Program for Young Scientists
  • Xiaomi Young Talents Program, and China Postdoctoral Science Foundation

Cite

APA

Guo, Y., Guo, F., Guo, K., Xie, S., Long, X., Yang, R., Li, L., & Gu, F. (2026). UE-GLoc: Uncertainty-Aware Graph Neural Networks for Robust and Accurate WiFi Indoor Localization. ACM Transactions on Sensor Networks, 22(4), 1-23. https://doi.org/10.1145/3820501

Vancouver

Guo Y, Guo F, Guo K, Xie S, Long X, Yang R, et al. UE-GLoc: Uncertainty-Aware Graph Neural Networks for Robust and Accurate WiFi Indoor Localization. ACM Transactions on Sensor Networks. 2026;22(4):1-23. doi:10.1145/3820501

BibTeX
@article{Guo2026,
  author = {Guo, Yixue and Guo, Fangming and Guo, Kehan and Xie, Song and Long, Xianlei and Yang, Ronghua and Li, Leilei and Gu, Fuqiang},
  title = {UE-GLoc: Uncertainty-Aware Graph Neural Networks for Robust and Accurate WiFi Indoor Localization},
  journal = {ACM Transactions on Sensor Networks},
  year = {2026},
  volume = {22},
  number = {4},
  pages = {1--23},
  doi = {10.1145/3820501}
}
Start for free →