EUVIMEDEUVIMED entdecken
Crossref

MetaLoc: Learning to Learn Wireless Localization

Jun Gao, Dongze Wu, Feng Yin, Qinglei Kong, Lexi Xu, Shuguang Cui

IEEE Journal on Selected Areas in Communications · 2023-12 · 41 (12) · 3831-3847

DOI: 10.1109/jsac.2023.3322766 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Journal on Selected Areas in Communications, 2023-12. Verfasst von Jun Gao und 5 weiteren Autor:innen. Die Arbeit wurde bisher 143-mal zitiert (Crossref) und nennt 63 Literaturangaben. Gefördert von: NSFC, Basic Research Project, National Key R&D Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Existing localization methods that intensively leverage the environment-specific received signal strength (RSS) or channel state information (CSI) of wireless signals are rather accurate in certain environments. However, these methods, whether based on pure statistical signal processing or data-driven approaches, often struggle to generalize to new environments, which results in considerable time and effort being wasted. To address this challenge, we propose MetaLoc, which is the first fingerprinting-based localization framework that leverages the Model-Agnostic Meta-Learning (MAML). Specifically, built on a deep neural network with strong representation capabilities, MetaLoc is trained on historical data sourced from well-calibrated environments, employing a two-loop optimization mechanism to obtain the meta-parameters. These meta-parameters act as the initialization for quick adaptation in new environments, reducing the need for much human effort. The framework introduces two paradigms for the optimization of meta-parameters: a centralized paradigm that simplifies the process by sharing data from all historical environments, and a distributed paradigm that maintains data privacy by training meta-parameters for each specific environment separately. Furthermore, the advanced distributed paradigm modifies the vanilla MAML loss function to ensure that the reduction of loss occurs in a consistent direction across various training domains, thus facilitating faster convergence during training. Our experiments on both synthetic and real datasets demonstrate that MetaLoc outperforms baseline methods in terms of localization accuracy, robustness, and cost-effectiveness. The code and datasets used in this study are publicly available at: https://github.com/WU-Dongze/MetaLoc.

Förderung

  • NSFC
  • Basic Research Project
  • National Key R&D Program of China
  • Shenzhen Outstanding Talents Training Fund
  • Guangdong Research Projects
  • Guangdong Provincial Key Laboratory of Future Networks of Intelligence
  • Shenzhen Key Laboratory of Big Data and Artificial Intelligence
  • Key Area R&D Program of Guangdong Province

Zitieren

APA

Gao, J., Wu, D., Yin, F., Kong, Q., Xu, L., & Cui, S. (2023). MetaLoc: Learning to Learn Wireless Localization. IEEE Journal on Selected Areas in Communications, 41(12), 3831-3847. https://doi.org/10.1109/jsac.2023.3322766

Vancouver

Gao J, Wu D, Yin F, Kong Q, Xu L, Cui S. MetaLoc: Learning to Learn Wireless Localization. IEEE Journal on Selected Areas in Communications. 2023;41(12):3831-3847. doi:10.1109/jsac.2023.3322766

BibTeX
@article{Gao2023,
  author = {Gao, Jun and Wu, Dongze and Yin, Feng and Kong, Qinglei and Xu, Lexi and Cui, Shuguang},
  title = {MetaLoc: Learning to Learn Wireless Localization},
  journal = {IEEE Journal on Selected Areas in Communications},
  year = {2023},
  volume = {41},
  number = {12},
  pages = {3831--3847},
  doi = {10.1109/jsac.2023.3322766}
}
Kostenlos starten →