EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Few-Shot Learning in Wi-Fi-Based Indoor Positioning

Feng Xie, Soi Hoi Lam iD, Ming Xie iD, Cheng Wang

Biomimetics · 12.09.2024 · 9 (9) · 551

DOI: 10.3390/biomimetics9090551 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biomimetics, online erschienen am 12.09.2024. Verfasst von Feng Xie und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Science and Technology, Sanda University, Shanghai 201209, China. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Funded Project of the Sanda University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper explores the use of few-shot learning in Wi-Fi-based indoor positioning, utilizing convolutional neural networks (CNNs) combined with meta-learning techniques to enhance the accuracy and efficiency of positioning systems. The focus is on addressing the challenge of limited labeled data, a prevalent issue in extensive indoor environments. The study explores various scenarios, comparing the performance of the base CNN and meta-learning models. The meta-learning approach involves few-shot learning tasks, such as three-way N-shot, five-way N-shot, etc., to enhance the model’s ability to generalize from limited data. The experiments were conducted across various scenarios, evaluating the performance of the models with different numbers of samples per class (K) after filtering by cosine similarity (FCS) during both the stages of data preprocessing and meta-learning. The scenarios included both base classes and novel classes, with and without meta-learning. The results indicated that the base CNN model achieved varying accuracy levels depending on the scenario and the number of samples per class retained after FCS. Meta-learning performed acceptably in scenarios with fewer samples, which are the distinct datasets pertaining to novel classes. With 20 samples per class, the base CNN achieved an accuracy of 0.80 during the pre-training stage, while meta-learning (three-way one-shot) achieved an accuracy of 0.78 on a new small dataset with novel classes.

Schlagwörter

Stichwörter der Autor:innen

cosine similarityfew-sample learningfew-shot learningindoor positioninglimited labeled datameta-learning

Autor:innen und Institutionen

  • School of Information Science and Technology, Sanda University, Shanghai 201209, China.
  • Faculty of Science and Technology, University of Macau, Macau 999078, China.
  • School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore 639798, Singapore.

ORCID-Profile: Soi Hoi Lam, Ming Xie

Förderung

  • Key Funded Project of the Sanda University

Zitieren

APA

Xie, F., Lam, S. H., Xie, M., & Wang, C. (2024). Few-Shot Learning in Wi-Fi-Based Indoor Positioning. Biomimetics, 9(9), 551. https://doi.org/10.3390/biomimetics9090551

Vancouver

Xie F, Lam SH, Xie M, Wang C. Few-Shot Learning in Wi-Fi-Based Indoor Positioning. Biomimetics. 2024;9(9):551. doi:10.3390/biomimetics9090551

BibTeX
@article{Xie2024,
  author = {Xie, Feng and Lam, Soi Hoi and Xie, Ming and Wang, Cheng},
  title = {Few-Shot Learning in Wi-Fi-Based Indoor Positioning},
  journal = {Biomimetics},
  year = {2024},
  volume = {9},
  number = {9},
  pages = {551},
  doi = {10.3390/biomimetics9090551}
}
Kostenlos starten →