EUVIMEDEUVIMED entdecken
Crossref

Imbalanced Semi-Supervised Learning for WiFi Gesture Recognition via Dynamic Threshold-Based Spatio-Temporal Attention Networks

Qihua Feng, Chunhui Duan, Jiawei Xue, Chaozhuo Li, Feiran Huang, Xi Zhang, Jian Weng, Philip S. Yu

IEEE Transactions on Mobile Computing · 2026-01 · 25 (1) · 483-499

DOI: 10.1109/tmc.2025.3592965 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2026-01. Verfasst von Qihua Feng und 7 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 80 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Beijing Institute of Technology Research Fund Program for Young Scholars, Science and Technology Major Project of Tibetan Autonomous Region of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

WiFi sensing advancements facilitate the capture of human gestures from wireless signals, ensuring both privacy preservation and robustness under low-light conditions. Deep learning-based WiFi Human Gesture Recognition (HGR) demonstrates remarkable performance in handling complex gestures. To reduce labeling efforts, recent years have seen the emergence of semi-supervised WiFi HGR, leveraging massive amounts of unlabeled data. However, existing semi-supervised schemes often assume a balanced class distribution and utilize a fixed threshold for selecting pseudo-labels of unlabeled samples, leading to low performance for minority classes and decreased model generalization on real-world imbalanced datasets. To address this issue, we propose a novel semi-supervised WiFi HGR approach with dynamic pseudo-labeling thresholds to handle imbalanced class distribution, incorporating Spatial-Temporal Attention (STA) networks. Unlike using a fixed threshold for all unlabeled samples, our design implements class-independent thresholds for different classes, dynamically adjusting them by encoding pseudo-label distribution during training. To emphasize critical features in informative areas within the WiFi signals, we incorporate both spatial self-attention and temporal attention mechanisms to dynamically learn salient features and identify pivotal frames, respectively. Moreover, we introduce adaptive WiFi data augmentations that propel the semi-supervised framework and enhance model robustness. Experimental results on the Widar3.0 dataset reveal that our approach outperforms existing semi-supervised methods by large margins in accuracy, effectively mitigating imbalanced bias and enhancing model generalization.

Förderung

  • National Natural Science Foundation of China
  • Beijing Institute of Technology Research Fund Program for Young Scholars
  • Science and Technology Major Project of Tibetan Autonomous Region of China
  • Open Research Fund of Machine Learning and Cyber Security Interdiscipline Research Engineering Center of Jiangsu Province
  • National Joint Engineering Research Center of Network Security Detection and Protection Technology
  • Guangdong Key Laboratory of Data Security and Privacy Preserving
  • Guangdong Hong Kong Joint Laboratory for Data Security and Privacy Protection
  • Engineering Research Center of Trustworthy AI

Zitieren

APA

Feng, Q., Duan, C., Xue, J., Li, C., Huang, F., Zhang, X., Weng, J., & Yu, P. S. (2026). Imbalanced Semi-Supervised Learning for WiFi Gesture Recognition via Dynamic Threshold-Based Spatio-Temporal Attention Networks. IEEE Transactions on Mobile Computing, 25(1), 483-499. https://doi.org/10.1109/tmc.2025.3592965

Vancouver

Feng Q, Duan C, Xue J, Li C, Huang F, Zhang X, et al. Imbalanced Semi-Supervised Learning for WiFi Gesture Recognition via Dynamic Threshold-Based Spatio-Temporal Attention Networks. IEEE Transactions on Mobile Computing. 2026;25(1):483-499. doi:10.1109/tmc.2025.3592965

BibTeX
@article{Feng2026,
  author = {Feng, Qihua and Duan, Chunhui and Xue, Jiawei and Li, Chaozhuo and Huang, Feiran and Zhang, Xi and Weng, Jian and Yu, Philip S.},
  title = {Imbalanced Semi-Supervised Learning for WiFi Gesture Recognition via Dynamic Threshold-Based Spatio-Temporal Attention Networks},
  journal = {IEEE Transactions on Mobile Computing},
  year = {2026},
  volume = {25},
  number = {1},
  pages = {483--499},
  doi = {10.1109/tmc.2025.3592965}
}
Kostenlos starten →