EUVIMEDEUVIMED entdecken
Crossref

Towards Stable WiFi-based HAR from Imbalanced Data and Changing Circumstances

Youquan Wang, Zhipeng Zhou, Shuai Wang, Xianjun Deng, Wei Xi, Wei Gong

ACM Transactions on Sensor Networks · 30.09.2025 · 21 (5) · 1-23

DOI: 10.1145/3757321 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Sensor Networks, online erschienen am 24.09.2025. Verfasst von Youquan Wang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 65 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

WiFi-based human activity recognition (WiFi-based HAR) has emerged as a technology in recent decades, offering convenient and privacy-friendly applications. However, existing frameworks designed for stable environments encounter challenges when faced with changing circumstances and imbalanced training datasets in realistic scenarios. In this article, we address both issues from a unified perspective by exploring a more generalized local minima. Initially, we revisit existing solutions and empirically observe the presence of sharp minima in trained long-tailed WiFi-based HAR models. Consequently, we propose a novel method called Class Region Flattening ( CRF ) to identify class-conditional flat minima. This approach effectively mitigates bias caused by the long-tailed distribution and enhances generalization capabilities in the face of changing circumstances. Furthermore, we introduce a selective flattening operation to prevent optimization conflicts among different activity categories and reduce computational overhead. We integrate CRF into mainstream WiFi-based HAR models and evaluate their performance using our collected WiFi-based HAR dataset. Through extensive experiments, we demonstrate that the incorporation of CRF leads to significant improvements in performance. These findings underscore the effectiveness of CRF in addressing the challenges posed by changing circumstances and imbalanced training datasets in WiFi-based HAR.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Wang, Y., Zhou, Z., Wang, S., Deng, X., Xi, W., & Gong, W. (2025). Towards Stable WiFi-based HAR from Imbalanced Data and Changing Circumstances. ACM Transactions on Sensor Networks, 21(5), 1-23. https://doi.org/10.1145/3757321

Vancouver

Wang Y, Zhou Z, Wang S, Deng X, Xi W, Gong W. Towards Stable WiFi-based HAR from Imbalanced Data and Changing Circumstances. ACM Transactions on Sensor Networks. 2025;21(5):1-23. doi:10.1145/3757321

BibTeX
@article{Wang2025,
  author = {Wang, Youquan and Zhou, Zhipeng and Wang, Shuai and Deng, Xianjun and Xi, Wei and Gong, Wei},
  title = {Towards Stable WiFi-based HAR from Imbalanced Data and Changing Circumstances},
  journal = {ACM Transactions on Sensor Networks},
  year = {2025},
  volume = {21},
  number = {5},
  pages = {1--23},
  doi = {10.1145/3757321}
}
Kostenlos starten →