EUVIMEDEUVIMED entdecken
Crossref

KNN-MMD: Cross Domain Wireless Sensing via Local Distribution Alignment

Zijian Zhao, Zhijie Cai, Tingwei Chen, Xiaoyang Li, Hang Li, Qimei Chen, Guangxu Zhu

IEEE Transactions on Mobile Computing · 2026-06 · 25 (6) · 8093-8110

DOI: 10.1109/tmc.2025.3644902 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2026-06. Verfasst von Zijian Zhao und 6 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 49 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Shenzhen-Hong Kong-Macau Technology Research Programme, Shenzhen Science and Technology Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Wireless sensing has recently found widespread applications in diverse environments, including homes, offices, and public spaces, utilizing Channel State Information (CSI). However, CSI is highly sensitive to environmental changes, where even minor alterations can significantly distort the CSI patterns. This sensitivity often leads to performance degradation when applying models trained in one environment to another. To address this challenge, Domain Alignment Learning (DAL) has been widely adopted for cross-domain tasks, as it focuses on aligning the global distributions of the source and target domains in feature space. Despite its popularity, DAL often neglects inter-category relationships, which can lead to misalignment between categories across domains, even when global alignment is achieved. To overcome it, we propose KNN-MMD, a novel few-shot method for cross-domain wireless sensing. Our approach begins by constructing a "help set" using K-Nearest Neighbors (KNN) from the target domain, enabling local alignment between the source and target domains within each category using Maximum Mean Discrepancy (MMD). Additionally, most existing methods struggle to determine an optimal stopping point during training due to the absence of labeled data from the target domain. Our method resolves this by excluding the support set from the target domain during training and employing it as a validation set to determine the stopping criterion. We evaluate the proposed method across several cross-domain Wi-Fi sensing tasks, including gesture recognition, person identification, fall detection, and action recognition. In a one-shot scenario, our method achieves accuracy rates of 93.26%, 81.84%, 77.62%, and 75.30% for the respective tasks.

Förderung

  • National Natural Science Foundation of China
  • Shenzhen-Hong Kong-Macau Technology Research Programme
  • Shenzhen Science and Technology Program
  • Guangdong Young Talent Research Project
  • Young Elite Scientists Sponsorship Program by CAST
  • Major Program (JD) of Hubei Province
  • Wuhan Science and Technology Achievement Transformation Project

Zitieren

APA

Zhao, Z., Cai, Z., Chen, T., Li, X., Li, H., Chen, Q., & Zhu, G. (2026). KNN-MMD: Cross Domain Wireless Sensing via Local Distribution Alignment. IEEE Transactions on Mobile Computing, 25(6), 8093-8110. https://doi.org/10.1109/tmc.2025.3644902

Vancouver

Zhao Z, Cai Z, Chen T, Li X, Li H, Chen Q, et al. KNN-MMD: Cross Domain Wireless Sensing via Local Distribution Alignment. IEEE Transactions on Mobile Computing. 2026;25(6):8093-8110. doi:10.1109/tmc.2025.3644902

BibTeX
@article{Zhao2026,
  author = {Zhao, Zijian and Cai, Zhijie and Chen, Tingwei and Li, Xiaoyang and Li, Hang and Chen, Qimei and Zhu, Guangxu},
  title = {KNN-MMD: Cross Domain Wireless Sensing via Local Distribution Alignment},
  journal = {IEEE Transactions on Mobile Computing},
  year = {2026},
  volume = {25},
  number = {6},
  pages = {8093--8110},
  doi = {10.1109/tmc.2025.3644902}
}
Kostenlos starten →