EUVIMEDEUVIMED entdecken
Crossref

WiPhase: A Human Activity Recognition Approach by Fusing of Reconstructed WiFi CSI Phase Features

Xingcan Chen, Chenglin Li, Chengpeng Jiang, Wei Meng, Wendong Xiao

IEEE Transactions on Mobile Computing · 2025-01 · 24 (1) · 394-406

DOI: 10.1109/tmc.2024.3461672 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2025-01. Verfasst von Xingcan Chen und 4 weiteren Autor:innen. Die Arbeit wurde bisher 38-mal zitiert (Crossref) und nennt 38 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Foshan Science and Technology Innovation Special Project, Regional Joint Fund of the Guangdong Basic and Applied Basic Research Fund.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Human activity recognition (HAR) is an important task in the field of human-computer interaction. Given the penetration of WiFi devices in our daily lives, HAR using WiFi channel state information (CSI) is a more cost-efficient and comfortable approach. However, most existing approaches ignore the correlation between CSI sub-carriers, which makes their models inefficient and need to rely on deeper and more complex networks to further improve performance. To solve these problems, we propose a reconstructed WiFi CSI phase based HAR approach (WiPhase), which contains a two-stream model to fuse both temporal features and sub-carrier correlation features of reconstructed CSI phase. Specifically, a gated pseudo-Siamese network (GPSiam) is designed to capture the temporal features of the reconstructed sparse CSI phase integration representation (CSI-PIR), and a dynamic resolution based graph attention network (DRGAT) is designed to capture the nonlinear correlation between CSI sub-carriers by the reconstructed CSI phase graph. Furthermore, dendrite network (DD) makes the final decision by combining the features output from GPSiam and DRGAT. Experimental results show that WiPhase outperforms the existing state-of-the-art approaches.

Förderung

  • National Natural Science Foundation of China
  • Foshan Science and Technology Innovation Special Project
  • Regional Joint Fund of the Guangdong Basic and Applied Basic Research Fund

Zitieren

APA

Chen, X., Li, C., Jiang, C., Meng, W., & Xiao, W. (2025). WiPhase: A Human Activity Recognition Approach by Fusing of Reconstructed WiFi CSI Phase Features. IEEE Transactions on Mobile Computing, 24(1), 394-406. https://doi.org/10.1109/tmc.2024.3461672

Vancouver

Chen X, Li C, Jiang C, Meng W, Xiao W. WiPhase: A Human Activity Recognition Approach by Fusing of Reconstructed WiFi CSI Phase Features. IEEE Transactions on Mobile Computing. 2025;24(1):394-406. doi:10.1109/tmc.2024.3461672

BibTeX
@article{Chen2025,
  author = {Chen, Xingcan and Li, Chenglin and Jiang, Chengpeng and Meng, Wei and Xiao, Wendong},
  title = {WiPhase: A Human Activity Recognition Approach by Fusing of Reconstructed WiFi CSI Phase Features},
  journal = {IEEE Transactions on Mobile Computing},
  year = {2025},
  volume = {24},
  number = {1},
  pages = {394--406},
  doi = {10.1109/tmc.2024.3461672}
}
Kostenlos starten →