EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

VBCNet: A Hybird Network for Human Activity Recognition

Fei Ge iD, Zhenyang Dai, Zhimin Yang, Fei Wu, Liansheng Tan

Sensors · 05.12.2024 · 24 (23) · 7793

DOI: 10.3390/s24237793 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 05.12.2024. Verfasst von Fei Ge und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, Central China Normal University, Wuhan 430070, China. Hauptthemen laut MEDLINE: Human Activities, Neural Networks, Computer. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, China Higher Education Institution Industry-University-Research Innovation Fund.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, the research on human activity recognition based on channel state information (CSI) of Wi-Fi has gradually attracted much attention in order to avoid the deployment of additional devices and reduce the risk of personal privacy leakage. In this paper, we propose a hybrid network architecture, named VBCNet, that can effectively identify human activity postures. Firstly, we extract CSI sequences from each antenna of Wi-Fi signals, and the data are preprocessed and tokenised. Then, in the encoder part of the model, we introduce a layer of long short-term memory network to further extract the temporal features in the sequences and enhance the ability of the model to capture the temporal information. Meanwhile, VBCNet employs a convolutional feed-forward network instead of the traditional feed-forward network to enhance the model’s ability to process local and multi-scale features. Finally, the model classifies the extracted features into human behaviours through a classification layer. To validate the effectiveness of VBCNet, we conducted experimental evaluations on the classical human activity recognition datasets UT-HAR and Widar3.0 and achieved an accuracy of 98.65% and 77.92%. These results show that VBCNet exhibits extremely high effectiveness and robustness in human activity recognition tasks in complex scenarios.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Human ActivitiesNeural Networks, ComputerHumansWireless TechnologyAlgorithms

Stichwörter der Autor:innen

BiLSTMViTWi-Fi channel state informationbody-coordinate velocity profileconvolutional feed-forward

Autor:innen und Institutionen

  • School of Computer Science, Central China Normal University, Wuhan 430070, China.

ORCID-Profile: Fei Ge

Förderung

  • National Natural Science Foundation of China
  • China Higher Education Institution Industry-University-Research Innovation Fund

Zitieren

APA

Ge, F., Dai, Z., Yang, Z., Wu, F., & Tan, L. (2024). VBCNet: A Hybird Network for Human Activity Recognition. Sensors, 24(23), 7793. https://doi.org/10.3390/s24237793

Vancouver

Ge F, Dai Z, Yang Z, Wu F, Tan L. VBCNet: A Hybird Network for Human Activity Recognition. Sensors. 2024;24(23):7793. doi:10.3390/s24237793

BibTeX
@article{Ge2024,
  author = {Ge, Fei and Dai, Zhenyang and Yang, Zhimin and Wu, Fei and Tan, Liansheng},
  title = {VBCNet: A Hybird Network for Human Activity Recognition},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {23},
  pages = {7793},
  doi = {10.3390/s24237793}
}
Kostenlos starten →