EUVIMEDEUVIMED entdecken
Crossref

Lightweight CSI-Based Human Activity Recognition for Multitask IoT Applications

Chenchen Liu, Fucheng Miao, Yiting Chen, Jiangbo Wu, Hong Wan, Tiantian Tang, Tomoaki Ohtsuki, Guan Gui, Hikmet Sari

IEEE Internet of Things Journal · 01.09.2025 · 12 (17) · 35817-35827

DOI: 10.1109/jiot.2025.3580141 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Internet of Things Journal, erschienen am 01.09.2025. Verfasst von Chenchen Liu und 8 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 35 Literaturangaben. Gefördert von: Natural Science Foundation of China, Key Project of the Natural Science Foundation of the Higher Education Institutions of Jiangsu Province, Japan Science and Technology Agency (JST) Adopting Sustainable Partnerships for Innovative Research Ecosystem (ASPIRE) program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As the global population continues to age and technologies, such as the Internet of Things (IoT) and edge computing advance rapidly, indoor human activity recognition (HAR)-based on Wi-Fi channel state information (CSI) has gained significant research attention. However, the high computational complexity of existing HAR methods limits their deployment on resource-constrained devices. To address this challenge, we propose a lightweight HAR method using branch decision lightweight two-stream convolution-augmented transformer (BLTHAT) model, which integrates depthwise separable convolutions (DSC) and an improved framework structure to enhance computational efficiency. Additionally, we introduce the branch fusion network (BFN), a decision-making module designed to optimize feature processing and improve model robustness. Further enhancements in attention mechanisms and regularization strategies contribute to reducing complexity while maintaining high recognition accuracy. Comprehensive experiments were conducted on a multilabel dataset. The results demonstrate that our proposed HAR method achieves high computational efficiency with minimal complexity, making it well-suited for IoT applications. Ablation studies further confirm that the multibranch structure of the BFN module enhances feature extraction without significantly increasing computational overhead.

Förderung

  • Natural Science Foundation of China
  • Key Project of the Natural Science Foundation of the Higher Education Institutions of Jiangsu Province
  • Japan Science and Technology Agency (JST) Adopting Sustainable Partnerships for Innovative Research Ecosystem (ASPIRE) program

Zitieren

APA

Liu, C., Miao, F., Chen, Y., Wu, J., Wan, H., Tang, T., Ohtsuki, T., Gui, G., & Sari, H. (2025). Lightweight CSI-Based Human Activity Recognition for Multitask IoT Applications. IEEE Internet of Things Journal, 12(17), 35817-35827. https://doi.org/10.1109/jiot.2025.3580141

Vancouver

Liu C, Miao F, Chen Y, Wu J, Wan H, Tang T, et al. Lightweight CSI-Based Human Activity Recognition for Multitask IoT Applications. IEEE Internet of Things Journal. 2025;12(17):35817-35827. doi:10.1109/jiot.2025.3580141

BibTeX
@article{Liu2025,
  author = {Liu, Chenchen and Miao, Fucheng and Chen, Yiting and Wu, Jiangbo and Wan, Hong and Tang, Tiantian and Ohtsuki, Tomoaki and Gui, Guan and Sari, Hikmet},
  title = {Lightweight CSI-Based Human Activity Recognition for Multitask IoT Applications},
  journal = {IEEE Internet of Things Journal},
  year = {2025},
  volume = {12},
  number = {17},
  pages = {35817--35827},
  doi = {10.1109/jiot.2025.3580141}
}
Kostenlos starten →