EUVIMEDEUVIMED entdecken
Open Access · CC BY 3.0

Lightweight privacy-preserving human activity recognition from CSI data using a CNN-temporal attention network

Khondakar Ashik Shahriar, Maruf Ahmed, Hafiz Imtiaz

Digital Discovery · 2026 · 5 (6) · 2701-2715

DOI: 10.1039/d6dd00077k ↗

Kurz gefasst

Fachartikel in der Zeitschrift Digital Discovery, 2026. Verfasst von Khondakar Ashik Shahriar und 2 weiteren Autor:innen. Die Arbeit nennt 98 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 3.0). Gefördert von: Bangladesh University of Engineering and Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We propose an end-to-end privacy-preserving CSI-based HAR framework integrating a CNN with temporal attention, which outperforms existing studies on multiple benchmark datasets with distance, height and environmental variations.

Förderung

  • Bangladesh University of Engineering and Technology

Zitieren

APA

Shahriar, K. A., Ahmed, M., & Imtiaz, H. (2026). Lightweight privacy-preserving human activity recognition from CSI data using a CNN-temporal attention network. Digital Discovery, 5(6), 2701-2715. https://doi.org/10.1039/d6dd00077k

Vancouver

Shahriar KA, Ahmed M, Imtiaz H. Lightweight privacy-preserving human activity recognition from CSI data using a CNN-temporal attention network. Digital Discovery. 2026;5(6):2701-2715. doi:10.1039/d6dd00077k

BibTeX
@article{Shahriar2026,
  author = {Shahriar, Khondakar Ashik and Ahmed, Maruf and Imtiaz, Hafiz},
  title = {Lightweight privacy-preserving human activity recognition from CSI data using a CNN-temporal attention network},
  journal = {Digital Discovery},
  year = {2026},
  volume = {5},
  number = {6},
  pages = {2701--2715},
  doi = {10.1039/d6dd00077k}
}
Kostenlos starten →