EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Tools and Methods for Achieving Wi-Fi Sensing in Embedded Devices

Jesus A Armenta-Garcia iD, Felix F Gonzalez-Navarro iD, Jesus Caro-Gutierrez iD, Conrado I Garcia-Reyes iD

Sensors · 08.10.2025 · 25 (19) · 6220

DOI: 10.3390/s25196220 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 08.10.2025. Verfasst von Jesus A Armenta-Garcia und 3 weiteren Autor:innen. Beteiligte Einrichtung: Engineering Institute, Universidad Autonoma de Baja California, Calle de la Normal S/N Col. Insurgentes Este, Mexicali 21100, Mexico. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universidad Autonoma de Baja California, SECIHTI-Mexico.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Wi-Fi sensing has emerged as a powerful approach to Human Activity Recognition (HAR) by utilizing Channel State Information (CSI). However, current implementations face two significant challenges: reliance on firmware-modified hardware for CSI collection and dependence on GPU/cloud-based deep learning models for inference. To address these limitations, we propose a two-fold embedded solution: a novel CSI collection tool built on low-cost microcontrollers that surpass existing embedded alternatives in packet rate efficiency under standard baud rate conditions and an optimized DenseNet-based HAR model deployable on resource-constrained edge devices without cloud dependency. In addition, a new HAR dataset is presented. To deal with the scarcity of training data, an Empirical Mode Decomposition (EMD)-based data augmentation method is presented. With this strategy, it was possible to enhance model accuracy from 59.91% to 97.55%. Leveraging this enhanced dataset, a compact DenseNet variant is presented. An accuracy of 92.43% at 232 ms inference latency is achieved when implemented on an ESP32-S3 microcontroller. Using as little as 127 kB of memory, the proposed model offers acceptable performance in terms of accuracy and privacy-preserving HAR at the edge; it also represents a scalable and low-cost Wi-Fi sensing solution.

Schlagwörter

Stichwörter der Autor:innen

HARWi-Fi sensingdata augmentationdeep learning

Autor:innen und Institutionen

  • Engineering Institute, Universidad Autonoma de Baja California, Calle de la Normal S/N Col. Insurgentes Este, Mexicali 21100, Mexico.

ORCID-Profile: Jesus A Armenta-Garcia, Felix F Gonzalez-Navarro, Jesus Caro-Gutierrez, Conrado I Garcia-Reyes

Förderung

  • Universidad Autonoma de Baja California
  • SECIHTI-Mexico

Zitieren

APA

Armenta-Garcia, J. A., Gonzalez-Navarro, F. F., Caro-Gutierrez, J., & Garcia-Reyes, C. I. (2025). Tools and Methods for Achieving Wi-Fi Sensing in Embedded Devices. Sensors, 25(19), 6220. https://doi.org/10.3390/s25196220

Vancouver

Armenta-Garcia JA, Gonzalez-Navarro FF, Caro-Gutierrez J, Garcia-Reyes CI. Tools and Methods for Achieving Wi-Fi Sensing in Embedded Devices. Sensors. 2025;25(19):6220. doi:10.3390/s25196220

BibTeX
@article{ArmentaGarcia2025,
  author = {Armenta-Garcia, Jesus A and Gonzalez-Navarro, Felix F and Caro-Gutierrez, Jesus and Garcia-Reyes, Conrado I},
  title = {Tools and Methods for Achieving Wi-Fi Sensing in Embedded Devices},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {19},
  pages = {6220},
  doi = {10.3390/s25196220}
}
Kostenlos starten →