EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

STAR: A Privacy-Preserving, Energy-Efficient Edge AI Framework for Human Activity Recognition via Wi-Fi CSI in Mobile and Pervasive Computing Environments

Kexing Liu, Qiang Zhao, Rui Wang iD, Yuchu Lin, Jiahui Yu, Simon James Fong iD

Sensors · 2026

DOI: 10.3390/s26123692 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2026. Verfasst von Kexing Liu und 5 weiteren Autor:innen. Beteiligte Einrichtung: ZUMRI-DeepFuture Technology Joint Lab, The Zhuhai UM Science & Technology Research Institute (ZUMRI), Zhuhai 519000, China. Hauptthemen laut MEDLINE: Human Activities, Privacy, Wireless Technology, Artificial Intelligence. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Development Fund, University of Macau, ZUMRI-DeepFuture Technology Joint Lab.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Human activity recognition (HAR) using Wi-Fi channel state information (CSI) offers a privacy-preserving and contactless sensing modality suitable for smart homes, healthcare monitoring, and pervasive mobile Internet of Things (IoT) environments. However, existing CSI-based HAR approaches often suffer from computational inefficiency, high latency, and limited feasibility on resource-constrained embedded platforms. This work presents STAR (Sensing Technology for Activity Recognition), an edge AI-optimized framework that integrates lightweight temporal modeling, adaptive signal processing, and hardware-aware co-optimization to enable real-time, energy-efficient HAR on low-power embedded devices. STAR employs a streamlined three-layer Gated Recurrent Unit (GRU) architecture that reduces model parameters by 33% compared to conventional Long Short-Term Memory (LSTM) designs while maintaining strong temporal modeling capability. To enhance signal quality, STAR incorporates a multi-stage pre-processing pipeline consisting of median filtering, an eighth-order Butterworth low-pass filtering, and empirical mode decomposition (EMD) to denoise CSI amplitude measurements and extract stable spatial-temporal features. For on-device deployment, the system is implemented on a Rockchip RV1126 processor equipped with an embedded Neural Processing Unit (NPU) and interfaced with an ESP32-S3 CSI acquisition module. Experimental results demonstrate a mean recognition accuracy of 93.52% across seven activity classes and 99.11% for human-presence detection using a compact 97.6k-parameter model. INT8-quantized inference achieves a processing throughput of 33 MHz with only 8% CPU utilization, achieving a six-fold improvement in inference speed over CPU-based execution. With sub-second response latency and low power consumption, the system ensures real-time, privacy-preserving HAR, offering a practical, scalable solution for mobile and pervasive computing environments.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Human ActivitiesPrivacyWireless TechnologyArtificial IntelligenceHumansSignal Processing, Computer-AssistedInternet of ThingsAlgorithmsIntelligent SystemsLong Short Term Memory

Stichwörter der Autor:innen

Wi-Fi CSIedge AIembedded edge deviceshuman activity recognitionmobile IoTprivacy-preserving sensing

Autor:innen und Institutionen

  • ZUMRI-DeepFuture Technology Joint Lab, The Zhuhai UM Science & Technology Research Institute (ZUMRI), Zhuhai 519000, China.
  • School of Communication and Information Engineering, Shanghai University, Shanghai 200444, China.
  • School of Computer Science and Engineering, Macau University of Science and Technology, Macau SAR 999078, China.
  • Department of Computer and Information Science, Faculty of Science and Technology, University of Macau, Macau SAR 999078, China.

ORCID-Profile: Rui Wang, Simon James Fong

Förderung

  • Science and Technology Development Fund
  • University of Macau
  • ZUMRI-DeepFuture Technology Joint Lab

Zitieren

APA

Liu, K., Zhao, Q., Wang, R., Lin, Y., Yu, J., & Fong, S. J. (2026). STAR: A Privacy-Preserving, Energy-Efficient Edge AI Framework for Human Activity Recognition via Wi-Fi CSI in Mobile and Pervasive Computing Environments. Sensors. https://doi.org/10.3390/s26123692

Vancouver

Liu K, Zhao Q, Wang R, Lin Y, Yu J, Fong SJ. STAR: A Privacy-Preserving, Energy-Efficient Edge AI Framework for Human Activity Recognition via Wi-Fi CSI in Mobile and Pervasive Computing Environments. Sensors. 2026. doi:10.3390/s26123692

BibTeX
@article{Liu2026,
  author = {Liu, Kexing and Zhao, Qiang and Wang, Rui and Lin, Yuchu and Yu, Jiahui and Fong, Simon James},
  title = {STAR: A Privacy-Preserving, Energy-Efficient Edge AI Framework for Human Activity Recognition via Wi-Fi CSI in Mobile and Pervasive Computing Environments},
  journal = {Sensors},
  year = {2026},
  doi = {10.3390/s26123692}
}
Kostenlos starten →