EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Privacy and Energy-Aware Federated Framework for Human Activity Recognition

Ahsan Raza Khan iD, Habib Ullah Manzoor iD, Fahad Ayaz iD, Muhammad Ali Imran iD, Ahmed Zoha iD

Sensors · 22.11.2023 · 23 (23) · 9339

DOI: 10.3390/s23239339 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 22.11.2023. Verfasst von Ahsan Raza Khan und 4 weiteren Autor:innen. Beteiligte Einrichtung: James Watt School of Engineering, University of Glasgow, Glasgow G12 8QQ, UK. Hauptthemen laut MEDLINE: Privacy, Awareness. Die Arbeit wurde bisher 35-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Human activity recognition (HAR) using wearable sensors enables continuous monitoring for healthcare applications. However, the conventional centralised training of deep learning models on sensor data poses challenges related to privacy, communication costs, and on-device efficiency. This paper proposes a federated learning framework integrating spiking neural networks (SNNs) with long short-term memory (LSTM) networks for energy-efficient and privacy-preserving HAR. The hybrid spiking-LSTM (S-LSTM) model synergistically combines the event-driven efficiency of SNNs and the sequence modelling capability of LSTMs. The model is trained using surrogate gradient learning and backpropagation through time, enabling fully supervised end-to-end learning. Extensive evaluations of two public datasets demonstrate that the proposed approach outperforms LSTM, CNN, and S-CNN models in accuracy and energy efficiency. For instance, the proposed S-LSTM achieved an accuracy of 97.36% and 89.69% for indoor and outdoor scenarios, respectively. Furthermore, the results also showed a significant improvement in energy efficiency of 32.30%, compared to simple LSTM. Additionally, we highlight the significance of personalisation in HAR, where fine-tuning with local data enhances model accuracy by up to 9% for individual users.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

PrivacyAwarenessHumansPhysical PhenomenaCommunicationHuman Activities

Stichwörter der Autor:innen

CNNLSTMfederated learninghuman activity recognitionspiking neural networkwearable sensing

Autor:innen und Institutionen

  • James Watt School of Engineering, University of Glasgow, Glasgow G12 8QQ, UK.
  • FSD-Campus, University of Engineering and Technology, Lahore 38000, Pakistan.

ORCID-Profile: Ahsan Raza Khan, Habib Ullah Manzoor, Fahad Ayaz, Muhammad Ali Imran, Ahmed Zoha

Zitieren

APA

Khan, A. R., Manzoor, H. U., Ayaz, F., Imran, M. A., & Zoha, A. (2023). A Privacy and Energy-Aware Federated Framework for Human Activity Recognition. Sensors, 23(23), 9339. https://doi.org/10.3390/s23239339

Vancouver

Khan AR, Manzoor HU, Ayaz F, Imran MA, Zoha A. A Privacy and Energy-Aware Federated Framework for Human Activity Recognition. Sensors. 2023;23(23):9339. doi:10.3390/s23239339

BibTeX
@article{Khan2023,
  author = {Khan, Ahsan Raza and Manzoor, Habib Ullah and Ayaz, Fahad and Imran, Muhammad Ali and Zoha, Ahmed},
  title = {A Privacy and Energy-Aware Federated Framework for Human Activity Recognition},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {23},
  pages = {9339},
  doi = {10.3390/s23239339}
}
Kostenlos starten →