EUVIMEDEUVIMED entdecken
Crossref

Personalized Human Activity Recognition: Real-Time On-Device Training and Inference

Bidyut Saha, Riya Samanta, Ram Babu Roy, Chinmay Chakraborty, Soumya K. Ghosh

IEEE Consumer Electronics Magazine · 2025-03 · 14 (2) · 84-89

DOI: 10.1109/mce.2024.3398294 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Consumer Electronics Magazine, 2025-03. Verfasst von Bidyut Saha und 4 weiteren Autor:innen. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 14 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The conventional human activity recognition (HAR) systems use smartwatches, smartphones, and other wearable devices to autonomously derive consumer physical activities. However, implementing real-time HAR in resource-constrained applications is challenging. Computational offloading approaches must address network reliance, latency, and data privacy, which affect system performance. The present study proposes a low-cost, wearable HAR device that collects and transmits the inertial measurement unit (IMU) telemetry signals to smartphones, enabling real-time on-device activity detection. Human actions are subjective and affected by physiological, environmental, and behavioral factors, complicating HAR systems’ performance in personalized contexts. Generalized methods for existing systems reduce performance for new consumers or due to alterations in consumer locomotive signatures. Thus, our second goal is to enable the on-device personalization of wearable HAR models with minimum customer calibration. The HAR device, which is in the form of a smart-band, transfers data to and from smartphones through Bluetooth Low Energy (BLE). A lightweight 1D convolutional neural network (CNN) is built and, using transfer learning, the network model is fine-tuned from real-time sensed data. On-device HAR inferences ensure real-time processing on smartphones without computational offloading. Smartphone-based on-device training for fine-tuning the model allows the HAR system to get customized without compromising privacy or computational costs. The experimental results show that the personalized classification achieves on average 98% accuracy when assessed using four benchmark datasets.

Zitieren

APA

Saha, B., Samanta, R., Roy, R. B., Chakraborty, C., & Ghosh, S. K. (2025). Personalized Human Activity Recognition: Real-Time On-Device Training and Inference. IEEE Consumer Electronics Magazine, 14(2), 84-89. https://doi.org/10.1109/mce.2024.3398294

Vancouver

Saha B, Samanta R, Roy RB, Chakraborty C, Ghosh SK. Personalized Human Activity Recognition: Real-Time On-Device Training and Inference. IEEE Consumer Electronics Magazine. 2025;14(2):84-89. doi:10.1109/mce.2024.3398294

BibTeX
@article{Saha2025,
  author = {Saha, Bidyut and Samanta, Riya and Roy, Ram Babu and Chakraborty, Chinmay and Ghosh, Soumya K.},
  title = {Personalized Human Activity Recognition: Real-Time On-Device Training and Inference},
  journal = {IEEE Consumer Electronics Magazine},
  year = {2025},
  volume = {14},
  number = {2},
  pages = {84--89},
  doi = {10.1109/mce.2024.3398294}
}
Kostenlos starten →