Lightweight Deep Learning for Real-Time Health Monitoring on Edge Devices

K. Sindhuja, K. Akila, M. Dharani, G. Nagarjunarao, Akash K.

2025

Abstract

Deep learning in edge computing is revolutionizing healthcare, delivering real-time tracking of crucial health variables on mobile and wearable. We propose to design "lightweight" deep learning models that are tailored for small scale edge devices. The proposed framework solves the problems concerning the limited computational capacity, energy consumption, and variability of the physiological signals, in order to accomplish a reliable, real-time physiological analysis with cloud connectivity not required. The system is optimized for deployment at the edge, providing low-latency and high-throughput performance under realistic conditions and enabling real-time health monitoring, early detection of anomalies, and personalized feedback. Experimental results show promising accuracy and low resource consumption for the models, making them practically deployable in large-scale mobile health ecosystems.

Paper Citation

in Harvard Style

Sindhuja K., Akila K., Dharani M., Nagarjunarao G. and K. A. (2025). Lightweight Deep Learning for Real-Time Health Monitoring on Edge Devices. In Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - Volume 1: ICRDICCT`25; ISBN 978-989-758-777-1, SciTePress, pages 243-249. DOI: 10.5220/0013862100004919

in Bibtex Style

@conference{icrdicct`2525,
author={K. Sindhuja and K. Akila and M. Dharani and G. Nagarjunarao and Akash K.},
title={Lightweight Deep Learning for Real-Time Health Monitoring on Edge Devices},
booktitle={Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - Volume 1: ICRDICCT`25},
year={2025},
pages={243-249},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013862100004919},
isbn={978-989-758-777-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - Volume 1: ICRDICCT`25
TI - Lightweight Deep Learning for Real-Time Health Monitoring on Edge Devices
SN - 978-989-758-777-1
AU - Sindhuja K.
AU - Akila K.
AU - Dharani M.
AU - Nagarjunarao G.
AU - K. A.
PY - 2025
SP - 243
EP - 249
DO - 10.5220/0013862100004919
PB - SciTePress