Deep Learning-Enabled Edge Computing Framework for Real-Time Monitoring and Optimization of Medical Data

R. Suganya, K. Ruth Isabels, M. Ambika, Sabitha Valaboju, Eniyan S., C. Umarani

2025

Abstract

Thus, the convergence of deep learning and edge computing has been proposed for real-time monitoring and optimization of medical data. In this paper, a new Edge-Aware Deep Learning Architecture is presented for the privacy-preserving, energy-efficient and scalable healthcare solution. In contrast to traditional cloud-based models, this framework allows for on-device inference, which reduces response times while also preventing the potential exposure of private patient data by using local data processing techniques. It employs lightweight model compression methods, including pruning and quantization, to minimize power usage and prolong wearables' lifetime in the wearable medical device domain. Edge-specific fine-tuning, coupled with knowledge distillation to promote their use in end systems, is thus adopted to perform their strict deployment with sustaining high diagnostic performance. Moreover, the framework is also designed to support federated learning and interoperable data protocols, allowing it to interface with current hospital infrastructure as well as enabling collective learning across geographically distributed systems. Experiments that are performed in different edge devices also validate that the solution is scalable and fit in for urban and rural healthcare ecosystem. In summary, this architecture represents a game-changing step towards intelligent, contextualized, and secure healthcare analytics at the edge.

Paper Citation

in Harvard Style

Suganya R., Isabels K., Ambika M., Valaboju S., S. E. and Umarani C. (2025). Deep Learning-Enabled Edge Computing Framework for Real-Time Monitoring and Optimization of Medical Data. 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 562-570. DOI: 10.5220/0013869300004919

in Bibtex Style

@conference{icrdicct`2525,
author={R. Suganya and K. Isabels and M. Ambika and Sabitha Valaboju and Eniyan S. and C. Umarani},
title={Deep Learning-Enabled Edge Computing Framework for Real-Time Monitoring and Optimization of Medical Data},
booktitle={Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - Volume 1: ICRDICCT`25},
year={2025},
pages={562-570},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013869300004919},
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 - Deep Learning-Enabled Edge Computing Framework for Real-Time Monitoring and Optimization of Medical Data
SN - 978-989-758-777-1
AU - Suganya R.
AU - Isabels K.
AU - Ambika M.
AU - Valaboju S.
AU - S. E.
AU - Umarani C.
PY - 2025
SP - 562
EP - 570
DO - 10.5220/0013869300004919
PB - SciTePress