Secure and Decentralized Deep Learning: Federated Intelligence for Privacy - Preserving Smart Healthcare Systems

M. Udhayakumar, M. Dharani, T. Marthandan, Manoj Kumar S., Rithika T., Riyas R.

2025

Abstract

Aim: The research formulates a secure, decentralized deep learning model based on federated intelligence for privacy-friendly smart healthcare systems. Materials and Methods:  Through the implementation of federated deep learning algorithms that allows multiple devices to train a model without sharing data, the system improves security with accuracy collaboratively. Group 1 Data Preservation has been secured under SVM and ANN algorithms in Machine Learning and Group 2 Federated deep learning with Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) models is a powerful approach for training sequential data models in a decentralized manner. Results: Federated model delivers higher accuracy (88.23% – 96.45%) than the existing model (78.56% -- 91.32%), reaches a maximum of 94.87% accuracy and Significance-value equal to 0.0043. Conclusion:  In this project, the results of federated intelligence-based deep learning confirm that it provides strong privacy assurance while maintaining higher model accuracy than the SVM and ANN Machine Learning algorithms.

Paper Citation

in Harvard Style

Udhayakumar M., Dharani M., Marthandan T., S. M., T. R. and R. R. (2025). Secure and Decentralized Deep Learning: Federated Intelligence for Privacy - Preserving Smart Healthcare Systems. In Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25; ISBN 978-989-758-777-1, SciTePress, pages 144-148. DOI: 10.5220/0013924200004919

in Bibtex Style

@conference{icrdicct`2525,
author={M. Udhayakumar and M. Dharani and T. Marthandan and Manoj S. and Rithika T. and Riyas R.},
title={Secure and Decentralized Deep Learning: Federated Intelligence for Privacy - Preserving Smart Healthcare Systems},
booktitle={Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25},
year={2025},
pages={144-148},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013924200004919},
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 - ICRDICCT`25
TI - Secure and Decentralized Deep Learning: Federated Intelligence for Privacy - Preserving Smart Healthcare Systems
SN - 978-989-758-777-1
AU - Udhayakumar M.
AU - Dharani M.
AU - Marthandan T.
AU - S. M.
AU - T. R.
AU - R. R.
PY - 2025
SP - 144
EP - 148
DO - 10.5220/0013924200004919
PB - SciTePress