Back to Search Start Over

Revolutionizing COVID-19 Management: Block chain-Enabled Prediction and Secure Storage using Deep Learning Techniques.

Authors :
Arulmozhi, B.
Sheeba, Dr. J I
Devaneyan, S. Pradeep
Source :
Procedia Computer Science; 2023, Vol. 230, p853-863, 11p
Publication Year :
2023

Abstract

The proposed research presents a blockchain-based healthcare system that seeks to address the limitations of current data-sharing methods by providing secure and efficient data transfer, enhancing data privacy and security, enabling effective data sharing interoperability, and promoting data-driven healthcare decision-making. A blockchain platform, IPFS, and rule-based access control are among the technologies suggested for use in the proposed system. Implementing this system could result in more personalized and effective medication for patients, as well as lower healthcare costs and improved care quality. The suggested approach, known as the Homomorphic Zero-Knowledge Blockchain Algorithm (HZBA), employs a block chain technique linked with Proxy Re Encryption with Homomorphic with Zero proof knowledge. Finally, the Covid19-dataset has collected from Kaggle repository and HCDNN method has used to complete the classification. The proposed blockchain-based healthcare system has the potential to revolutionize healthcare by resolving data privacy and security concerns, increasing data accuracy, fostering more interoperability in data sharing, and enhancing data-driven healthcare decision-making. The proposed blockchain-based healthcare system provides potential answers to data sharing difficulties in the healthcare business. One potential disadvantage is the system's complexity and cost of installation. The experimental results and classification performance parameters have been thoroughly demonstrated [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
18770509
Volume :
230
Database :
Supplemental Index
Journal :
Procedia Computer Science
Publication Type :
Academic Journal
Accession number :
174641275
Full Text :
https://doi.org/10.1016/j.procs.2023.12.047