Private blockchain-based encryption framework using computational intelligence approach

Electronic Health monitoring system has performed an essential role in managing healthcare monitoring. E-health can provide effective and valuable facilities for the patients to monitor. Though, there are protection disputes in the current E-Health system. The current e-health system, on the other h...

Full description

Saved in:
Bibliographic Details
Published inEgyptian informatics journal Vol. 23; no. 4; pp. 69 - 75
Main Authors Ghazal, Taher M., Hasan, Mohammad Kamrul, Abdullah, Siti Norul Huda Sheikh, Bakar, Khairul Azmi Abu, Al Hamadi, Hussam
Format Journal Article
LanguageEnglish
Published Elsevier B.V 01.12.2022
Elsevier
Subjects
Online AccessGet full text

Cover

Loading…
More Information
Summary:Electronic Health monitoring system has performed an essential role in managing healthcare monitoring. E-health can provide effective and valuable facilities for the patients to monitor. Though, there are protection disputes in the current E-Health system. The current e-health system, on the other hand, has security issues. Malevolent doctors may work together with cloud Storage Service Providers (CSPs) to interfere with patients' electronic health records (EHRs) or promptly leak EHR matter to other enemies for income. (EHRs). The malevolent doctors may conspire with the Patient Healthcare Monitoring Service Provider (PHMSP) to manipulate with the patients'. For profit, EHRs or directly divulge the EHR content of EHRs to other opponents. Block-chain has recently appeared as one of the most powerful methods in the protection and secrecy fields. It is assumed to be the promised security approach that will eventually replace the security challenges in existing e-health monitoring systems. Encryption in blockchain refers to technical methods that make accessing encrypted data difficult for unauthorized resources. This research proposed a blockchain-based encryption framework to provide security-based solutions using a computational intelligence methodology. The proposed approach provides better results in terms of 0.93 in the training phase and 0.91 in the validation accuracy.
ISSN:1110-8665
2090-4754
DOI:10.1016/j.eij.2022.06.007