Blockchain Trust based Authentication Protocol with Malicious Data Analysis Using Deep Learning Architectures: Electronic Medical Record Application

New opportunities for effective patient data management have emerged as a result of introduction of electronic health records (EHRs). By utilizing ML to mine digital patient record datasets, for instance, preventative rather than reactive medical practice is feasible. EHR is vulnerable to both insider and external threats due to sensitive nature of data, but security applications typically face the network's outer perimeter. Using deep learning methods, this study aims to enhance cloud data storage and malicious data detection. Blockchain trust based authentication is used to improve security-based cloud data storage in this study. After that, fuzzy rule Bayesian discriminant analysis is used to find malicious data. Utilizing results of malware analysis as well as detection and ML methods to evaluate difference in correlation symmetry, it was demonstrated that it was possible to detect harmful traffic on computer systems, thereby increasing network security. Data transmission rate, random accuracy, computation cost, communication overhead, mean average precision, and specificity are all examined in the experimental analysis for various electronic medical record datasets.