Advanced LWAVF Framework Based on Neural Network Security in IoMT for Managing Patient Data Authentication and Integrity Validation with Consensus Mapping

Abstract

The Internet of Medical Things (IoMT) plays an essential role in health care systems to provide ubiquitous patient monitoring, health record management, and disease diagnosis support. The sensitive data requires robust security measures to protect sensitive health information. As IoMT data sharing is pursued through the decentralized cloud, authentication is vital to prevent anonymous access/ modification of data. However, the existing systems face difficulties such as integrity, authentication, and privacy issues while managing sensitive data. The research difficulties are overcome by applying the Light-weight Authentication and Validation Framework (LWAVF), which uses the encryption to ensure data security. This framework performs patient-monitored data authentication and integrity validation at the sender and receiver ends.  A sender-receiver utilizes the AES-256 bit authentication to format the patient data to meet the sharing security requirements. The data authentication signature uses the sender and receiver conjugation time and agreement to verify the integrity at the receiver end. During this process, a consensus mechanism is deployed to monitor the mapping of time, agreement status, sender’s data count, and receiver’s data count that supports integrity. Therefore, the validation is performed by disjoining the agreement after matching with the consensus data. The matching, verification, and agreement status validation are eased using one-track neural learning. The mapping parameter validation and their existence are verified by this learning model recurrent to the conjugation time in which the proposed system ensures 416.35ms time for data sharing time, 3.22ms  for authentication, 5.98ms for integrity verification, 455.55ms for latency and 20.14ms complexity.