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) is vital for modern health care, enabling continuous patient monitoring, health record management, and disease diagnosis.However, the sensitive nature of health data requires robust security measures, particularly when decentralized cloud-based data sharing is employed.Current systems often struggle to maintain data integrity, authentication, and protect privacy.Hence, the research proposes the Lightweight Authentication and Validation Framework (LWAVF), which is designed to securely authenticate and validate patient data at both the sender and receiver ends.The framework uses AES-256 encryption to format and protect data during transfer.It incorporates a consensus mechanism to track key parameters from both parties, such as time, agreement status, and data counts, ensuring accurate validation.A unique one-track neural learning model simplifies its verification process by analyzing mapping parameters over time.The research results demonstrate the framework's efficiency, achieving 416.35 ms for data sharing, 3.22 ms for authentication, 5.98 ms for integrity verification, a latency of 455.55 ms, and a complexity of 20.14 ms, highlighting its suitability for secure, real-time IoMT applications.This research contributes to the development of enhanced, secure, and low-latency data authentication and validation for real-time healthcare applications within the IoMT ecosystem.

Ähnliche Arbeiten