Cyber-Physical System Converged Digital Twin for Secure Patient Monitoring and Attack Detection

A live or non-living object's digital twin is its mirror image. Businesses, particularly in the healthcare sector, are entering a new era thanks to digital twins and cyber-physical systems (CPS), which collect patient health data to offer users quick, efficient, and on-demand services. Under the proposed system, a range of patient health metrics are gathered via various medical devices and wearables that send data to the main database. This data is then analysed to improve diagnosis and train automated systems. A physical item serves as the primary database, and to investigate, summarise, and mine data for diagnosis while keeping an eye on the patient in real time, a virtual object or digital twin of the same is maintained in parallel. The e-health cloud data must be secured against unwanted access using an iris biometric feature for biometric authentication. The proposed article developed a two-phase Enhanced Efficient Net Convolution Neural Network-based architecture to distinguish between the real and fake user samples. To distinguish between faked and real iris biometric samples, the suggested system is trained on several datasets using an Enhanced Efficient Net Convolution Neural Network to make modifications.