Securing the patient healthcare data using Deep Inception-ResNet based CPABPP model in Internet of Things

Abstract

The IoT is transforming healthcare by enabling extensive connectivity between medical professionals, equipment, staff, and patients, facilitating real-time monitoring. While the network's scale and diversity offer advantages for data exchange, they also pose challenges for privacy and security, particularly with sensitive medical information. To address this, deep learning-based cryptographic and biometric systems are utilized for authentication and anomaly detection in medical systems. However, power constraints on network sensors necessitate efficient security schemes. Thus, the authors propose a novel framework, the deep Inception-ResNetV2 with privacy preservation, to secure data transmission while minimizing encryption and decryption time. Implementing this method reduces the network's burden, saving time and costs in communication. Compared to alternatives like private biometric-based authentication, this model demonstrates superior performance.

URN:NBN:sciencein.jist.2024.v12.805