A Robust and Secure Electronic Internet of Things-Cloud Healthcare Framework for Disease Classification Using Deep Learning

Abstract

In the modern era, the Internet of Things (IoT) based nano-electronic devices are essential to provide practical patient information through monitoring performance in the healthcare system. Moreover, remote health monitoring is becoming necessary for lowering healthcare expenses and enhancing patient care due to the aging population and the rise in chronic illnesses. Recently, there has been a lot of interest in the IoT based nanoelectronics devices as a potential solution for remote health monitoring. An extensive range of physiological data, including heart rates, blood oxygen levels, body temperatures, ECG signals, etc., can be collected and analyzed by IoT-based sensors devices, giving medical practitioners real-time feedback so they can respond appropriately. Therefore, in this paper, a novel Functional neural network-based Aquila optimization (FNN-AO) algorithm is developed to classify the various types of diseases. Furthermore, an Identity-based Encryption (IbE) algorithm is adapted to secure the healthcare data. Initially, IoT based electronic sensors collect and store healthcare data in the cloud storage system. This process was done with the help of the MATLAB platform, and parameters were analyzed and compared with existing techniques in terms of performance metrics. From the comparison, the proposed framework has a 2.34% improvement over the other models.