Smart Healthcare in IoT using Convolutional Based Cyber Physical System
S. Suganyadevi, S. Shanmuga Priya, R. Menaha, S. Sathiya, Pooja Jha, Sakena Benazer S
Abstract
The intelligent Internet of Things (IoT) through infinite networking possibilities for medical data investigation is elevating the interaction between technology and healthcare society. Recent years have seen fruitful transformations in deep networks and the widespread use of health wearables. IoT enabled by Deep Neural Networks brought about novel societal advances in medicine and brought new possibilities to the study of healthcare data. Despite the improvements, there are still certain problems that need to be addressed in terms of service quality. In this research, we present Grey Filter Bayesian Convolution Neural Network (GFB-CNN), a Deep Neural Network-driven IoT smart healthcare approach that makes use of real-time data. Here, we suggested a comprehensive AI-driven Internet of Things (IoT) eHealth architecture using a GFB-CNN to improve accuracy and efficiency across critical quality of service criteria. In order to evaluate the method’s viability, a large-scale Mobile HEALTH (MHEALTH) dataset is analysed. From design ideas to matching accuracy, overheads, and time related to state-of-the-art approaches, this instructive example examines and addresses all relevant elements of the suggested method. The GFB-CNN approach has assessed beside state-of-the-art methods in a multiplicity of simulated settings. We demonstrate that our approach successfully analyses health information investigation for heart signs by efficiently differentiating among good and sick heart signals with low time and cost required for sensing and data collecting.