A Bayesian Deep Learning Network System Based on Edge Computing

Abstract

According to a study of health centers across the country, the physical health state is evaluated through a log-based, multi-access physical monitoring program and the accompanying challenges they face in their lifestyle. The deficiency of important nutrients is causing organ degradation, which in turn causes a wide range of health issues, especially for newborns, children, and adults. The physical activities of children and teenagers must be constantly monitored to eliminate issues in their lives through a smart environment. Physical monitoring systems with many access points, information needs, and accurate health-status diagnoses are becoming increasingly important in today’s fast-paced world. In eliminating problems from their lives, a smart environment must constantly monitor the physical activities of children and teenagers. There is a growing need for physical monitoring systems with multiple access points, information needs, and accurate health-status diagnoses in today’s human–robot interactive communication process rapidly changing world. Smart-log patches incorporating researchers have developed and tested sensors for the Internet of Things (IoT) in this study. The smart-log patch is a Bayesian deep learning network system that is based on edge computing (BDLN-EC) to infer and recognize various physical data gathered from people. Deep learning-driven wireless communication is described in signal analysis, encoding and decoding, security and privacy, channel estimation, and compression sensing. Deep learning-driven wireless connectivity intuitions and methodologies are the focus of our work. Wearable IoT systems with multimedia capabilities have been tested and evaluated for accuracy, efficacy, error, and energy usage.