Deep learning technique for patients healthcare monitoring using IoT body based body sensors and edge servers
D. Shekar Goud, B. B. Beenarani, C. Brijilal Ruban, Rani Fathima, M. L. Bharathi, A. Rajaram, Pravin R. Kshirsagar, Vineet Tirth
Abstract
Architectural, cognitive, and service layers are the three components that come together to form the system as a whole. The data that is acquired by the instruments at the application layer is processed by the system that is in charge of the network. The conceptual layer, which is where edge sensors are put, is responsible for managing radio resource management and intersensor connections in order to solve the issues raised by the physical layer about increasing power consumption and increased latency. In response to the processed data provided by the logical layer, the application layer will make judgements. The key objective is to lower prices so that they are more accessible to regular people. Patients will not only be able to maintain their financial stability, but they will also have easy access to private therapy. This research presents a solution based on the Internet of Things (IoT), which will simplify the usage of a generally complicated medical device while allowing you to do it at a reasonable cost and in the comfort of your own home. The Elephant Herding Optimizations using Convolutional Neural Networks (CNNs) method is discussed here in order to differentiate between healthy and unhealthy patterns of behavior. The scoring function, also known as fuzzy logic, is used in order to arrive at a conclusion on the severity of the irregularity. In the end, tests were carried out to see how well the recommended work fared in contrast to the existing approaches in terms of specificity, recall, f1-score, and ROC curve. These metrics were examined.