Chimp Optimization Algorithm based Recurrent Neural Network for Smart Health Care System in Edge computing based IoMT

The Internet of Medical Things (IoMT) and Artificial Intelligence (AI) have changed the traditional healthcare scheme to an intelligent system. The data are produced continuously by millions of devices and sensors, exchanging important messages through supporting network devices that monitor and control the smart-world infrastructures. While compared with cloud computing, the data storage or computation are migrated to the network (near end users) by edge computing. Therefore, edge computing is highly required to satisfy intelligent healthcare systems' requirements. However, the confluence of IoMT and AI opens up new potential in the healthcare sector. The main objective of this paper is to create a disease detection model for heart disease utilizing AI approaches. The given model includes many phases, including data gathering, preprocessing for detection of outliers, classification of disease, and weight parameter adjustment. Initially, the Correlation Based Feature Selector (CFS) approach is used in this study to exclude outliers. Then, the research work employs a Chimp Optimization Algorithm (ChOA)-based Recurrent Neural Network (RNN) model for illness diagnosis. ChOA is to fine-tune the 'weights' parameters of the RNN model to categorize medical data better. During the testing, the given ChOA -RNN model achieved extreme accuracies of 96.16 percent in identifying heart disease. As a result, the suggested model may be used as a suitable illness analysis tool for intelligent healthcare systems.