A Design of Disease Diagnosis based Smart Healthcare Model using Deep Learning Technique

A Smart Healthcare System (SHS) is developed from traditional healthcare by integrating the Internet of Things (IoT) with Artificial Intelligence (AI). The data are captured by millions of devices and sensors, where it is exchanged continuously with medical staff to monitor the health of patients. An important message can then be analyzed using various machine learning (ML) / deep learning (DL) algorithms to predict the severity of diseases and then shared through wireless connectivity with medical professionals who can make appropriate recommendations. The main aim of the research work is to develop a disease detection model based on SHS for diabetic disease using DL classifiers. The method considered both collected and public datasets stored in the cloud for building SHS to allow accurate time monitoring of patient health conditions. IoT devices as sensors enable smooth data gathering, while AI algorithms use the data to diagnose diseases. For disease diagnosis, Restricted Boltzmann Machine based generative adversarial network (RBM -GAN) model has only three stages for the full prediction process. The experiments are carried out in two datasets, where the performance of the proposed RBM-GAN model is compared with existing DL classifiers. The simulation results show that the proposed model increased the accuracy by 5% on both two datasets than current DL classifiers. The proposed RBM-GAN model is used as a suitable illness analysis tool for SHS from these results.