An IoT-based Covid-19 Healthcare Monitoring and Prediction Using Deep Learning Methods

Abstract

The Internet of Things (IoT) is developing a more significant transformation in the healthcare industry by improving patient care with reduced cost of treatments. Main aim of this research is to monitor the Covid-19 patients and report the health issues immediately using IoT. Collected data is analyzed using deep learning model. The technological advancement of sensor and mobile technologies came up with IoT-based healthcare systems. These systems are more preventive than the traditional healthcare systems. This paper developed an efficient real-time IoT-based COVID-19 monitoring and prediction system using a deep learning model. By collecting symptomatic patient data and analyzing it, the COVID-19 suspects are predicted in the early stages in a better way. The effective parameters are selected using the Modified Chicken Swarm optimization (MCSO) approach by mining the health parameters gathered from the sensors. The COVID-19 presence is computed using the hybrid Deep learning model called Convolution and graph LSTM using the desired features. (ConvGLSTM). This process includes four stages such as data collection, data analysis (feature selection), diagnostic system (DL model), and the cloud system (Storage). The developed model is experimented with using the dataset from Srinagar based on parameters such as accuracy, precision, recall, F1 score, RMSE, and AUC. Based on the outcome, the proposed model is effective and superior to the traditional approaches to the early identification of COVID-19.