Design and Implementation of Remote Health Monitoring System and Application for Priority Recognition Using Machine Learning

This work demonstrates a remote health monitoring system that provides a holistic perspective of cases and their health conditions. Remote Patient Monitoring (RPM) systems will play a conspicuous role in the millennium of medical management. In this paper, to monitor covid patients during their quarantine days to keep track of chronic circumstances. For that, the model of a non-reactive preference grading independently in a single device to collect the essential parameters like blood Oxygen level, temperature and pulse rate. To predict and conduct the priority division using supervised machine learning algorithm for the received medical packets and relay them according to their priorities. This hitch results in transmitting advanced significance data packets of high importance in an advanced average waiting time. In this design, to acknowledge a vital criterion distinguishing the priority of health-info carried by a file and other low-ranking digital data parcels of different cases. The stored data then given for the supervised machine learning classification algorithms. In that the better accuracy of priority classification of 93.5% obtained from support vector machine (SVM) algorithm outperforms than the other machine learning classifiers and are 91%, 88%, 89% with respect to Multilayer Perception(MLP), Baysian Network (BN) and Logisitic Regression(LR).