An evolutionary algorithm for the solution of multi-objective optimization problem

Abstract

Worldwide, COVID-19 widespread has a significant impact on a great number of people. The hospital admittance issue for patients with COVID-19 has been optimized by previous research. Identifying the symptoms that can be used to determine a patient's health status, whether they are dead or alive is a difficult task for medical professionals. To solve this issue, the multi-objective group counseling optimization (MOGCO) algorithm was used to control this problem. First, the zitzler-deb-thiele (ZDT)-2 benchmark function is used to evaluate the MOGCO, multi-objective particle swarm optimization (MOPSO), and non-dominated sorting genetic algorithm (NSGA) II. In comparison to MOPSO and NSGA-II, MOGCO is closest to the Pareto front line according to graphic statistics on different fitness evolution values such as 4000, 6000, 8000, and 10000. As a result, MOGCO is used for COVID-19 data optimization. Moreover, six symptoms (heart rate, oxygen saturation, fever, body pain, flue, and breath) were optimized to see if the COVID-19 patients were still alive. The information was gathered from GitHub. Based on the minimum and maximum values of these symptoms obtained by the suggested method, the optimum study shows that COVID-19 patients can remain alive.