Mathematical modeling and AI based decision making for COVID-19 suspects backed by novel distance and similarity measures on plithogenic hypersoft sets

Abstract

It goes without saying that coronavirus (COVID-19) is an infectious disease and many countries are coping with its different variants. Owing to the limited medical facilities, vaccine and medical experts, need of the hour is to intelligently tackle its spread by making artificial intelligence (AI) based smart decisions for COVID-19 suspects who develop different symptoms and they are kept under observation and monitored to see the severity of the symptoms. The target of this study is to analyze COVID-19 suspects data and detect whether a suspect is a COVID-19 patient or not, and if yes, then to what extent, so that a suitable decision can be made. The decision can be categorized such that an infected person can be isolated or quarantined at home or at a facilitation center or the person can be sent to the hospital for the treatment. This target is achieved by designing a mathematical model of COVID-19 suspects in the form of a multi-criteria decision making (MCDM) model and a novel AI based technique is devised and implemented with the help of newly developed plithogenic distance and similarity measures in fuzzy environment. All findings are depicted graphically for a clear understanding and to provide an insight of the necessity and effectiveness of the proposed method. The concept and results of the proposed technique make it suitable for implementation in machine learning, deep learning, pattern recognition etc.