Implementation of Linear Regression Analysis for the Optimal Controlling of COVID-19 Preventive Measures Variable for Environmental Sustainable Solution

This study discusses about integrating linear regression analysis (LRN) to regulate variables as effectively as possible in order to prevent COVID-19. The variables related to preventive measures are presented in terms of the frequency of maintaining social distance, the frequency of using masks and sanitizers, and the frequency of vaccinations. The new aspect of this approach is the use of LRN to train the variables for preventive measures and deliver a sustainable environment solution. A nation such as India had a steady rise in COVID-19 cases during the epidemic and a subsequent decline following the implementation of certain preventive measures. The covid-19 curve can be flattened and reduces when preventive actions are taken, however the main drawback of the previous approaches was that it showed poor mean square error, poor convergence rate, and increased sensitivity. Data collecting for COVID-19 cases in India during the first wave is where it starts. After that, a nonlinear multi-objective function trained by linear regression analysis is created using the variables related to preventive actions. Furthermore, if periodic preventive actions are implemented, it is anticipated that the COVID-19 curve will flatten and decrease, ensuring sustainability. Then, when compared to other current methods, the covid-19 curve exhibits a faster convergence rate, improved mean square error, and sensitivity when LNA is used instead.