Estimation of Daily Cases, Deaths, Serious Patients and Recovering Pa-tients of Covid-19 in Turkey with Machine Learning Methods

Abstract

Covid-19 is the first pandemic of the current century, and it differs from previous pandemics due to its duration, loss of life, and psychological, sociological, and economic effects. In this process, the virus has produced and continues to produce many variants. Considering the frequency and the amount of mobility on Earth, this situation does not seem likely to change soon. Understanding the course of this pandemic will be helpful in being prepared for possible future pandemics. For this purpose, the daily data published by the Turkish Ministry of Health was examined, and machine learning methods were used to understand the features and make predictions for the future on different data groups. The data groups used are in a time series structure with a very complex course, and the number of daily cases, the number of severe patients, the number of patients who died per day and the number of patients who recovered per day were selected. The results of polynomial regression, least squares polynomial fit, and cubic spline fit are shown in this article. The results of the study are presented both visually through graphics, and numerically, in the form of tables containing the values of mean, median, standard deviation and sum of the Canberra distance, which is an accepted performance criterion in time series estimation. It is seen that the best results for the four time-series mentioned above are obtained by the cubic spline method. Simulation studies were carried out using the Python programming language.