Published Paper Details:

Abstract- The Eruption of the Novel Corona virus or the COVID-19 in various parts of the world has been affected by the epidemic. The world as a whole and caused millions of death number this remains an inauspicious caveat to public health and will be stained as one of the greatest pandemics in world history. The proposed work utilizes a support vector regression model to predict the total number of the case found total deaths and recovered cases, the cumulative number of confirmed cases and several daily cases. The data is collected for the time period of 1st March to 30th April (61 Days). The total number of cases as of 30th April is found to be 35043 confirmed cases with 1147 total deaths and 8889 recovered patients. The model was developed in Python 3.6.3 to obtain the predicted values of the aforementioned cases until 30th June. The proposed methodology is based on a prediction of values using a support vector regression model with Radial Basis Function as the kernel and 10% confidence interval for the curve fitting. The data has been split into train and test set with test size 40% and training 60%. The model performance parameters are calculated as mean square error, root means square error, regression score, and percentage accuracy. The sample has above 97% accuracy in predicting deaths, recovered, the cumulative number of confirmed cases, and 87% accuracy in predicting daily new cases. The results suggest a Gaussian decrease in the number of cases and could take another 4 to 5 months to come down to the minimum level with no new cases being reported. The method is very efficient and has higher accuracy than linear or polynomial regression. In addition, this paper also analyses the current trends or patterns of Covid-19 in India. With the help of the Indian Ministry of Health and Family Welfare dataset, this study proposes different trends and patterns experienced in different parts of the world.