Selecting a Better Classifier Using Machine Learning for COVID-19

Abstract

This paper will elaborate that how timely available data and Machine learning algorithms can help in determining premature exposure of coronavirus (COVID-19) and aided the world in formulating to reduce the loss. We will investigate which machine learning algorithms are best fit to predict COVID-19 data sets. In this study our focus will be on the spread of COVID-19 internationally in different countries. This study will serve as a resource for the future research and development on COVID-19 by producing better research in this field. To achieve the outcomes and future forecasting of COVID-19, we analyze the records and datasets of COVID-19 through Machine Learning algorithms. For this purpose, we used six algorithms to construct classifiers such as Support Vector Machine (SVM), Decision Tree, K-Nearest Neighbor (K-NN), Naïve Bayes, Logistic Regression and Random Forecast. These algorithms were applied on Python a machine learning software. The dataset is acquired by WHO data sets and data sets provided online at Github and compiled and organized by different communities to track the spread of the virus. The Performance of the best classifier will be measured using Accuracy. The model developed with Decision Tree is the most efficient with the highest percentage of accuracy of 99.85 %, followed by Random Forecast with 99.60 %, Naïve Bayes with 97.52 % accuracy, Logistic Regression with 97.49 % accuracy, Support Vector Machine with 98.85 % accuracy and K-NN with 98.06 % accuracy. In our research, we discussed two types of classification: Binary and Multinomial. Support Vector Machine and Decision Tree give us precise results. Other classifier models gave satisfactory outcomes. The outcomes may be helping to predict the future circumstances of COVID-19. From the past studies we have used Autoregressive integrated moving average (ARIMA) model for time series data. SIR models to check the spread of Nowcasting and forecasting the spread of 2019-nCoV in China and worldwide.