Welcome to
Beaconhouse National University

SB | Dr. Usman Sattar Publishes Research | Selecting a Better Classifier using Machine Learning for COVID-19

Dr. Usman Sattar, Assistant Professor has published a research article Selecting a Better Classifier using Machine Learning for COVID-19 in the International Journal of Computing and Digital Systems - an HEC recognized journal.

Please find Abstract of the article below. The paper can be viewed at the following link: https://journal.uob.edu.bh/handle/123456789/4312.


"This paper will elaborate that how timely available data and Machine learning algorithms can help in determining premature exposure to coronavirus (COVID-19) and aided the world in formulating to reduce the loss. We will investigate which machine learning algorithms are the 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 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 on 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."

The Beaconhouse Group
Arrow-Top Created with Sketch.