A review on classification of SARS-CoV-2 using machine learning approaches
Rajkumar Pandiarajan, Vanniappan Balamurugan
Abstract
Almost all nations have been combating the COVID-19 pandemic, which is caused by Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2). Diagnosis of COVID-19 and its variants is still a challenging task since the efficiency of the existing classifiers is not optimum. Previously, machine learning classifiers such as Support Vector Machine, K-Nearest Neighbour, Decision Tree, etc., and deep learning classifiers viz. Gated Recurrent Unit, Convolutional Neural Network, Long Short Term Memory Network, etc. have been used for classifying the COVID-19. Such methods need lot of computational efforts and rely only on annotations of viral genes. This paper reviews the machine learning and deep learning techniques that have been applied in the classification of SARS-CoV-2 and analyses their performances critically. The comparative analysis reveals that deep learning classifiers outperform the machine learning classifiers in terms of classification accuracy, and deep learning classifiers require pre-processing. Further, this paper identifies the research gaps and provides possible future directions.