A Novel Feature Selection Algorithm Based on Aquila Optimizer for COVID-19 Classification

ABSTRACT

To this day, the prevention of coronavirus disease is still an arduous battle. Medical imaging technology has played an important role in the fight against the epidemic. This paper is to perform feature selection on the CT image feature sets used for COVID-19 detection to improve the speed and accuracy of detection. In this work, the population-based intelligent optimization algorithm Aquila optimizer is used for feature selection. This feature selection method uses an S-shaped transfer function to process continuous values and convert them into binary form. And when the performance of the updated solution is not good, a new mutation strategy is proposed to enhance the convergence effect of the solution. Through the verification of two CT image sets, the experimental results show that the use of the S-shaped transfer function and the proposed mutation strategy can effectively improve the effect of feature selection. The prediction accuracy of the features selected by this method on the two open datasets is 99.67% and 99.28%, respectively. © 2022, IFIP International Federation for Information Processing.