Competitive verse water wave optimisation enabled COVID-Net for COVID-19 detection from chest X-ray images

Abstract

ABSTRACT Coronavirus disease 2019 (COVID-19) pandemic has a rigorous impact on the healthiness of the world’s population. Therefore, in order to stop the spread of the disease, it is crucial to identify COVID-19 as soon as feasible. Therefore, a robust and effective competitive verse water wave optimisation-based COVID-Net (CVWWO-based COVID-Net) technique is developed in the detection of COVID-19. The CVWWO is designed by incorporating the competitive multi-verse optimizer (CMVO) and water wave optimization (WWO) algorithm. The region of interest (RoI) extraction approach is used in the removal of falsifications from the input chest X-ray (CXR) images. Thereafter, the segmentation of lung lobe is determined using kernel-based Bayesian fuzzy clustering (BFC). The features are useful in the detection of COVID-19. Here, the COVID-Net is accomplished, in which the training is performed using the CVWWO. The best results of the implemented approach are total positive rate (TPR) of 96%, total negative rate (TNR) of 93.72% and accuracy of 96%.