Detection and classification of COVID-19 disease using SWHO-based deep neural network classifier

Corona is an unanticipated disease that invaded the lives of millions of people and caused a global pandemic. Along with that, the disease affected the normal lifestyle and initiated a massive economic crisis. In this research, COVID-19 disease detection and severity identification are performed using the proposed SWHO-based deep Neural Network (SWHO-based deep NN) classifier. In this optimised deep NN classifier, the network parameters of the deep NN classifier are optimised using the Spadger Wolf Hawk Optimization (SWHO), which tunes the weight and bias of the classifier. The importance of the SWHO algorithm relies on faster convergence and less time is taken for the computation. Moreover, the severity of corona is classified based on mild, moderate, and severe classes using the SWHO-based deep NN, which helps medical professionals to equip the patients based on their necessity. The severity analysis is performed in this research, and the proficiency of the research is analysed based on the performance measures, accuracy, sensitivity, and specificity. The proposed method acquired the accuracy, sensitivity, and specificity of 92.809%, 95.082%, and 96.296% in terms of k-fold and 95.870%, 96.875%, and 98.800% in terms of training percentage, respectively. The proposed method effectively analysed, predicted, and classified the disease efficiently.