An optimized deep learning architecture for the diagnosis of COVID-19 disease based on gravitational search optimization

In this paper, a novel approach called GSA-DenseNet121-COVID-19 based on hybrid convolutional neural network (CNN) architecture is proposed using an optimization algorithm. The CNN that was used DenseNet121 and the algorithm gravitational search (GSA). GSA adapted to determine best values for hyperparameters of architecture, achieve high level accuracy in diagnosing COVID-19 disease through chest x-ray image analysis. obtained results showed able correctly classify 98% test set. To efficacy setting optimum DenseNet121, it compared another social ski driver (SSD). comparison demonstrated its ability better diagnose than SSD-DenseNet121 as second only 94% As well as, Inception-v3 manual method determining hyperparameters. GSA-DenseNet121 beat other approach, 95% set samples.