Covid-19 is a rapidly spreading viral disease that infects not only humans, but animals are also infected because of this disease. The daily life of human beings,their health, and the economy of a country are affected due to this deadly viral disease. Covid-19is a common spreading disease, and till now, not a single country canprepare a vaccine for COVID-19. A clinical study of COVID-19 infected patients has shown that these typesof patients are mostly infected from a lung infection after coming inContact with this disease. In the year 2020,a novel corona virus has emerged as a very pandemic disease which affects the public health throughout the world. It has become necessary to screen large numberpeople to identify the infected ones and reduce thespread of disease. A real time PCR (polymerise chain reaction) is a standard tool for diagnosis for pathological testing. There are failure cases for this toolas it gives more false test results which make path to look for alternate tool. Chest x-rays is a better alternative for PCR for COVID-19 screening. But here accuracy of results matters a lot. Here a diagnosis recommender system for examining lung images is proposed which can assist the doctors and reduce the burden over them. Deep neural network technique CNN (convolutionneural network) is used for achieving best accuracy results. CNN (convolution neural network) which has emerged as an effective tool for analyzing big data – uses complex algorithms and artificial neural networks to train machines/computers so that they can learnfrom experience, classify and recognize data/images just like a human brain does. VGG19 is a variant of VGG model which in short consists of 19 layers (16 convolution layers, 3 Fully connected layer, 5 MaxPool layers and 1 SoftMax layer) VGG- 19 is a convolutionalneural network that is 19 layers deep. You can loada pretrained version of the network trained on more than a million images from the ImageNet database [1].The pretrained network can classify images into 1000 object categories, such as keyboard, mouse, pencil, andmany animals, chest-x-rays, the model is evaluated on the CIFAR-10 dataset and achieved 91.8% accuracy.



Software And Hardware