Paper Title
Detection of Sar-Cov2 and Pneumonia using CNN H5 Model on Chest X-Ray Images

Abstract
To avoid adverse clinical outcomes and an unsustainable load on the health-care system, early diagnosis and treatment of Covid-19 patients at increased risk of developing critical disease are crucial. Decision trees, deep network, VGG-16, VGG-19, ResNet50, Mobile Net and MobileNetV2, Bayesian Networks have been used in the existing approaches. This paper aims to detect the presence and severity of the corona virus in a body and to successfully differentiate between Pneumonia and the Covid-19 using the H5 model on the X-Ray images. X-Rays of patients with Pneumonia, Covid and completely normal patients will be used in the process. H5 model is being used for its high classification accuracy. The advantage of this approach is its shorter training period, faster test results and no human intervention. The result works on classifying X-Ray images to Covid positive and Covid negative and further classifies the Covid positive tested images to Pneumonia positive or negative. Future work may include to find percentage of the infection in lungs for post vaccination X-Ray images and to decrease the validation loss for better accuracy. Keywords - H5 Convolutional Neural Network Model, COVID-19, Severe Acute Respiratory Syndrome Corona Virus 2 (SARS cov-2), Tensor Flow.