TRANSFER LEARNING BASED CNN FOR COVID 19

Abstract

Covid-19 has significantly impacted individuals and health care systems on a global scale. Finding COVID-19 is difficult because there aren't manytesting kits available. A deep transfer learning-based CNN technique is used to recognize Covid 19 in chest CTimages. Chest CT scans from both Covid and non-Covid sources are included in the dataset used to train themodel. Computed tomography (CT) is a faster and more precise means of infection diagnosis when compared to x-ray imaging. This is because CT scan pictures show more potential infection indicators than x-rays, which explains why. X-rays do, however, release less ionizing energy than a CT scan. Deep transfer learning approaches can both train and fine- tune the weights of networks that have previously been trained using datasets, which is why they are effective for this. Inorder to evaluate pictures, deep learning in computer vision especially uses convolutional neural networks (CNNs). For the classification of CT scan pictures to manage the complex structure, deep architecture is needed. We hypothesize that using radiographical fluctuations of covid-19 in CT images, pre-trained deep transfer learning-based CNN models may be able to extract certain graphical properties of covid-19 and provide a clinical diagnosis. The main advantages oftransfer learning include reduced training time, improved neural network performance, and the absence of a large amount of data. Key Words: Covid 19, CNN, ResNet101, Transfer Learning