Data Augmentation using Auxiliary Classifier for Improved Detection of Covid 19 
Lakshmisetty Ruthvik Raj1, Bitra Harsha Vardhan2, Mullapudi Raghu Vamsi3, Keerthikeshwar Reddy Mamilla4, Poorna Chandra Vemula5
1Lakshmisetty Ruthvik Raj, Department of Computer Science, Vellore Institute of Technology, Vellore (Tamil Nadu), India.
2Bitra Harsha Vardhan, Department of Computer Science, Vellore Institute of Technology, Vellore (Tamil Nadu), India.
3Mullapudi Raghu Vamsi, Department of Computer Science, Vellore Institute of Technology, Vellore (Tamil Nadu), India.
4Keerthikeshwar Reddy Mamilla, Department of Computer Science, Vellore Institute of Technology, Vellore (Tamil Nadu), India.
5Poorna Chandra Vemula*, Department of Computer Science, Vellore Institute of Technology, Vellore (Tamil Nadu), India.
Manuscript received on August 17, 2021. | Revised Manuscript received on September 26, 2021. | Manuscript published on September 30, 2021. | PP: 209-214 | Volume-10 Issue-3, September 2021. | Retrieval Number: 100.1/ijrte.C63860910321 | DOI: 10.35940/ijrte.C6386.0910321
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: COVID-19 is a severe and potentially fatal respiratory infection called coronavirus 2 disease (SARS-Co-2). COVID-19 is easily detectable on an abnormal chest x-ray. Numerous extensive studies have been conducted due to the findings, demonstrating how precise the detection of coronas using X-rays within the chest is. To train a deep learning network, such as a convolutional neural network, a large amount of data is required. Due to the recent end of the pandemic, it is difficult to collect many Covid x-ray images in a short period. The purpose of this study is to demonstrate how X-ray imaging (CXR) is created using the Covid CNN model-based convolutional network. Additionally, we demonstrate that the performance of CNNs and various COVID-19 acquisition algorithms can be used to generate synthetic images from data extensions. Alone, with CNN distribution, an accuracy of 85 percent was achieved. The accuracy has been increased to 95% by adding artificial images generated from data. We anticipate that this approach will expedite the discovery of COVID-19 and result in radiological solid programs. We leverage transfer learning in this paper to reduce time complexity and achieve the highest accuracy.
Keywords: CXR, Convolutional Neural Networks, VGGNET, RESNET.