aDepartment of Electronics and Communication Engineering, Vidya Academy of Science and Technology, Thalakottukara, Thrissur-680501, Kerala, India, rifa969619@gmail.com
bDepartment of Electronics and Communication Engineering, Vidya Academy of Science and Technology, Thalakottukara, Thrissur-680501, Kerala, India, rakesh.v.s@vidyaacademy.ac.in
cDepartment of Electronics and Communication Engineering, Vidya Academy of Science and Technology, Thalakottukara, Thrissur-680501, Kerala, India, swapnakumar.s@vidyaacademy.ac.in
Online Published on 12 July, 2022.
The COVID-19 (novel coronavirus 2019) pandemic condition is getting worse and severely affecting the health of human beings globally. An effective screening of infected patients is a critical step towards the fight against COVID-19. One of the key approaches to screening is the radiology examination using chest radiography. Studies have revealed that human and living beings present abnormalities in chest radiography images that are characteristics of those infected with COVID-19.This article discusses CONV-Net, a deep convolutional neural network design tailored for the detection of COVID-19 cases from human chest X-ray (CXR) images. The most widely used screening method is PCR testing. It is a highly sensitive and accurate method and requires more manpower, time, and money. An alternative noninvasive method discussed in this article is the detection of COVID-19 from chest radiography examinations. It is a computer-aided diagnostic process, but it offers better protection compared to PCR testing. The platform chosen for this project is Google colab and the library is TensorFlow with Keras.
Deep learning, Environment, Google colab, Radiography examination, TensorFlow with Keras
