Covid-19 X-Ray Image Detection using ResNet50 and VGG16 in Convolution Neural Network
2022 IEEE Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation, IATMSI 2022
; 2022.
Artículo
en Inglés
| Scopus | ID: covidwho-20242756
ABSTRACT
COVID-19 is an outbreak of disease which is created by China. COVID-19 is originated by coronavirus (CoV), generally created mutation pattern with 'SARS-CoV2' or '2019 novel coronavirus'. It is declared by the World Health Organization of 2019 in December. COVID-19 is a contagious virus and contiguous disease that will create the morality of life. Even though it is detected in an early stage it can be incurable if the severity is more. The throat and nose samples are collected to identify COVID-19 disease. We collected the X-Ray images to identify the virus. We propose a system to diagnose the images using Convolutional Neural Network (CNN) models. Dataset used consists of both Covid and Normal X-ray images. Among Convolutional Neural Network (CNN) models, the proposed models are ResNet50 and VGG16. RESNET50 consists of 48 convolutional, 1 MaxPool, and Average Pool layers, and VGG16 is another convolutional neural network that consists of 16 deep layers. By using these two models, the detection of COVID-19 is done. This research is designed to help physicians for successful detection of COVID-19 disease at an early stage in the medical field. © 2022 IEEE.
CNN (Convolutional Neural Network); Covid-19; ResNet50 (Residual Network); VGG16 (Visual Geometry Group); Convolution; Convolutional neural networks; Multilayer neural networks; Viruses; Convolution neural network; Convolutional neural network; Coronaviruses; Image detection; Neural network model; X-ray image
Texto completo:
Disponible
Colección:
Bases de datos de organismos internacionales
Base de datos:
Scopus
Tipo de estudio:
Estudio pronóstico
Idioma:
Inglés
Revista:
2022 IEEE Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation, IATMSI 2022
Año:
2022
Tipo del documento:
Artículo
Similares
MEDLINE
...
LILACS
LIS