AUTHOR=Ragab Mahmoud , Alshehri Samah , Azim Gamil Abdel , Aldawsari Hibah M. , Noor Adeeb , Alyami Jaber , Abdel-khalek S. 

TITLE=COVID-19 Identification System Using Transfer Learning Technique With Mobile-NetV2 and Chest X-Ray Images

JOURNAL=Frontiers in Public Health

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/public-health/articles/10.3389/fpubh.2022.819156

DOI=10.3389/fpubh.2022.819156

ISSN=2296-2565

ABSTRACT=: Diagnosis is a crucial precautionary step in research study right into the coronavirus, which shows similar indications with various other pneumonia types. The COVID-19 pandemic is causing a significant outbreak in more than 150 nations worldwide. It was having a powerful influence on the wellness and the lives of many individuals worldwide. Among the important actions in fighting COVID-19 is discovering the contaminated patients early and positioning them under unique treatment. Finding this problem from radiography and radiology images is perhaps among the fastest techniques to recognize individuals. Artificial intelligence strategies have the potential to overcome this difficulty. Transfer learning MobileNetV2 is a convolutional Neural network architecture that seeks to execute well on mobile devices. In this paper, we use MobileNetV2 with Transfer learning techniques as a classifier to recognize coronaviruses. Two data sets are used; the first consists of 309 Chest X-ray images (102 with Covid-19 and 207 Normal), the second consists of 516 Chest X-ray images (102 with Covid-19 and 414 Normal). We assessed the model, the network based on the sensitivity rate, the specificity rate, confusion matrix and F1-measure. Also, we present the receiver operating characteristic (ROC) curve. The numerical simulation reveals that the model accuracy is 95,8% and 100%, where dropout is 0.3 and 0.4, respectively. The model is implemented using Keras and python programming.