Research Article
Ftl-CoV19: A Transfer Learning Approach to Detect COVID-19
Tarishi Singh ,
1
Praneet Saurabh ,
1
Dhananjay Bisen ,
2
Lalit Kane ,
3
Mayank Pathak ,
4
and G. R. Sinha
5
1
Mody University of Science and Technology, Lachhmangarh, Rajasthan, India
2
Madhav Institute of Technology and Sciences, Gwalior, Madhya Pradesh, India
3
University of Petroleum and Energy Studies, Dehradun, Uttarakhand, India
4
Technocrats Institute of Technology, Bhopal, Madhya Pradesh, India
5
Myanmar Institute of Information Technology, Mandalay, Myanmar
Correspondence should be addressed to G. R. Sinha; drgrsinha@ieee.org
Received 29 March 2022; Accepted 1 June 2022; Published 6 July 2022
Academic Editor: Kapil Sharma
Copyright © 2022 Tarishi Singh et al. is is an open access article distributed under the Creative Commons Attribution License,
which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
COVID-19 is an infectious and contagious disease caused by the new coronavirus. e total number of cases is over 19 million and
continues to grow. A common symptom noticed among COVID-19 patients is lung infection that results in breathlessness, and
the lack of essential resources such as testing, oxygen, and ventilators enhances its severity. Chest X-ray can be used to design and
develop a COVID-19 detection mechanism for a quicker diagnosis using AI and machine learning techniques. Due to this silver
lining, various new COVID-19 detection techniques and prediction models have been introduced in recent times based on chest
radiography images. However, due to a high level of unpredictability and the absence of essential data, standard models have
showcased low efficiency and also suffer from overheads and complexities. is paper proposes a model fine tuning transfer
learning-coronavirus 19 (Ftl-CoV19) for COVID-19 detection through chest X-rays, which embraces the ideas of transfer learning
in pretrained VGG16 model with including combination of convolution, max pooling, and dense layer at different stages of model.
Ftl-CoV19 reported promising experimental results; it observed training and validation accuracy of 98.82% and 99.27% with
precision of 100%, recall of 98%, and F1 score of 99%. ese results outperformed other conventional state of arts such as CNN,
ResNet50, InceptionV3, and Xception.
1. Introduction
e first human trace of COVID-19 was reported in De-
cember 2019, caused through novel coronavirus. Steadily, it
spreads throughout the world through various means of
communication. e first human cases of COVID-19 were
first reported in Wuhan City, China, in the month of De-
cember 2019. Gradually, it spreads and was declared as a
pandemic by the WHO (World Health Organization) en-
vironment presented in Figure 1 [1]. Novel coronavirus
disease is one such disease that infected tens of millions and
affected billions of people’s lives. e symptoms usually
comprise of moderate fever, cough, fatigue, respiratory
problems, and joint pain. Coronavirus is contagious and
spreads through droplets in open environment if an infected
person comes in proximity with another healthy person [2].
e coronaviruses “CoV” are a vast category of viruses
that includes a series of symptoms such as the common flu to
fatal respiratory illnesses. e infection ranges from
symptoms such as seasonal cold, fever, cough, loss of smell,
shortness in breathing, and difficulty in breathing. is risk
factor of this virus increases if the patient is already subjected
to serious conditions such as cancer, diabetes, obesity, and
even smoking. COVID-19 not only targets the body’s im-
mune system but also the respiratory system causing acute
conditions such as pneumonia, renal failure, and much
more. More than million people have lost their life from the
outbreak of COVID-19.
e virus has a pattern of hitting different parts of world
in waves; for instance, the first wave of COVID-19 in India
was recorded in September 2020, while second wave started
from March 2021. Different studies pointed the various risk
Hindawi
Computational Intelligence and Neuroscience
Volume 2022, Article ID 1953992, 16 pages
https://doi.org/10.1155/2022/1953992