ABSTRACT

Coronavirus disease 2019 also known as COVID-19 has become a pandemic. The
disease is caused by a beta coronavirus called Severe Acute Respiratory Syndrome
Coronavirus 2 (SARS-CoV-2). The severity of the disease can be understood bythe
massive number of deaths and affected patients globally. If the diagnosis is fast-
paced, the disease can be controlled in a better manner. Laboratory tests are
available for diagnosis, but they are bounded by available testing kits and time. The
use of radiological examinations that comprise Computed Tomography (CT) can be
used for the diagnosis of the disease. Specifically, chest X-Ray images can be
analysed to identify the presence of COVID-19 in a patient. In this paper, an
automated method for the diagnosis of COVID-19 from the chest X-Ray images is
proposed. The method presents an improved depth wise convolution neural
network for analysing the chest X-Ray images. Wavelet decomposition is applied
to integrate multiresolution analysis in the network. The frequency sub-bands
obtained from the input images are fed in the network for identifying the disease.
The network is designed to predict the class of the input image as normal, viral
pneumonia, and COVID-19. A comparative study with the existing methods is also
performed. The metrics like accuracy, sensitivity, and F1-measure are calculated
for performance evaluation. The performance of the proposed method is better than
the existing methodologies and thus can be used for the effective diagnosis of the
disease.

v
 TABLE

CHAPTER NO TITLE PAGE

NO

1. INTRODUCTION 1

1.1 BACKGROUND AND BASICS 1

1.2 EXISTING SYSTEM 1

1.3 PROPOSED SYSTEM 2

1.4 ADVANTAGES OF PROPOSED SYSTEM 2

2. LITERATURE SURVEY 3

3. METHODOLOGY 5

3.1 SYSTEM REQUIRMENT SPECIFICATION 5

3.1.1 HARDWARE REQUIREMENTS 5

3.1.2 SOFTWARE REQUIREMENTS 5

3.2 SOFTWARE ENVIRONMENT 5

3.3 ARCHITECTURE 15

3.4 MODULES 16

3.5 DATAFLOW DIAGRAM 17

3.6 UML DIAGRAM 20

3.7 FEASIBILITY STUDY 23

3.8 SYSTEM DESIGN AND TESTING PLAN 24

4. RESULT AND DISCUSSION 29

5. CONCLUSION 30

VI
 LIST OF FIGURES
FIGURE NO TITLE PAGE NO

3.3.1 ARCHITETURE 15

3.5.1 DATAFLOW DIAGRAM 1 18

3.5.2 DATAFLOW DIAGRAM 2 18

3.5.3 DATAFLOW DIAGRAM 3 19

3.5.4 DATAFLOW DIAGRAM 4 19

3.6.1 USECASE DIAGRAM 21

3.6.2 SEQUENCE DIAGRAM 22

3.6.3 ACTIVITY DIAGRAM 23

VII
 CHAPTER 1
INTRODUCTION
1.1 BACKGROUND AND BASICS
A pandemic is an outbreak of a disease globally affecting many populations. The
world has witnessed many pandemics in the 20th century. The latest coronavirus
disease known as COVID-19 has appeared and spread extremely fast. COVID-19
infection are observed to have serious pneumonia with abnormal observations on
chest Computed Tomography (CT) examination. The unavailability of medicine
for this disease requires efficient diagnosis methods for controlling the disease. A
deep learning-based model is applied on CT images for detection of COVID-19.
Some researchers have also developed public datasets comprising of chest X-
Ray images of COVID-19 patients. A method named COVID-Net is developed and
applied on these public datasets for diagnosis of COVID-19. The use of deep
learning for diagnosis from the chest X-Ray images provides good results. Deep
learning models are being widely used for medical image processing. The
detection of pneumonia is done using convolution neural networks. In this paper,
an automated method for the diagnosis of COVID-19 from a deep network is
proposed. The proposed network utilizes the feature generated by multiresolution
analysis. The combination of wavelet transforms along with the deep network
brings multiple advantages. The wavelet decomposition is fed into the network.
The network used is not the traditional Convolutional Neural Network (CNN). A
depthwise separable network is utilized in this work.

1.2 EXISTING SYSTEM

The person administering the test will twirl a long stick with a soft brush on the
end, similar to a pipe cleaner, up your nose for a few seconds. There will be a
collection of secretions collected by the soft bristles for study. To get a good
specimen, the swab must go back a long way, so cells and fluids must be
extracted from the whole passageway that links the base of the nose to the back
of the neck. However, since the body isn't used to having an object in that place, it
produces a slew of strange sensations. For one thing, it activates the lachrymal
reflex, which means it will bring tears to your eyes if it’s done correctly. I wouldn't
go so far as to say it hurt, but it is uncomfortable. Since the swab will also touch
the back of thethroat, it may also trigger a gag reflex.

1
1.3 PROPOSED SYSTEM

We have proposed an automatic prediction of covid-19 using a deep convolutional neural

networks and Chest X-ray images. The proposed models will have end-to- end structure
without manual feature extraction and selection methods. Chest Xray is the best tool for
the detection of covid-19. The method presents an improved depth wise convolution
neural network for analysing the chest X-Ray images. Wavelet decomposition is applied to
integrate multiresolution analysis in the network. The frequency sub-bands obtained from
the input images are fed in the network for identifying the disease. The network is
designed to predict the class of the input image as normal, viral pneumonia, and COVID-
19. A comparative study with the existing methods is also performed. The metrics like
accuracy, sensitivity, and F1-measure are calculated for performance evaluation. The
performance of the proposed method is better than the existing methodologies and thus
can be used forthe effective diagnosis of the disease.

1.4 ADVANTAGES OF PROPOSED SYSTEM

1. Pneumonia Deetection

2. Lung Disease Detection

2
 CHAPTER 2
LITERATURE SURVEY

 Narinder Singh Punn et al.[2]The flare-up of intense respiratory condition, known as

COVID-2019 (SARS-CoV-2), has compromised the whole world. The world is giving a

valiant effort to battle the spread of this dangerous infection in framework, finance, news

markets, insurance, medical care and numerous different apparatuses. Craftsmanship

scientists have zeroed in on their insight into numerical advancement to break down the

condition of the scourge, utilizing information from the nation over.

 Palash Ghosh et al.[3]The sickness has spread to 212 nations and areas and has tainted

(affirmed) multiple million individuals. In India, the infection was first given an account of

January 30, 2020 to an understudy getting back from Wuhan in Kerala. Across India (as of

May 3, 2020), the quantity of individuals tainted is north of 37,000. Most investigations and

diaries center around the quantity of tainted individuals the nation over.

 Sina Ardabili et al[4].In the normal instances of foreseeing the worldwide COVID-19

plague, the epidemiological and measurable epidemiological model has been important to

the specialists and notable in the media. Because of the great degree of vulnerability and

absence of significant data, the standard models are not satisfactory over the long haul.

 Fotio Petropoulos, et al[5].Nonetheless, prediction requires adequate data.

Simultaneously, what's to come isn't so unsurprising as it used to be. What's more, the

speculation depends on the believability of the news media and the anticipated changes.

Mental factors additionally assume a significant part in how individuals see and react with

the impacts of the sickness and what it can mean for them.
3
 Arti. M. K, K. Bhatnagar et al[6].Nonetheless, prediction requires adequate data.

Simultaneously, it is obscure right now what he will do subsequent to leaving the post.

Moreover, the theory depends on the believability of the news media and the anticipated

changes. Mental factors likewise assume a significant part in how individuals see and

react to the danger of illness, and they dread that it could influence them.

 H.Shekhar et al[7] .The information from March 15, 2020 to April 30, 2020 is utilized to

approve the model, and t he interior speed is steady. In some Indian nations, for example,

Maharashtra, Gujarat and Delhi, individuals are tainted every day. The underlying disease

is supposed to be on the ascent and is relied upon to keep on developing. Unexpected

blasts are characterized by contrasts in the way of life of these three nations.

 Yan, L., Zhang et al [8].The abrupt ascent in COVID-19 is putting a strain on worldwide

wellbeing administrations. At this stage, it is critical to analyze the illness rapidly, precisely

and early. To help independent direction and arranging in wellbeing programs, the review

utilized blood tests from 485 tainted patients in Wuhan, China, to identify indications of

death from the sickness.

 L. Li, Z. Yang et al [9].As indicated by the authority data transmission framework, this

report inspects how the 2019 Coronavirus (COVID-19) is communicated. The mistake

between the model and the information bend is tiny. At that point, he anticipated the

plague and comprehended it prior to settling on a choice and dissecting the nations that

aided settle on the choice.

4
 CHAPTER 3
METHODOLOGY

3.1 System Requirement Specification

3.1.1 HARDWARE REQUIREMENTS:

System - Windows7/10
Speed - 2.4GHZ
Hard disk - 40GB
Monitor - 15VGA Color
Ram - 4GB

3.1.2 SOFTWARE REQUIREMENTS:

Operating system - Windows 7
Coding Language - PYTHON

3.2 SOFTWARE ENVIRONMENT

Python:

Python is a high-level, interpreted, interactive and object-oriented scripting

language. Python is designed to be highly readable. It uses English keywords
frequently where as other languages use punctuation, and it has fewer syntactical
constructions than other languages.

 Python is Interpreted − Python is processed at runtime by the interpreter.

You do not need to compile your program before executing it. This is similar
to PERL and PHP.

 Python is Interactive − You can actually sit at a Python prompt and interact
with the interpreter directly to write your programs.

 Python is Object-Oriented − Python supports Object-Oriented style or

technique of programming that encapsulates code within objects.

5
  Python is a Beginner's Language − Python is a great language for the
beginner-level programmers and supports the development of a wide range
of applications from simple text processing to WWW browsers to games.

History of Python

Python was developed by Guido van Rossum in the late eighties and early nineties
at the National Research Institute for Mathematics and Computer Science in the
Netherlands.

6
Python is derived from many other languages, including ABC, Modula-3, C,
C++,
Algol-68, SmallTalk, and Unix shell and other scripting languages.

Python is copyrighted. Like Perl, Python source code is now available under the
GNU General Public License (GPL).

Python is now maintained by a core development team at the institute, although

Guido van Rossum still holds a vital role in directing its progress.

Python Features

Python's features include −

 Easy-to-learn − Python has few keywords, simple structure, and a clearly

defined syntax. This allows the student to pick up the language quickly.

 Easy-to-read − Python code is more clearly defined and visible to the eyes.

 Easy-to-maintain − Python's source code is fairly easy-to-maintain.

 A broad standard library − Python's bulk of the library is very portable

and cross-platform compatible on UNIX, Windows, and Macintosh.

 Interactive Mode − Python has support for an interactive mode which

allows interactive testing and debugging of snippets of code.

 Portable − Python can run on a wide variety of hardware platforms and has
the same interface on all platforms.

 Extendable − You can add low-level modules to the Python interpreter.

These modules enable programmers to add to or customize their tools to be
more efficient.

 Databases − Python provides interfaces to all major commercial databases.

7
3.5 DATA FLOW DIAGRAM:

1. The DFD is also called as bubble chart. It is a simple graphical formalism

that can be used to represent a system in terms of input data to the system,
various processing carried out on this data, and the output data is generated
by this system.
2. The data flow diagram (DFD) is one of the most important modeling tools. It
is used to model the system components. These components are the system
process, the data used by the process, an external entity that interacts with
the system and the information flows in the system.
3. DFD shows how the information moves through the system and how it is
modified by a series of transformations. It is a graphical technique that
depicts information flow and the transformations that are applied as data
moves from input to output.
4. DFD is also known as bubble chart. A DFD may be used to represent a
system at any level of abstraction. DFD may be partitioned into levels that
represent increasing information flow and functional detail.

22