Raj Kumar Goel Institute of Technology Ghaziabad ISO

9001:2015 Certified
5th KM. STONE, DELHI-MEERUT ROAD, GHAZIABAD (U.P)-201003
Department of Computer Science & Engineering

Project Progress Report

1. Course : Bachelor of Technology

2. Semester : VIIIth
3. Branch : Computer Science & Engineering 4
4. Project Title : DL (Diagnostic Logistic)
5. Details of Students:
S. No. Roll No. Name Role as Signature
1 1900330100120 Khushi Tyagi Team Leader
2 1900330100127 Lavish Sadh Designer
3 1900330100129 Manan Singh Coder, Tester
4 1900330100039 Ankita Singh Report

6. SUPERVISOR:

(Ms. Vernika Singh)

Remarks from Project Supervisor:

…………………………………………………………………………………

…………………………………………………………………………………

…………………………………………………………………………………

…………………………………………………………………………………

i
 PROJECT SYNOPSIS

STATEMENT-:

Now-a-days, people face various diseases due to the environmental condition and their living
habits. So, the prediction of disease at earlier stage becomes important task. The correct
prediction of disease is the most challenging task. To overcome this problem data mining plays
an important role to predict the disease. With the help of disease data, data mining finds hidden
pattern information in the huge amount of medical data. We proposed general disease
prediction based on symptoms of the patient.

WHY TOPIC CHOSEN-:

As we all know now days due to COVID-19, people have the fear of diseases even at the
minimum symptoms. The basic idea behind making the project was to give people an interface
on which the rely and see the disease they are having and get the medicines acc. The just have
to enter the symptoms the are having and the system will analyse the symptoms and tell the
user the disease he/she may be suffering from.

OBJECTIVE-:

It is critical to comprehend the accurate diagnosis of patients by clinical examination and

evaluation. For compelling determination decision support systems that depend on computer
may assume an indispensable job. Health care field creates enormous information about
clinical evaluation, report in regards to patient, cure, subsequent meet-ups, medicine and so
forth. Today machine learning is present everywhere so that without knowing it, one can
possibly use it many times a day. Both the algorithms KNN and SVM provide accurate result.

METHODOLOGY-:

KNN (K-Nearest Neighbor): - KNN algorithm assumes the similarity between new case/data
and available case and put the new case into the category that is most similar to the available
categories. SVM (Support Vector Machine):- SVM creates the best line or decision boundary
that can segregate n-dimensional space into classes so that we can easily put the new data point
in the correct category in the future.

ii
HARWARE REQUIREMENT-:

A computer system with min 8gb of RAM, 50gb of Storage, a powerful graphic card to support
the virtual calculation and graphics.

SOFTWARE REQUIRMENT-:

Android Studio- To use the emulator for the application interface control, editing and
development.

Vs Code- Used to write python code for the development.

Sublime text- Used to write the code for the web application development.

Octave (GUI) - Used to run the ML algorithms and train the machine.

TESTING TECHNOLOGY-:

Automated Testing-: Automated testing is a process in which the tester uses special tools to
put the software through its paces and find any bugs that may exist. Automated testing is an
integral part of the development process. It can help in identifying bugs and defects early on in
the development lifecycle, which can save time and money on fixing them later on. Automated
tests are also known to be more reliable than manual tests because they are less prone to human
errors.

WHAT CONTRIBUTION DOES THE PROJECT MAKE-:

We got accurate general disease risk prediction as output, by giving the input as patients record
which help us to understand the level of disease risk prediction low time consumption and
minimal cost possible for disease prediction and risk prediction.

iii
 TABLE OF CONTENTS

CHAPTER NO. TITLE PAGE NO.

SYNOPSIS ii
LIST OF FIGURES vii
LIST OF TABLES ix

1. INTRODUCTION 1
1.1 Objective 1
1.2 Motivation 1
1.3 Problem Definition 2
1.4 Methodology 2
1.4.1 KNN Algorithm 2
1.4.2 Support vector machine 4
1.4.3 Random Forest Algorithm 5
1.5 Background and related work 6
1.5.1 Different Approaches 7
1.6 Related Work 9

2. HARDWARE & SOFTWARE REQUIREMENT 11

2.1 Software 11
2.1.1 Android Studio 11
2.1.2 VS code 11
2.1.3 Sublime Text 12
2.1.4 Octave (GUI) 13
2.2 Hardware 14

3. Software Development Life Cycle 15

3.1 SDLC MODEL 15
3.1.1 Waterfall model 15
3.1.2 RAD model 16
3.1.3 Spiral Model 17
3.1.4 V-Model 18

iv
 3.1.5 Increment model 19
3.1.6 Agile model 19
3.1.7 Iterative model 20
3.1.8 Big Bang model 21
3.1.9 Protype model 21
3.2 How it affects our model 22

4. SOFTWARE REQUIREMENT SPECIFICATION AND ANALYSIS 24

4.1 System Features 24
4.2 Requirement specification for healthcare maintenance system 24
4.2.1 Output 24
4.2.2 Steps 25
4.3 Other non-functional requirements 25
4.3.1 Performance requirements 25
4.3.2 Safety requirements 25
4.3.3 Security requirements 25
4.4 Software Analysis 26
4.4.1 Requirements 26
4.4.2 Performance requirements 26
4.4.2 Safety requirements 26
4.4.3 Security requirements 27

5. RISK ASSESSMENT 28
5.1 Evolution Matrices 29
5.1.1 Feature engineering 29
5.1.2 Pre-processing 29
5.1.3 Risk equation 30
5.2 Classification 30
5.3 Risk assessment service 31
5.3.1 Risk score 31
5.3.2 Risk factor 31

v
6. DFD AND APPLICATION ARCHITECTURE 32
6.1 Zero-layer DFD 32
6.2 First-layer DFD 33
6.3 Second-layer DFD 34

7. PROJECT MODULE DESIGN 35

7.1 Machine learning model 35
7.2 User interface 38

8. TESTING, TRAINING AND EVALUATION 39

8.1 Testing methodologies 39

8.2 Unit Testing 39
8.3 System testing 39
8.4 Quality Assurance 40
8.5 Functional test 40
8.6 Output of Machine Training & Testing 40

9. PROJECT SNAPSHOTS 45
9.1 Output screen of web application 45
9.2 Dataset 50

10. LIMITATIONS OF THE PROJECT 51

10.1 Limited data availability 51
10.2 Lack of Transparency 51
10.3 Overfitting 51
10.4 Lack of Interpretability 51
10.5 Data Privacy and Security 52
10.6 Ethical Considerations 52
10.7 Lack of expert input 52

11. FUTURE SCOPE OF THE PROJECT 53

CONCLUSION 55
REFERENCES 56

vi
 LIST OF FIGURES

CHAPTER NO. TITLE PAGE NO

1 Figure 1.1 KNN Classification 3

1 Figure 1.2 KNN graph representation 3
1 Figure 1.3 SVM graph representation 4
1 Figure 1.4 Random Forest Representation 5

2 Figure 2.1 Android Studio 11

2 Figure 2.2 VS Code 12
2 Figure 2.3 Sublime text 12
2 Figure 2.4 Octave(GUI) 13

3 Figure 3.1 SDLC 15

3 Figure 3.2 Waterfall model 16
3 Figure 3.3 RAD model 17
3 Figure 3.4 Spiral model 18
3 Figure 3.5 V-model 18
3 Figure 3.6 Incremental model 19
3 Figure 3.7 Agile model 20
3 Figure 3.8 Iterative model 20
3 Figure 3.9 Big Bang model 21
3 Figure 3.10 Prototype Model 22

4 Figure 4.1 System Development Cycle 26

5 Figure 5.1 Risk factor 28

6 Figure 6.1 0 Level DFD 32

Figure 6.2 1st Level DFD 33
Figure 6.3 2nd Level DFD 34

vii
7 Figure 7.1 Detailed Design model 35

8 Figure 8.1 Skin rash training results 40

8 Figure 8.2 Acidity training results 41
8 Figure 8.3 Itching training results 41
8 Figure 8.4 Joint pain training results 42
8 Figure 8.5 Chills training results 42
8 Figure 8.6 Shivering training results 43
8 Figure 8.7 Sneezing training results 43
8 Figure 8.8 Overall system training results 44

9 Figure 9.1 Home Page 45

9 Figure 9.2 About us Page 45
9 Figure 9.3 Contact Us form 45
9 Figure 9.4 Initial Detection Page 46
9 Figure 9.5 Disease based on set of Symptoms 1 46
9 Figure 9.5 Disease based on set of Symptoms 2 46
9 Figure 9.5 Disease based on set of Symptoms 3 46
9 Figure 9.5 Disease based on set of Symptoms 4 46
9 Figure 9.5 Disease based on set of Symptoms 5 46
9 Figure 9.5 Disease based on set of Symptoms 6 46
9 Figure 9.5 Disease based on set of Symptoms 7 46
9 Figure 9.12 Training dataset 50
9 Figure 9.13 Testing dataset 50

viii
 LIST OF TABLES

CHAPTER NO. TITLE PAGE NO

1 Table 1.1 Table of Research Data 7

ix