Prediction of Cardiovasclar Disease Using Machine Learning Algorithm

You might also like

Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 8

PREDICTION OF CARDIOVASCLAR DISEASE USING

MACHINE LEARNING ALGORITHM

A PROJECT REPORT

Submitted by

AMUDHINI V P (115011012568)

SANTHINI T (115011012581)

in partial fulfillment for the award of the degree

of

BACHELOR OF TECHNOLOGY

in

COMPUTER SCIENCE AND ENGINEERING

PERIYAR NAGAR, VALLAM-613 403, THANJAVUR.

MAY 2019

1
DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

Periyar Nagar, Vallam Thanjavur-613 403, Tamil Nadu, India


Phone: +91- 4362 -264600 Fax: +91 - 4362- 264660
Email: coe@pmu.edu Web: http://www.pmu.edu

BONAFIDE CERTIFICATE

Certified that this Project report “PREDICTION OF CARDIOVASCULAR


DISEASE USING MACHINE LEARNING ALGORITHM” is the bonafide work
of “AMUDHINI V P (115011012568), SANTHINI T (115011012581)” who carried
out the project work under my supervision.

Signature :

Name : Dr. A.E. NARAYANAN Ms. R. POONGUZHALI

Head of the Department Project Guide


Date :

Submitted for Periyar Maniammai Institute of Science and Technology Project Viva –
Voce Examination held on ……………..…….. at PMIST.

Signature :

Name :

External Examiner Internal Examiner

Date :

ii
ACKNOWLEDGEMENT
We feel much grateful to wave our salutation to our institution. We wish to express our
gratitude to our Esteemed Chancellor Dr. K. VEERAMANI, M.A., B.L., the paramount of
our institution for this patronage to do the project as a successful one.

We wish to express our heartfelt gratitude to our Honorable Vice-Chancellor


Dr. S . Velusami, B.E., M.E., Ph.D. Periyar Maniammai Institute of Science & Technology
for providing us the facilities and excellent infrastructure that enabled us to complete the
project successfully.

I would like to express my humble and sincere thanks to Dr.S.A.Dhanaraj, Registrar,


Periyar Maniammai Institute of Science & Technology for his support and guidance for
complete the project successfully.

It is my pleasure to extend my gratitude to Dr. P.K.Srividhya, Dean Academics, Periyar


Maniammai Institute of Science & Technology for her constant support and encouragement
to do the project as a successful one.

We express our sincere thanks to our Dean, Faculty of Computing Sciences and Engineering
Dr.J.Jeyachidra, MCA, Ph.D., without her extensive support, valuable advice and
suggestions, this project would not have reached a state of fruition.

We wish to acknowledge our credits and deep sense of gratitude to our


Head of the Department, Computer Science and Engineering,
Dr. A.E. NARAYANAN, B.E., M.Tech., Ph.D., whose support was incomparable and his
guidance made this project a successful one.

With a deep feeling of indebtedness, we extend our heartfelt gratitude and profound thanks to
our Project Co-ordinator Mr. K.M. Arivuchelvan B.E., M.E.,(Ph.D.), Assistant Professor
(SS), Computer Science and Engineering and my esteemed guide
Ms. R Poonguzhali, B.E, M.E, Assistant Professor (SS), Computer Science and
Engineering, for their valuable guidance, spontaneous help and assistance in providing the
continuous encouragement for the successful completion of the project.

We will never fail to acknowledge the help and encouragement that we received from our
parents and support from friends in the preparation of our project work. We are very thankful
to all who have helped us.

iii
ABSTRACT
A cardiovascular disease is one of the most threatening diseases today. It consists of
coronary artery diseases (CAD) like angina and myocardial infarction (heart attack), stroke,
hypertensive heart disease etc. To predict these diseases accurately and more effectively,
Machine learning algorithms are used. The algorithms used for prediction are Support
Vector Machine (SVM), Naïve Bayes, Decision tree, K-Nearest Neighbor, Neural
Networks. Support Vector Machine (SVM) algorithm is best among other algorithms and its
accuracy is not below 50% in any testing and training dataset. This algorithm has low
generalization error and it is also computationally inexpensive. In this system, the attributes
of dataset is been reduced to increase the accuracy of prediction. This selected attributes are
more significant to predict the disease.

Keywords – Cardiovascular disease, Machine Learning, Support Vector Machine.

iv
TABLE OF CONTENTS
CHAPTER TITLE PAGE NO
NO
ACKNOWLEDGMENT iii

ABSTRACT iv

1 INTRODUCTION 1

1.1 Methodology 7

1.1.1 Machine Learning 7

1.1.2 Support Vector Machine(SVM) 8

1.1.3 Working of SVM 8

1.1.4 Pros and Cons associated with SVM 10

1.2 Advantages 11

1.2.1 Advantages of Machine Learning 11

1.2.2 Advantages of Support Vector Machine 11

1.3 Applications 12

1.3.1Applications of Machine Learning 12

1.3.2 Applications of Support Vector Machine 13

2 REQUIREMENTS 14

2.1 Hardware Requirements 14

2.2 Software Requirements 14

v
3 LITERATURE SURVERY 15

4 MODULE DESCRIPITION 33

4.1 Architecture 33

4.2 Module 1 - Collection of Data from Dataset 34

4.3 Module 2 - Load the Training Data 35

4.4 Module 3 - Algorithm Implementation 36

4.4.1 SVM Algorithm Implementation 36

4.5 Module 4 - Load the Testing data 37

5 IMPLEMENTATION DETAILS 39

5.1 Source Code 39

5.2 Screenshots 43

5.3 User Manual 45

CONCLUSION 46

REFERENCES 47

APPENDIX 50

vi
LIST OF FIGURES
FIGURE NO TITLE PAGE NO
1 Support Vector Machine 8

2 SVM classifier 9

3 Thumb Rule 1 9

4 Thumb Rule 2 10

5 Implementation Process Diagram 17

6 Proposed methodology and implementation of with SVM and 18


FFBP

7 Smart Mouse 19

8 Smart Mirror 20

9 Smart Chair 20

10 Smart Phone 21

11 Proposed system for prediction of cardiovascular diseases 25

12 Flowchart of the risk level prediction system 29

13 Train data 36

14 Test data 38

15 Implementation Screenshots 43 & 44

vii
LIST OF ABBREVIATIONS

S.NO. ABBREVIATIONS EXPANSION


1 CVD Cardiovascular Disease
2 SVM Support Vector Machine
3 CHD Coronary Heart Disease
4 CAD Coronary Artery Disease
5 ECG Electrocardiography
6 KNN K-Nearest Neighbor
7 ANN Artificial Neural Network
8 NN Neural Network
9 BA Backpropagation Algorithm
10 NB Naïve Bayes

viii

You might also like