Prediction of Cardiovasclar Disease Using Machine Learning Algorithm
Prediction of Cardiovasclar Disease Using Machine Learning Algorithm
Prediction of Cardiovasclar Disease Using Machine Learning Algorithm
A PROJECT REPORT
Submitted by
AMUDHINI V P (115011012568)
SANTHINI T (115011012581)
of
BACHELOR OF TECHNOLOGY
in
MAY 2019
1
DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING
BONAFIDE CERTIFICATE
Signature :
Submitted for Periyar Maniammai Institute of Science and Technology Project Viva –
Voce Examination held on ……………..…….. at PMIST.
Signature :
Name :
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 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.
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.
iv
TABLE OF CONTENTS
CHAPTER TITLE PAGE NO
NO
ACKNOWLEDGMENT iii
ABSTRACT iv
1 INTRODUCTION 1
1.1 Methodology 7
1.2 Advantages 11
1.3 Applications 12
2 REQUIREMENTS 14
v
3 LITERATURE SURVERY 15
4 MODULE DESCRIPITION 33
4.1 Architecture 33
5 IMPLEMENTATION DETAILS 39
5.2 Screenshots 43
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
7 Smart Mouse 19
8 Smart Mirror 20
9 Smart Chair 20
10 Smart Phone 21
13 Train data 36
14 Test data 38
vii
LIST OF ABBREVIATIONS
viii