Please use this identifier to cite or link to this item: http://hdl.handle.net/10266/4619
Title: Prediction of Heart Disease using Hybrid Methodology of Selecting Features
Authors: Pahwa, Kanika
Supervisor: Kumar, Ravinder
Keywords: machine learning;Feature selection;Naive bayes;random forest
Issue Date: 10-Aug-2017
Abstract: Generally Healthcare industry is known to be ’information rich’ , but woefully all the data required to discover hidden patterns are not mined .In present time heart disease is most fatal one.This is one of the leading cause of death in countries like UK ,Canada,India,Australia .Attack of heart disease is so abrupt that it rarely gives anyone a time to tackle with it.So detection of disease precisely and timely is complicated and intricate task in field of medical. Medical professionals may take wrong decision during diagnosis which may cause death of patient . For effective decision making in field of medical ,advanced techniques of data mining are used. The work represented here mainly focuses on prediction of heart disease using supervised machine learning models. On basis of available features , data is classified into two classes i.e. presence and absence using Random Forest and Naive Bayes . In addition , approach is proposed to select features before classification in order to improve performance of models. Here proposed approach helps to derive importance of features . This is done by applying SVM-RFE and gain ratio algorithms to dataset which in results assigns weight to each feature.This approach helps to improve accuracy and reduce computational time.Experimental results shows that proposed approach of selecting feature increases accuracy for both models.
URI: http://hdl.handle.net/10266/4619
Appears in Collections:Masters Theses@CSED

Files in This Item:
File Description SizeFormat 
4619.pdf1.27 MBAdobe PDFThumbnail
View/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.