COMPARISON OF CLASSIFICATION TECHNIQUES ON HEART DISEASE DATA SET

kk revathi revathi, K.K. Kavitha

Abstract


Today’s world in all fields extract useful knowledge from data, Data Mining is an analytic process designed to explore data. Classification analysis is one of the main techniques used in Data Mining. It brings up the differences between different models and evaluates their accuracies in detecting a problem in various aspects. In this work, we focus on Heart Disease problem; specifically we took University of California (UCI) heart disease dataset and WEKA (Waikato Environment for knowledge Analysis) data mining tool. Various researches have investigated this dataset for better prediction measures. In our paper does a comparative study of commonly used machine learning algorithms to detecting heart diseases. The aim of this research to judge the accuracy of different data mining algorithms such as naive bayes, IBK, random forest on heart disease dataset and determine the optimum algorithm for detection of heart disease.

Keywords


Data Mining, Classification, Bayesian, lazy, IBK, random Forest, WEKA, naive bayes

Full Text:

PDF


DOI: https://doi.org/10.26483/ijarcs.v8i9.4870

Refbacks

  • There are currently no refbacks.




Copyright (c) 2017 International Journal of Advanced Research in Computer Science