<![CDATA[The world's high death rate from heart disease requires early prevention by medical doctors to diagnose heart disease early. The machine learning approach makes it possible to predict the risk of developing heart disease by examining certain values at a low cost. This study will contribute to the development of a combination of Logistic Regression and SVM models that integrate SVM and Logistic Regression algorithms by implementing selection features using hybrid PSO and GA methods. The combination concept of Logistic Regression SVM (LRSVM) applied to this study is to reduce the risk of SVM output errors by interpreting and modifying the output of SVM classifiers by the results of Logistic Regression analysis. The test results showed that LRSVM with pso-GA hybrid-based selection feature achieved better performance for coronary heart disease classification with 99.66% accuracy compared to classification accuracy with SVM algorithm without selection feature]]>
Copyrights © 2021
