Implementation Of C5.0 Classification And Support Vector Machine Algorithm With Correlation-Based Feature Selection In Application Liver Disease

Abstract

Liver disease is a general term that refers to a number of disorders or problems that affect the liver. The liver is an important organ in the human body and has many diverse functions, including food processing, protein production, toxin removal, and energy storage. Therefore, when the liver experiences disorders or disease, it can have a serious impact on the overall health and function of the body. Liver disease is a significant global health problem. Early detection as well as classification of liver disease can provide valuable guidance for effective treatment. Based on the problems above, the aim of this research is to create a liver disease classification model using C5.0 and Support Vector Machine with Radial Basis Function (RBF) and Sigmoid kernels. With data obtained from the liver disease dataset. The two methods will be compared and we will find out which one produces the best results. The method used is also optimized with CFS (Correlation Based Feature Selection) feature selection. The results of the classification process, namely the C5.0 Model and Support Vector Machine (RBF) with CFS have a similar accuracy of 76%, while the Support Vector Machine (Sigmoid) has an accuracy of 70%, without feature selection the C5.0 algorithm has an accuracy of 66% , Support Vector Machine between RBF and sigmoid kernels has an accuracy of 69% and 55%.