Performance Comparison of Adaptive Neuro Fuzzy Inference System and Support Vector Machine Algorithm in Balanced and Unbalanced Multiclass Data Classification

Abstract

Data is a record collection of facts. At first the data in the real world were largely unbalanced. Although, the existence of data on fewer categories is much more important to know data on more categories. However, there are some balanced data. This balanced data is the possibility of a ratio of 1:1 in which, the data in the dataset is the same. In this study, using the ANFIS algorithm and SVM to see affected performance on balanced and imbalanced data with multiclass. Data is taken from the UCI Machine Learning named Iris dataset and Wine dataset. There are four step taken from this research which is selection, preprocessing, data mining, and conclusion. From the research conducted using SVM and ANFIS, it is known that the SVM method on the Wine dataset has an accuracy of 96.6 percent and the ANFIS method on the Iris dataset has an accuracy of 94.7 percent.