An Improved Fuzzy Multi-class Twin Support Vector Machine

Abstract

Multi-class twin support vector machine (MTSVM) is a multi-class classification algorithm. It has extensive application in the multi-class classification problems. In order to improve the classification performance of MTSVM, an improved fuzzy multiclass twin support vector machine (IF-MTSVM) is proposed. Then the solution to IF-MTSVM is derived. Experiments on ordinary UCI datasets and datasets with 5% noises added show that this new method has certain advantages over other fuzzy multi-class twin support vector machines.