A novel interval-valued fuzzy multiple twin support vector machine

Abstract

Multiple twin support vector machine (MTSVM) which evaluates all the training data into a ``one-versus-rest'' structure is a multi-class classification algorithm. It has extensive applications in the multi-class classification problems. Like twin support vector machine (TSVM), MTSVM treats all sample points equally because it lacks the ability to judge the importance of different sample points. In order to improve the classification performance of MTSVM, a new method of adding interval-valued fuzzy membership degree to sample points is proposed. In this way, a novel interval-valued fuzzy multiple twin support vector machine (IVF-MTSVM) is established in this paper. Previous methods of adding fuzzy membership degree to sample points are totally based on their importance to the class, while the method in this paper emphasizes the importance of sample points to the classification model, and takes into account the importance to the class to some extent. This is a new perspective to establish fuzzy membership degree to sample points in support vector machines since it is different from the previous methods in thinking. Then the solution to IVF-MTSVM is derived. Experiments on UCI datasets show that this new method has certain advantages over other multi-class twin support vector machine methods in ``one-versus-rest'' structure and other fuzzy multiple twin support vector machine established by some previous methods. Finally, Friedman test and Benferroni-Dunn test are used to verify the statistical significance of this new method.