A Fuzzy Universum Support Vector Machine Based on Information Entropy

Abstract

Universum-based support vector machines (USVMs) are known to give better generalization performance than standard SVM methods by incorporating prior information about the data. In datasets involving noise and outliers, this universum-based scheme is not so effective because the generated universum data points do not lie in between the two classes. In this paper, we propose a fuzzy universum support vector machine (FUSVM) by introducing the weights to the universum data points based on their information entropy. Since there is no standard approach of selecting the universum, our information entropy based approach is helpful in giving less weight to the outlier universum points and thus gives prior information about the data in an appropriate manner. In addition, we also propose a fuzzy-based approach for universum twin support vector machine named as fuzzy universum twin support vector machine (FUTSVM). Experimental results on several benchmark datasets indicate that, comparing to SVM, USVM, TWSVM and UTSVM our proposed FUSVM and FUTSVM have shown better generalization performance