Fuzzy least squares twin support vector machines

Abstract

Least Squares Twin Support Vector Machine (LST-SVM) has been shown to be an efficient and fast algorithm for binary classification. In many real-world applications, samples may not deterministically be assigned to a single class; they come naturally with their associated uncertainties. Also, samples may not be equally importantand their importance degrees affect the classification. Despite its efficiency, LST-SVM still lacks the ability to deal with these situations. In this paper, we propose Fuzzy LST-SVM (FLST-SVM) to cope with these difficulties.