A kind of fuzzy least squares support vector machines for pattern classification

Support Vector Machine (SVM) is a new machine learning method, and Least Squares Support Vector Machine is an SVM version that involves equality instead of inequality constraints, and works with a least squares cost function. Both of these two methods learn the decision surface from two distinct classes of input points, and each point is assigned to one of these two classes. But in many applications, a few points are not sure assigned to one of these two classes. In this paper, we apply a fuzzy degree based on membership function to each input point and reformulate the LS-SVM such that different input points can have different contributions to the learning of the decision function.