Fuzzy support vector regression for function approximation with noises

Fuzzy support vector machine (FSVM) have been very successful in pattern recognition problems with outliers or noises. FSVM enhances the SVM in reducing the effect of noises in data points. In this paper, we introduce FSVM to regression problems for function approximation with noises. We apply a fuzzy membership to each input point of SVR and reformulate SVR into fuzzy SVR (FSVR) such that different input points can make different contributions to the learning of decision function.