Fuzzy pattern classification tuning by parameter learning based on fusion concept

In this paper, a fuzzy pattern classification tuning approach is proposed, which is based on fusion concept. In this method, tuning parameters are learned in a training procedure, enabling system to be capable of managing individual classification task. Fuzzy c-means, as a specific instance of Tuning Reference, is employed as a tool to offer membership function which is used for making decisions and its membership function fuses (tunes) another membership function captured from fuzzy pattern classification and then final decisions are made upon fused one. Experiments are taken on five benchmark datasets, one of them shows an equal performance and the other four present better results than each single classifier.