Adaptive Fuzzy Clustering for improving classification performance in yeast data set

In data mining, there is inter-category imbalance of data which includes unnecessary data that hinder the formulation of an efficient model. This paper called FSFC+ introduces a new focused sampling based on adaptive Fuzzy Clustering. By applying FSFC+, the optimal number of clusters was used by adaptive method. It removes unuseful data that can be obstacles to the formulation of an efficient model. When there is no information about data set, we would evaluate the fitness of partitions produced by cluster validity index. In addition, it is very useful in data analysis because it can quantify the degree of membership of data to multiple clusters.