A fuzzy Min-Max neural network classifier based on centroid

Based on the analysis of the parameters of fuzzy Min-Max neural network, a new classification method of fuzzy Min-Max neural network for real data pattern is proposed. A new membership function is designed which control the descend of membership degree by the distance of the geometric center of hyperbox and Centroid, and the membership function can also adjust the boundary of hyperbox. The influence of parameters of new membership function is discussed by 1-D samples. The availability of the new method is validated by simulation of IRIS dataset.