An Approach for Prototype Generation based on Similarity Relations for Problems of Classification

Yumilka B. Fernandez Hernandez, Rafael Bello, Yaima Filiberto, Mabel Frias, Lenniet Coello Blanco, Yaile Caballero


In this paper, a new method for solving classification problems based on prototypes is proposed. When using similarity relations for granulation of a universe, similarity classes are generated, and a prototype is constructed for each similarity class. Experimental results show that the proposed method has higher classification accuracy and a satisfactory reduction coefficient compared to other well-known methods, proving to be statistically superior in terms of classification’s precision.



Prototype generation, similarity relations, classification

Full Text: PDF