EFFICIENT FUZZY PARTITION OF PATTERN SPACE FOR CLASSIFICATION PROBLEMS

This paper proposes an efficient fuzzy partition method of a pattern s pace for classification problems. The proposed method is based on the sequential subdivision of fuzzy subspaces and the generated fuzzy subs paces have different sizes. In the proposed method, first an n-dimensi onal pattern space is divided into 2'' fuzzy subspaces with the same s ize. Next one of the fuzzy subspaces is selected and subdivided into 2 '' fuzzy subspaces. This procedure is iterated until a stopping condit ion is satisfied. Some criteria for selecting a fuzzy subspace to be s ubdivided are proposed and compared with each other by computer simula tions. The proposed method is also compared with other fuzzy classific ation methods.