Rough-fuzzy knowledge encoding and uncertainty analysis: relevance in data mining

Abstract

Data mining and knowledge discovery is described from pattern recognition point of view along with the relevance of soft computing. The concept of computational theory of perceptions (CTP), its characteristics and the relation with fuzzy-granulation (f-granulation) are explained. Role of f-granulation in machine and human intelligence, and its modeling through rough-fuzzy integration are discussed. Three examples of synergistic integration, e.g., rough-fuzzy case generation, rough-fuzzy c-means and rough-fuzzy c-medoids are explained with their merits and role of fuzzy granular computation. Superiority, in terms of performance and computation time, is illustrated for the tasks of case generation (mining) in large scale case based reasoning systems, segmenting brain MR images, and analyzing protein sequences.