Universität Paderborn » SFB 901 » Events


Talk given by Prof. Sankar Kumar Pal (Indian Statistical Institute)

Begin: Mon, 23. of Nov 2015 ( 4:00 PM)
Location: Warburger Str. 100, room O4.267


The theory of fuzzy sets (FS) was first explained in 1965 by  Lotfi A. Zadeh, University of California, Berkely. The theory has been explored as a model of uncertainty analysis during the last fifty years by scientists over the globe for developing methodologies for decision-making problems of various kinds. The successful application areas and systems developed broadly include: fuzzy logic control based systems, fuzzy expert systems, and fuzzy pattern recognition and image processing systems. While the aims were to emulate and replace human operators and human expertise respectively in the first two categories, generalization and uncertainty handling were the objectives in the other one.

The talk addresses the characteristic features of fuzzy pattern recognition and image processing systems, mentioning the growth and evolution of the discipline. It highlights the contributions made towards this from Indian Statistical Institute, Kolkata since early 1975. The talk starts with the relevance of FS to pattern recognition problems, and explains with examples the significance of multi-valued recognition systems and the notion of embedding. Data mining and knowledge discovery from pattern recognition perspectives is explained. Then follows the objective of synergistic integrations of FS with artificial neural networks, genetic algorithms and rough sets, among others, in soft computing for improved performance, computational intelligence and decision-making. Emergence of granular mining in rough-fuzzy framework is explained along with the concepts of f-information granules and rough knowledge encoding. All these features are demonstrated through example experimental results in various domains ranging from speech recognition, image and video analysis, to bio-informatics and social networks.

The talk concludes with future directions of research and relevance to CTP (computational theory of perceptions), natural computing and Big data analysis.