A Sugeno fuzzy model for knowledge representation in a decision support system

Abstract

Research into the field of decision support systems has been strongly enhanced by the development of artificial intelligence applications. One of the main issues to be tackled in simulating human intelligence and reasoning is how to represent human knowledge in a computing system. In this paper, two main approaches are discussed: the formalization of a sequence of reasoning rules (the expert system approach) and the collection of a set of input-output instructions describing human experience but not the internal mechanisms leading to the decision (the neural network approach). The adoption of a Sugeno fuzzy model for supporting the decision-making processes in a company is proposed, and a case of application is presented for testing the performance of such a model and discussing the organizational implications of fuzzy and neuro-fuzzy approaches.