A direct linguistic induction method for systems

The aim of this paper is to present a method of obtaining a linguistic model that reflects the behavior of a combined well-known data. The method is based on the technique of successive division of the input space as CART (Classification and Regression Tree, Wadsworth, Monterey, CA, 1984) and ID3 (Mach. Learning 1 (1986) 81). The obtained rules have linguistic variables such as antecedent and consequent. The methods ID3 and CART are generalized to work directly with linguistic variables defined a priori, incorporating the concept of linguistic interval in order to represent the disjunctions of the linguistic labels.