AGGREGATION OPERATORS AND FUZZY-SYSTEMS MODELING

A general class of aggregation operators called MICA having the properties of monotonicity, symmetry and an identity element are introduced. We stress the significance of the choice of identity in characterizing the operator. We show that the t-norm and t-conorm are special cases of these operators. Other classes of these operators are introduced, notably an additive class which is very much in the spirit of the kind of aggregation used in neural networks. It is shown how a general description of the fuzzy systems modeling technique can be obtained using these operators.