A NEURO-FUZZY APPROACH TO DATA-ANALYSIS OF PAIRWISE COMPARISONS

Artificial neural networks provide iterative on-line learning schemes for modeling non-linear systems. An iterative learning algorithm in fu zzy models, which is called neuro-fuzzy, has been recently developed w ithin the framework of fuzzy modeling in the sense of M. Sugeno. In th is paper, using neuro-fuzzy approach, two quantification methods of pa irwise comparisons are presented in order to derive the associated wei ghts of different objects. The proposed methods can be applied even in the case of incomplete pairwise comparisons. A simplified fuzzy reaso ning model is obtained in the form of Gaussian radial basis functions. The psychological sensation responses of human beings to minute vibra tions are analyzed by the newly proposed neuro-fuzzy approach. The pro posed approach is compared with Guttman's method and Saaty's analytic hierarchy process (AHP). In our two neuro-fuzzy approaches, psychologi cal values are obtained with the interval and the ratio scale properti es. They are represented by smooth functions of class C(infinity).