A Quantification Method of Pairwise Comparisons by Neuro-Like Fuzzy Modeling(Journal of Japan Society for Fuzzy Theory and Systems)

概要

論文の詳細を見る
Artificial Neural Networks provide iterative on-line learning schemes for modeling non-linear systems. Within the framework of Fuzzy Modeling in the sense of M.Sugeno, an iterative learning algorithm in fuzzy models, which is called Neuro-Fuzzy, has been developed and applied to electrical home appliance products recently. In this paper, using Neuro-Like Fuzzy approach, two quantification methods of pairwise comparisons are presented in order to derive the associated weights of different items. The proposed methods can be applied even in the case of incomplete pairwise comparisons. The psychological sensation responses of human beings to minute vibrations are analysed by Saaty's AHP, Guttman's method and the newly proposed Neuro-Like Fuzzy Modeling of pairwise comparisons. In our two Neuro-Like Fuzzy approaches, psychological values are obtained in the forms of interval and ratio scale properties. They are represented by smooth functions of class C^∞.
1992-10-15