AN AUTOMATIC BUILDER FOR A KANSEI ENGINEERING EXPERT-SYSTEM USING SELF-ORGANIZING NEURAL NETWORKS

Kansei Engineering is a technology for translating human feelings into a product design. Linear multiple regression analysis is used as a to ol to analyze the feelings-design relations and building rules for Kan sei Engineering expert systems. Although the method is reliable, it is nevertheless, time and resource consuming and requires statistical ex pertise in relation to its mathematical constraints. In this paper, we introduce an automatic builder of Kansei expert systems using a self- organizing neural network ART1.5-SSS. ART1.5-SSS is our modified versi on of ART1.5, a variant of the Adaptive Resonance Theory neural networ k. Improvement on learning rule makes ART1.5-SSS a stable non-hierarch ical cluster analyzer and feature extractor, even in a small sample si ze condition. The network enables quick, automatic rule building in Ka nsei Engineering expert systems. The categorization and feature select ion performance of our new learning rule is compared to multivariate a nalyses and to the original ART1.5.