Apply Multi-class Fuzzy Support Vector Machines to Product-Form-Image Prediction

Abstract

Extracting critical form features from a product relative to solvespecific Kansei adjectives through Kansei image questionnaire system isan important method. Due to the fuzziness of Kansei image, a, fuzzyclassifier needs to be constructed. In this study, a kansei evaluationon product form employing multi-class fuzzy support vector machines(MF-SVMs) was proposed to extract implicit information of products.Critical form features were mapped into an n-dimensional vector; formulti-dimensional Kansei images, ``One-Versus-Rest{''} (OVR) method formulti-class SVMs was addressed to deal with this problem. For newproducts, system will specify it by using MF-SVMs based classificationmodel. A case study of mobile phone design is given to demonstrate theeffectiveness of the proposed methodology.