Development of customer satisfaction models for affective design using rough set and ANFIS approaches

Abstract

Rough set (RS)- and particle swarm optimization (PSO)- based adaptive neuro-fuzzy inference system (ANFIS) approaches are proposed to generate customer satisfaction models in affective design that address fuzzy and nonlinear relationships between affective responses and design attributes. The RS theory is adopted to reduce the number of fuzzy rules generated using ANFIS and simplify the structure of ANFIS. PSO is employed to determine the parameter settings of an ANFIS from which customer satisfaction models with better modeling accuracy can be generated. A case study of mobile phone affective design is used to illustrate the proposed approaches.