Product form design using ANFIS-KANSEI engineering model

Abstract

This study presents a novel approach based on Kansei engineering to determine the best design combination of product form elements for matching consumer-preferred product images. First, the evaluation of product's images is performed via the analytic hierarchy process, and their results are represented in terms of adjective image words. Second, an adaptive network-based fuzzy inference system (ANFIS) model is used to examine the relationship between product form elements and product images, thus identifying the most crucial elements of product form for known consumer-preferred product images. A neural network (NN) model is utilized for comparison to validate the prediction ability of ANFIS. To evaluate the performance of ANFIS and NN models, an experimental study on the form design of MP3 (MPEG 1 Layer 3) players is conducted. The evaluation result shows that the ANFIS model has a good prediction performance and is suitable to help product designers determine the best combination of form elements for achieving desirable product images.