Title: A Bayesian learning of probabilistic relations between perceptual attributes and technical characteristics of car dashboards to construct a perceptual evaluation model
Authors: Walid Ben Ahmed, Bernard Yannou
Addresses: Power Train Division, Renault, Sce 66101/UET Fiabilite Previsionnelle, DCT/Dept Metier Fiabilite et MAP, FR CTR A02 3 70, 67 rue des Bons Raisins, 92500 Rueil-Malmaison, France. ' Laboratoire Genie Industriel, Ecole Centrale Paris, Grande Voie des Vignes, 92295 Chatenay-Malabry, France
Abstract: Starting from a primary perceptual evaluation of a set of car dashboards, we propose to build a Bayesian network (BN) between perceptual attributes and design attributes. Two types of learning processes may be considered: supervised BN when the prediction on a targeted attribute must be optimised and unsupervised BN otherwise. These two types of BNs are considered along three design simulation scenarios: the direct scenario which consists of the prediction of a design change impact on customer perceptions, the inverse scenario for fixing design characteristics so as to result in an expected customer perception, and a more realistic combined scenario.
Keywords: decision making; Kansei engineering; design synthesis; perceptual evaluation; emotional design; Bayesian networks; emotion; automotive dashboards; dashboard design; vehicle design; design attributes; design change; customer perceptions.
International Journal of Product Development, 2009 Vol.7 No.1/2, pp.47 - 72
Published online: 25 Dec 2008 *Full-text access for editors Access for subscribers Purchase this article Comment on this article