A bayesian learning of probabilistic relations between perceptual attributes and technical characteristics of car dashboards to construct a perceptual evaluation model

Walid Ben Ahmed (1) , Bernard Yannou (1)

1 LGI - Laboratoire Génie Industriel - EA 2606

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.

Mots clés: decision-making; Kansei engineering; design synthesis; perceptual evaluation; emotional design; BNs; Bayesian networks

Domaines: Mécanique [physics.med-ph]; Modélisation et simulation

Walid Ben Ahmed, Bernard Yannou. A bayesian learning of probabilistic relations between perceptual attributes and technical characteristics of car dashboards to construct a perceptual evaluation model. International Journal of Product Development, 2009, 7 (1-2), pp.47-72. ⟨10.1504/IJPD.2009.022276⟩. ⟨hal-00748729⟩