Eliciting User Perceptions Using Assessment Tests Based on an Interactive Genetic Algorithm

Abstract

To avoid failures in the marketplace, the control of the risks in product innovation and the reduction of the innovation cycles require fast and valid assessments from customers. An interactive genetic algorithm (IGA) is proposed for eliciting users' perceptions about the shape of a product, in order to stimulate creativity and to identify design trends. Interactive users' assessment tests are conducted on virtual products to capture and analyze users' responses. The IGA is interfaced with Computer Aided Design (CAD) software (CATIA V5) to create sets of parameterized designs in real time, which are presented iteratively by a graphical interface to the users for evaluation. After a description of the IGA, a study on the convergence of the IGA is presented. The convergence varies, according to the tuning parameters of the algorithm and the size of the design problem. An experiment was carried out with a set of 45 users on the application case, a dashboard, put forward by Renault. The implementation of the perceptive tests and the analysis of the results are described using hierarchical ascendant classification (HAC) and multivariate analysis. This paper shows how the results of tests using IGA can be used to elicit user perception and to detect design trends.

Optimization of the Sound of Electric Vehicles According to Unpleasantness and Detectability

“…Since the user decides the individual fitness, there is no need for a prior and unique formulation of the fitness function. For some applications, such as exploring semantic dimensions (Poirson et al, 2013) or integrating complex perceptual processes (Wakefield et al, 2005) (Lee and Chang, 2010), this advantage is crucial.…”

“…Our implementation uses a binary coding and discrete-valued variables. A more complete description of the implementation of our IGA can be found in (Poirson et al, 2013). The IGA creates an initial population of designs by randomly generating the chromosomes and presents them to the user (e.g.…”

“…To address this problem, we propose in this paper an interactive optimization of EV sounds based on Interactive Genetic Algorithms (IGA). This model-free approach is efficient to improve design solutions during interactive assessments (Poirson et al, 2013), and to take into account subtle perceptual phenomenon (Wakefield et al, 2005). The first objective is to define a design method for the optimization of the tradeoff detectability/unpleasantness of EV sounds.…”

Estimating and Exploring the Product Form Design Space Using Deep Generative Models

“…A single query for a set of generated responses is often the focus of knowledge representation tools geared towards product form representations [32] following early ideas from Simon [44]. Iterative communication tools include interactive genetic algorithms [26,[45][46][47] and more recently proposed online crowdsourcing methods [21]. We note that while these previous approaches have used neural networks similar to this work, these previous uses have modeled preference elicitation rather than design representation and design generation.…”

An interactive motion planning framework that can learn from experience

“…The quality of the generated motion of the mannequin becomes a major issue, which mainly concerns reducing the redundant degrees of freedom and making the motion look more natural. Besides, a key challenge for the designers is to analyze end-users' responses in the design process and to promote product innovation, but users' preferences cannot be precisely formulated [15]. Hence, the optimization of the preference of users is today extremely difficult for an automatic method, and the integration with the direct participation of designers is an essential stage [16,17].…”