Layered Modeling of Affective, Perception, and Visual Properties: Optimizing Structure With Genetic Algorithm

Abstract

To design the “Kansei value” aspect of a product, it is useful to design multilayered relationships of perceptual and affective responses via the physical or psychophysical properties of the product. However, because they are qualitative and ambiguous, designing a model is time-consuming. Moreover, the design was conducted by hypothesis and trial-and-error by the experimenter. In this article, we developed a method to automatically construct several semioptimal structures by applying a genetic algorithm to model design based on structural equation modeling, using the results of image measurement and subjective evaluation experiments on various material samples. Under set convergence conditions, the method constructed statistically optimized structures that represent the relationships among adjectives describing perception and affective, and the properties. A semantic validation was performed to determine the final model. As a result, the proposed method could be used to construct a model that can be interpreted as semantically and statistically superior compared to methods in related studies. A unique feature of this article was the use of the physical and psychophysical properties obtained by measurements in the construction of a multilayer model. Also, the advantage of this method is that it can be used to construct important structures that may be overlooked.