A computational model simulating the mental function of multicolor aesthetic evaluation

Siyuan Fang, Keiichi Muramatsu, Tatsunori Matsui

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In this research, a computational model that simulates the mental function of multicolor aesthetic evaluation through backpropagation neural networks was constructed. Helmut Leder's psychological model served as the theoretical framework. We determined the macro-architecture of the computational model through two psychological experiments using the semantic differential (SD) method. The aesthetic score of a multicolor stimulus is defined as the inverse of its factor score on the factor "Pleasure" extracted in the first experiment, and each of the three factors extracted in the second experiment-i.e., "Stability," "Heaviness," and "Presence"-is regarded as a simple perceptual feature. The genetic algorithm was then employed to optimize the hidden layer node number, the learning rate, and the momentum constant of each neural network. In two simulation tests, this computational model exhibited some predictive power, implying that the model can be regarded as a relatively successful approximation of the psychological mechanism of multicolor aesthetic evaluation. In addition, the results of the second simulation also show that the perceptual feature "Heaviness" possesses the principal impact on the aesthetic evaluation of multicolor objects, whereas the other two perceptual features "Stability" and "Presence" have a minor influence. The heavier and/or more stable a multicolor object is perceived to be, the less aesthetically pleasing it is. Conversely, the stronger the sense of matter presence a multicolor object elicits, the more aesthetically appealing it is.

Original languageEnglish
JournalColor Research and Application
DOIs
Publication statusAccepted/In press - 2016

Fingerprint

aesthetics
evaluation
neural network
experiment
Neural networks
semantic differential
simulation
Experiments
Backpropagation
Macros
Momentum
stimulus
Genetic algorithms
Semantics
learning

Keywords

  • Aesthetic
  • Computational model
  • Genetic algorithm
  • Neural network
  • Semantic differential

ASJC Scopus subject areas

  • Human Factors and Ergonomics
  • Chemistry(all)
  • Chemical Engineering(all)

Cite this

@article{583ad18813614e8e94b78cf3d1368085,
title = "A computational model simulating the mental function of multicolor aesthetic evaluation",
abstract = "In this research, a computational model that simulates the mental function of multicolor aesthetic evaluation through backpropagation neural networks was constructed. Helmut Leder's psychological model served as the theoretical framework. We determined the macro-architecture of the computational model through two psychological experiments using the semantic differential (SD) method. The aesthetic score of a multicolor stimulus is defined as the inverse of its factor score on the factor {"}Pleasure{"} extracted in the first experiment, and each of the three factors extracted in the second experiment-i.e., {"}Stability,{"} {"}Heaviness,{"} and {"}Presence{"}-is regarded as a simple perceptual feature. The genetic algorithm was then employed to optimize the hidden layer node number, the learning rate, and the momentum constant of each neural network. In two simulation tests, this computational model exhibited some predictive power, implying that the model can be regarded as a relatively successful approximation of the psychological mechanism of multicolor aesthetic evaluation. In addition, the results of the second simulation also show that the perceptual feature {"}Heaviness{"} possesses the principal impact on the aesthetic evaluation of multicolor objects, whereas the other two perceptual features {"}Stability{"} and {"}Presence{"} have a minor influence. The heavier and/or more stable a multicolor object is perceived to be, the less aesthetically pleasing it is. Conversely, the stronger the sense of matter presence a multicolor object elicits, the more aesthetically appealing it is.",
keywords = "Aesthetic, Computational model, Genetic algorithm, Neural network, Semantic differential",
author = "Siyuan Fang and Keiichi Muramatsu and Tatsunori Matsui",
year = "2016",
doi = "10.1002/col.22067",
language = "English",
journal = "Color Research and Application",
issn = "0361-2317",
publisher = "John Wiley and Sons Inc.",

}

TY - JOUR

T1 - A computational model simulating the mental function of multicolor aesthetic evaluation

AU - Fang, Siyuan

AU - Muramatsu, Keiichi

AU - Matsui, Tatsunori

PY - 2016

Y1 - 2016

N2 - In this research, a computational model that simulates the mental function of multicolor aesthetic evaluation through backpropagation neural networks was constructed. Helmut Leder's psychological model served as the theoretical framework. We determined the macro-architecture of the computational model through two psychological experiments using the semantic differential (SD) method. The aesthetic score of a multicolor stimulus is defined as the inverse of its factor score on the factor "Pleasure" extracted in the first experiment, and each of the three factors extracted in the second experiment-i.e., "Stability," "Heaviness," and "Presence"-is regarded as a simple perceptual feature. The genetic algorithm was then employed to optimize the hidden layer node number, the learning rate, and the momentum constant of each neural network. In two simulation tests, this computational model exhibited some predictive power, implying that the model can be regarded as a relatively successful approximation of the psychological mechanism of multicolor aesthetic evaluation. In addition, the results of the second simulation also show that the perceptual feature "Heaviness" possesses the principal impact on the aesthetic evaluation of multicolor objects, whereas the other two perceptual features "Stability" and "Presence" have a minor influence. The heavier and/or more stable a multicolor object is perceived to be, the less aesthetically pleasing it is. Conversely, the stronger the sense of matter presence a multicolor object elicits, the more aesthetically appealing it is.

AB - In this research, a computational model that simulates the mental function of multicolor aesthetic evaluation through backpropagation neural networks was constructed. Helmut Leder's psychological model served as the theoretical framework. We determined the macro-architecture of the computational model through two psychological experiments using the semantic differential (SD) method. The aesthetic score of a multicolor stimulus is defined as the inverse of its factor score on the factor "Pleasure" extracted in the first experiment, and each of the three factors extracted in the second experiment-i.e., "Stability," "Heaviness," and "Presence"-is regarded as a simple perceptual feature. The genetic algorithm was then employed to optimize the hidden layer node number, the learning rate, and the momentum constant of each neural network. In two simulation tests, this computational model exhibited some predictive power, implying that the model can be regarded as a relatively successful approximation of the psychological mechanism of multicolor aesthetic evaluation. In addition, the results of the second simulation also show that the perceptual feature "Heaviness" possesses the principal impact on the aesthetic evaluation of multicolor objects, whereas the other two perceptual features "Stability" and "Presence" have a minor influence. The heavier and/or more stable a multicolor object is perceived to be, the less aesthetically pleasing it is. Conversely, the stronger the sense of matter presence a multicolor object elicits, the more aesthetically appealing it is.

KW - Aesthetic

KW - Computational model

KW - Genetic algorithm

KW - Neural network

KW - Semantic differential

UR - http://www.scopus.com/inward/record.url?scp=84977080785&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84977080785&partnerID=8YFLogxK

U2 - 10.1002/col.22067

DO - 10.1002/col.22067

M3 - Article

JO - Color Research and Application

JF - Color Research and Application

SN - 0361-2317

ER -