Home // International Journal On Advances in Intelligent Systems, volume 7, numbers 1 and 2, 2014 // View article
Authors:
Kazuhito Sato
Hiroaki Otsu
Hirokazu Madokoro
Sakura Kadowaki
Keywords: Bayesian networks; Self-organizing maps; Adaptive resonance theory; Expression levels; SRS-18; Intentional facial expressions
Abstract:
This paper presents a gender-specific stress model to analyze psychological stress factors affecting intentional facial expressions. We extract three facial expressions (i.e., happiness, anger, and sadness) from the basic six facial expressions. Then we present a graphical model of the relation between these three facial expressions and the psychological stress factors. From probabilistic reasoning based on the observed values of each facial expression, the following trends were obtained. The stress models constructed by Bayesian networks showed trends of different stress factors between men and women in relation to expression levels and psychological stress. The stress models appeared on happy faces of "lassitude" factor in men. The angry faces of "displeasure and anger" were affected by stress factors in women. Furthermore, the influence of "displeasure and anger" readily appeared in the upper part of the face when expressing "anger". In addition, the influence of "lassitude" strongly appeared in the lower part of the face with the expression of "sadness", in the upper part of the face with the expression of "happiness".
Pages: 194 to 207
Copyright: Copyright (c) to authors, 2014. Used with permission.
Publication date: June 30, 2014
Published in: journal
ISSN: 1942-2679