Home // AMBIENT 2014, The Fourth International Conference on Ambient Computing, Applications, Services and Technologies // View article
Authors:
Kazuhito Sato
Takashi Suto
Hirokazu Madokoro
Sakura Kadowaki
Keywords: Psychological measures, stress; Intentional facial expression; Machine learning approaches; Behavior modeling
Abstract:
This paper presents a framework of tempos and rhythms to clarify the relevance between psychological states and facial expressions, particularly addressing repetitive operations of intentional facial expressions after giving a stress stimulus. By acquiring image datasets of facial expressions under the states of pleasant–unpleasant stimulus for 20 subjects, we extracted expressive tempos for respective subjects. Consequently, averages of extraction rates show that the pleasant state was 81.1%. The unpleasant state was 77.8%. Regarding effects of pleasant–unpleasant stimulus on the expressive tempos, particularly addressing the variation of the number of frames constituting one tempo, the variation in unpleasant stimulus became greater than that in the pleasant stimulus. The results show that the analysis using expressive tempos and rhythms is valid as an indicator for estimating the psychological state.
Pages: 72 to 81
Copyright: Copyright (c) IARIA, 2014
Publication date: August 24, 2014
Published in: conference
ISSN: 2326-9324
ISBN: 978-1-61208-356-8
Location: Rome, Italy
Dates: from August 24, 2014 to August 28, 2014