Presentation 2021-05-28
Emotional Estimation by Micro-expression Using Ensemble Learning
Koki Kato, Hironobu Takano, Masahiro Saiko, Masahiro Kubo, Hitoshi Imaoka,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Bad news, such as cancer notifications from doctors, has a big impact on patients. The patient does not remember the contents of the interview. Therefore, it is necessary for medical doctors to estimate the patient's emotions during the interview and to understand the patient's internal condition. In the medical field, the development of a communication support system is required. The purpose of this study is to improve the accuracy of emotional estimation using micro-expressions which would express true emotions. The LBP-TOP selected by using the ratio of the inter-class variance to within-class one was used. Boosting, which is one of ensemble learning, was used as the classifier. In this paper, we show the experimental results obtained with the XGBoost and SVM.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Micro-expression / LBP-TOP / Ensemble Learning / XGBoost
Paper # MBE2021-2
Date of Issue 2021-05-21 (MBE)

Conference Information
Committee MBE
Conference Date 2021/5/28(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Takashi Watanabe(Tohoku Univ.)
Vice Chair Ryuhei Okuno(Setsunan Univ.)
Secretary Ryuhei Okuno(Akita-noken)
Assistant Akihiro Karashima(Tohoku Inst. of Tech.) / Jun Akazawa(Meiji Univ. of Integrative Medicine)

Paper Information
Registration To Technical Committee on ME and Bio Cybernetics
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Emotional Estimation by Micro-expression Using Ensemble Learning
Sub Title (in English)
Keyword(1) Micro-expression
Keyword(2) LBP-TOP
Keyword(3) Ensemble Learning
Keyword(4) XGBoost
1st Author's Name Koki Kato
1st Author's Affiliation Toyama Prefectural University(Toyama Pref. Univ.)
2nd Author's Name Hironobu Takano
2nd Author's Affiliation Toyama Prefectural University(Toyama Pref. Univ.)
3rd Author's Name Masahiro Saiko
3rd Author's Affiliation NEC Corporation(NEC)
4th Author's Name Masahiro Kubo
4th Author's Affiliation NEC Corporation(NEC)
5th Author's Name Hitoshi Imaoka
5th Author's Affiliation NEC Corporation(NEC)
Date 2021-05-28
Paper # MBE2021-2
Volume (vol) vol.121
Number (no) MBE-50
Page pp.pp.2-5(MBE),
#Pages 4
Date of Issue 2021-05-21 (MBE)