TY - GEN
T1 - Preliminary Reaction Analysis of Audience with Bio-Emotion Estimation Method
AU - Sugaya, Midori
AU - Hiramatsu, Takuya
AU - Yoshida, Reiji
AU - Chen, Feng
PY - 2018/6/8
Y1 - 2018/6/8
N2 - This study is to propose an analytical technique and evaluation measures effective for investigations of emotion estimation by using biological information. For conducting investigations to analyze atmosphere and emotions by corresponding biological information with a Russell's circumplex model, any of analytical techniques or evaluation measures are not established and therefore are used with uncertain effectiveness. In this study, we propose a novel technique using vector decomposition, while a reported study proposed a technique using the ratio of distances analysis, for emotion estimation on the basis of 8 emotion classifications by using 2 different types of biological information including an electroencephalogram and pulse rate, in which a point of emotion is classified on a circumplex model corresponding to a two-dimensional coordinate. Also, to validate the effectiveness, we analyzed audience's emotions responded to a show initially motivating us to investigate. We demonstrated that the evaluation measures could be more effective by validating the evaluation.
AB - This study is to propose an analytical technique and evaluation measures effective for investigations of emotion estimation by using biological information. For conducting investigations to analyze atmosphere and emotions by corresponding biological information with a Russell's circumplex model, any of analytical techniques or evaluation measures are not established and therefore are used with uncertain effectiveness. In this study, we propose a novel technique using vector decomposition, while a reported study proposed a technique using the ratio of distances analysis, for emotion estimation on the basis of 8 emotion classifications by using 2 different types of biological information including an electroencephalogram and pulse rate, in which a point of emotion is classified on a circumplex model corresponding to a two-dimensional coordinate. Also, to validate the effectiveness, we analyzed audience's emotions responded to a show initially motivating us to investigate. We demonstrated that the evaluation measures could be more effective by validating the evaluation.
KW - Affective computing
KW - Bio-emotion estimation method
KW - Biological information
KW - EEG
KW - Emotion estimation
KW - Pulse sensor
UR - http://www.scopus.com/inward/record.url?scp=85055522706&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85055522706&partnerID=8YFLogxK
U2 - 10.1109/COMPSAC.2018.10303
DO - 10.1109/COMPSAC.2018.10303
M3 - Conference contribution
AN - SCOPUS:85055522706
T3 - Proceedings - International Computer Software and Applications Conference
SP - 601
EP - 605
BT - Proceedings - 2018 IEEE 42nd Annual Computer Software and Applications Conference, COMPSAC 2018
A2 - Demartini, Claudio
A2 - Reisman, Sorel
A2 - Liu, Ling
A2 - Tovar, Edmundo
A2 - Takakura, Hiroki
A2 - Yang, Ji-Jiang
A2 - Lung, Chung-Horng
A2 - Ahamed, Sheikh Iqbal
A2 - Hasan, Kamrul
A2 - Conte, Thomas
A2 - Nakamura, Motonori
A2 - Zhang, Zhiyong
A2 - Akiyama, Toyokazu
A2 - Claycomb, William
A2 - Cimato, Stelvio
PB - IEEE Computer Society
T2 - 42nd IEEE Computer Software and Applications Conference, COMPSAC 2018
Y2 - 23 July 2018 through 27 July 2018
ER -