Abstract
Cases of physical and mental diseases caused by stress and negative emotions have increased annually. Many emotion recognition methods have been proposed. Facial expression is widely used for emotion recognition. However, since facial expressions may be expressed differently by different people, inaccurate results are unavoidable. Nerve and Physiological responses are incontrollable native response. Physiological responses and the corresponding signals are difficult to control when a person is overcome with emotion. Therefore, an emotion recognition system that considers physiological signals is proposed in this paper. An emotion induction experiment was performed to collect five physiological signals from subjects, namely electrocardiogram, respiration, galvanic skin response (GSR), blood volume pulse, and pulse. Support vector regression (SVR) was used to train three trend curves of three emotions (sadness, fear, and pleasure). Experimental results show that the proposed method has a high recognition rate of 90.6%.
| Original language | English |
|---|---|
| Title of host publication | ICS 2010 - International Computer Symposium |
| Pages | 12-17 |
| Number of pages | 6 |
| DOIs | |
| Publication status | Published - 2010 Dec 1 |
| Event | 2010 International Computer Symposium, ICS 2010 - Tainan, Taiwan Duration: 2010 Dec 16 → 2010 Dec 18 |
Publication series
| Name | ICS 2010 - International Computer Symposium |
|---|
Other
| Other | 2010 International Computer Symposium, ICS 2010 |
|---|---|
| Country | Taiwan |
| City | Tainan |
| Period | 10-12-16 → 10-12-18 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Computer Science(all)
Cite this
}
Application of support vector regression for phyciological emotion recognition. / Chang, Chuan Yu; Zheng, Jun Ying; Wang, Chi-Jen; Chung, Pau-Choo.
ICS 2010 - International Computer Symposium. 2010. p. 12-17 5685532 (ICS 2010 - International Computer Symposium).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - Application of support vector regression for phyciological emotion recognition
AU - Chang, Chuan Yu
AU - Zheng, Jun Ying
AU - Wang, Chi-Jen
AU - Chung, Pau-Choo
PY - 2010/12/1
Y1 - 2010/12/1
N2 - Cases of physical and mental diseases caused by stress and negative emotions have increased annually. Many emotion recognition methods have been proposed. Facial expression is widely used for emotion recognition. However, since facial expressions may be expressed differently by different people, inaccurate results are unavoidable. Nerve and Physiological responses are incontrollable native response. Physiological responses and the corresponding signals are difficult to control when a person is overcome with emotion. Therefore, an emotion recognition system that considers physiological signals is proposed in this paper. An emotion induction experiment was performed to collect five physiological signals from subjects, namely electrocardiogram, respiration, galvanic skin response (GSR), blood volume pulse, and pulse. Support vector regression (SVR) was used to train three trend curves of three emotions (sadness, fear, and pleasure). Experimental results show that the proposed method has a high recognition rate of 90.6%.
AB - Cases of physical and mental diseases caused by stress and negative emotions have increased annually. Many emotion recognition methods have been proposed. Facial expression is widely used for emotion recognition. However, since facial expressions may be expressed differently by different people, inaccurate results are unavoidable. Nerve and Physiological responses are incontrollable native response. Physiological responses and the corresponding signals are difficult to control when a person is overcome with emotion. Therefore, an emotion recognition system that considers physiological signals is proposed in this paper. An emotion induction experiment was performed to collect five physiological signals from subjects, namely electrocardiogram, respiration, galvanic skin response (GSR), blood volume pulse, and pulse. Support vector regression (SVR) was used to train three trend curves of three emotions (sadness, fear, and pleasure). Experimental results show that the proposed method has a high recognition rate of 90.6%.
UR - http://www.scopus.com/inward/record.url?scp=79851469190&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=79851469190&partnerID=8YFLogxK
U2 - 10.1109/COMPSYM.2010.5685532
DO - 10.1109/COMPSYM.2010.5685532
M3 - Conference contribution
AN - SCOPUS:79851469190
SN - 9781424476404
T3 - ICS 2010 - International Computer Symposium
SP - 12
EP - 17
BT - ICS 2010 - International Computer Symposium
ER -