Based on support vector regression for emotion recognition using physiological signals

Chuan Yu Chang, Jun Ying Zheng, Chi-Jen Wang

研究成果: Conference contribution

13 引文 (Scopus)

摘要

Facial expression are widely used for emotion recognition. Facial expressions may be expressed differently by different people subjectively, inaccurate results are unavoidable. Nevertheless, physiological reactions are non-autonomic nerves in physiology. The physiological reactions and the corresponding signals are hardly to control while emotions are excited. Therefore, an emotion recognition system with consideration of physiological signals is proposed in this paper. A specific designed mood induction experiment is performed to collect physiological signals of subjects. Five biosensors including electrocardiogram, respiration, galvanic skin responses (GSR), blood volume pulse, and pulse are used. Then a Support Vector Regression (SVR) is used to train three regression curves of three emotions (sad, fear, and pleasure). Experimental results show that the proposed method based on SVR emotion recognition has a good performance in accuracy.

原文English
主出版物標題2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010
DOIs
出版狀態Published - 2010 十二月 1
事件2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010 - Barcelona, Spain
持續時間: 2010 七月 182010 七月 23

出版系列

名字Proceedings of the International Joint Conference on Neural Networks

Other

Other2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010
國家Spain
城市Barcelona
期間10-07-1810-07-23

指紋

Physiology
Electrocardiography
Biosensors
Skin
Blood
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

引用此文

Chang, C. Y., Zheng, J. Y., & Wang, C-J. (2010). Based on support vector regression for emotion recognition using physiological signals. 於 2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010 [5596878] (Proceedings of the International Joint Conference on Neural Networks). https://doi.org/10.1109/IJCNN.2010.5596878
Chang, Chuan Yu ; Zheng, Jun Ying ; Wang, Chi-Jen. / Based on support vector regression for emotion recognition using physiological signals. 2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010. 2010. (Proceedings of the International Joint Conference on Neural Networks).
@inproceedings{ac562b47dc054f9cac85340f4f80617b,
title = "Based on support vector regression for emotion recognition using physiological signals",
abstract = "Facial expression are widely used for emotion recognition. Facial expressions may be expressed differently by different people subjectively, inaccurate results are unavoidable. Nevertheless, physiological reactions are non-autonomic nerves in physiology. The physiological reactions and the corresponding signals are hardly to control while emotions are excited. Therefore, an emotion recognition system with consideration of physiological signals is proposed in this paper. A specific designed mood induction experiment is performed to collect physiological signals of subjects. Five biosensors including electrocardiogram, respiration, galvanic skin responses (GSR), blood volume pulse, and pulse are used. Then a Support Vector Regression (SVR) is used to train three regression curves of three emotions (sad, fear, and pleasure). Experimental results show that the proposed method based on SVR emotion recognition has a good performance in accuracy.",
author = "Chang, {Chuan Yu} and Zheng, {Jun Ying} and Chi-Jen Wang",
year = "2010",
month = "12",
day = "1",
doi = "10.1109/IJCNN.2010.5596878",
language = "English",
isbn = "9781424469178",
series = "Proceedings of the International Joint Conference on Neural Networks",
booktitle = "2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010",

}

Chang, CY, Zheng, JY & Wang, C-J 2010, Based on support vector regression for emotion recognition using physiological signals. 於 2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010., 5596878, Proceedings of the International Joint Conference on Neural Networks, 2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010, Barcelona, Spain, 10-07-18. https://doi.org/10.1109/IJCNN.2010.5596878

Based on support vector regression for emotion recognition using physiological signals. / Chang, Chuan Yu; Zheng, Jun Ying; Wang, Chi-Jen.

2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010. 2010. 5596878 (Proceedings of the International Joint Conference on Neural Networks).

研究成果: Conference contribution

TY - GEN

T1 - Based on support vector regression for emotion recognition using physiological signals

AU - Chang, Chuan Yu

AU - Zheng, Jun Ying

AU - Wang, Chi-Jen

PY - 2010/12/1

Y1 - 2010/12/1

N2 - Facial expression are widely used for emotion recognition. Facial expressions may be expressed differently by different people subjectively, inaccurate results are unavoidable. Nevertheless, physiological reactions are non-autonomic nerves in physiology. The physiological reactions and the corresponding signals are hardly to control while emotions are excited. Therefore, an emotion recognition system with consideration of physiological signals is proposed in this paper. A specific designed mood induction experiment is performed to collect physiological signals of subjects. Five biosensors including electrocardiogram, respiration, galvanic skin responses (GSR), blood volume pulse, and pulse are used. Then a Support Vector Regression (SVR) is used to train three regression curves of three emotions (sad, fear, and pleasure). Experimental results show that the proposed method based on SVR emotion recognition has a good performance in accuracy.

AB - Facial expression are widely used for emotion recognition. Facial expressions may be expressed differently by different people subjectively, inaccurate results are unavoidable. Nevertheless, physiological reactions are non-autonomic nerves in physiology. The physiological reactions and the corresponding signals are hardly to control while emotions are excited. Therefore, an emotion recognition system with consideration of physiological signals is proposed in this paper. A specific designed mood induction experiment is performed to collect physiological signals of subjects. Five biosensors including electrocardiogram, respiration, galvanic skin responses (GSR), blood volume pulse, and pulse are used. Then a Support Vector Regression (SVR) is used to train three regression curves of three emotions (sad, fear, and pleasure). Experimental results show that the proposed method based on SVR emotion recognition has a good performance in accuracy.

UR - http://www.scopus.com/inward/record.url?scp=79959420875&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79959420875&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2010.5596878

DO - 10.1109/IJCNN.2010.5596878

M3 - Conference contribution

AN - SCOPUS:79959420875

SN - 9781424469178

T3 - Proceedings of the International Joint Conference on Neural Networks

BT - 2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010

ER -

Chang CY, Zheng JY, Wang C-J. Based on support vector regression for emotion recognition using physiological signals. 於 2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010. 2010. 5596878. (Proceedings of the International Joint Conference on Neural Networks). https://doi.org/10.1109/IJCNN.2010.5596878