The emotion recognition for grief based on nonlinear features of GSR

被引：0

作者：

Wang, Linwei ^{[1
]}

Liu, Guangyuan ^{[1
]}

Yang, Zhaofang ^{[2
]}

机构：

[1] School of Electronic and Information Engineering, Southwest University

[2] School of Computer and Information Science, Southwest University

来源：

Journal of Computational Information Systems | 2014年 / 10卷 / 04期

关键词：

Approximate entropy; Correlation dimension; Emotion recognition; Galvanic skin response; Method of surrogate data; The largest lyapunov exponent;

D O I：

10.12733/jcis9466

中图分类号：

学科分类号：

摘要：

The emotion recognition of the nonlinear physiological signal was discussed in this paper. The authors used induced material which was cut from four video clips to evoke four emotions: happy, grief, anger and fear, then collected some Galvanic Skin Response (GSR) of the four emotions from health subjects. A deterministic nonlinear of the GSR was verified by the method of surrogate data, then the relationship between the largest lyapunov exponent, correlation dimension, approximate entropy (ApEn) and the embedded dimensional, time delay were analyzed to find some law of the GSR. These nonlinear characteristics were used as effective features to distinguish emotions by using SVM classifier, and the experimental results indicate that the grief emotion could be recognized clearly by the nonlinear method. The best correct-classification ratio about grief emotion based on GSR signal could reach 80.31%. © 2014 Binary Information Press.

引用

页码：1639 / 1649

页数：10

共 19 条

[1]

Helmut P., Junichiro M., Mitsuru I., Using human physiology to evaluate subtle expressivity of a virtual quizmaster in a mathematical game, International Journal of Human-computer Studies, 62, 2, pp. 231-245, (2005)

[2]

Kim J., Andre E., Emotion recognition based on physiological changes in music listening, IEEE Transactions on Pattern Analysis and Machine Intelligence, 30, 12, pp. 2067-2083, (2008)

[3]

Wu G.-H., Liu G.-Y., The analysis of emotion recognition from GSR based on PSO, International Symposium on Intelligence Information Processing and Trusted Computing, pp. 28-29, (2010)

[4]

Zhang H., Liu G., Research of emotion recognition based on pulse signal, Proceedings of IEEE International Conference on Advanced Computer Theory and Engineering, 3, 8, pp. 506-509, (2010)

[5]

Rajendra Acharya U., Faust O., Kannathal N., Non-linear analysis of EEG signals at various sleep stages, Computer Methods and Programs in Biomedicine, 80, pp. 37-45, (2005)

[6]

Beyli E.D., Recurrent neural networks employing Lyapunov exponents for analysis of ECG signals, Expert Systems with Applications, 37, pp. 1192-1199, (2010)

[7]

Lang P.J., Emotion and motivation: Attention, perception, and action, Journal of Sport and Exercise Psychology, 22, pp. 122-140, (2000)

[8]

Wang X.-Y., Nonlinear dynamics research on the canine hearts in PHCA process, Chinese Journal of Computational Mechanics, 22, 4, pp. 470-476, (2005)

[9]

Coan J.A., Allen J.J.B., Handbook of Emotion Elicitation and Assessment, (2007)

[10]

Wen W.H., Qiu Y.H., Liu G.Y., Cheng N.P., Huang X.T., Construction and cross-correlation analysis of the affective physiological response database, Science China: Information Sciences, 53, 9, pp. 1774-1784, (2010)

← 1 2 →