Abstract
In order to improve the emotion recognition rate, this paper proposes an electroencephalograph (EEG) emotion recognition model using a library for support vector machine (LIBSVM) as the classifier. In this paper, we collected EEG signals from 10 volunteers along with the participants’ self-assessment of their affective state after each stimulus, in terms of Valence and arousal. After these signals are filtered, we calculate the features of Lempel-Ziv complexity, wavelet detail coefficient, and the co-integration relationship degree first. At the same time, EMD is carried out to calculate the average approximate entropy of the first four Intrinsic Mode Functions (IMFs). At last, all the features extracted will input into the LIBSVM for training and testing, and complete emotion recognition. In this paper, two classifications are carried out on the two dimensions of Valence and Arousal, respectively. The experimental results show that the average emotional recognition rate is 83.64% and 75.11%, respectively, which proves that the proposed scheme has a certain feasibility.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Y. Lee, W. Han, Y. Kim, Emotional recognition from facial expression analysis using Bezier curve fitting, in 2013 16th International Conference on Network-Based Information Systems (2013)
M. Ogino, Y. Mitsukura, An EEG-based robot arm control to express human emotions, in 2018 IEEE 15th International Workshop on Advanced Motion Control (AMC) (2018)
B. Fang, Q. Zhang, H. Wang, X. Yuan, Personality driven task allocation for emotional robot team. Int. J. Mach. Learn. Cybernet. 9(12), 1955–1962 (2018)
Y. Kim, Y. Shin, S. Kim, E. Kim, H. Shin, Emotion-based image retrieval, in International Conference on Consumer Electronics (IEEE) (2009)
T. Chen, S. Ju, X. Yuan, M. Elhoseny, F. Ren, M. Fan, Z. Chen, Emotion recognition using empirical mode decomposition and approximation entropy. Comput. Electric. Eng. 72, 383–392 (2018)
V. Bajaj, R.B. Pachori, Detection of human emotions using features based on the multiwavelet transform of EEG signals, in Brain-Computer Interfaces (Springer International Publishing, Cham, 2015), pp. 215–240
P. Ekman, Contacts across cultures in the face and emotion. J. Pers. Soc. Psychol. 17(2), 124–129 (1971)
J.A. Russell, A circumplex model of affect. J. Personal. Soc. Psychol. 39(6), 1161 (1980)
M.M. Branley, P.J. Lang, Measuring emotion: the self-assessment manikin and the semantic differential. J. Behav. Therapy Exp. Psychiatr. 25(1), 49–59 (1994)
Z. Wen, R. Xu, J. Du, A novel convolutional neural networks for emotion recognition based on EEG signal, in 2017 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC) (2017)
W.L. Zheng , B.L. Lu, Investigating critical frequency bands and channels for EEG-based emotion recognition with deep neural networks. IEEE Trans. Autonom. Mental Develop. 7(3), 1–1 (2015)
A.E. Putra, C. Atmaji, F. Ghaleb, EEG-based emotion classification using wavelet decomposition and K-nearest neighbor, in 2018 4th International Conference on Science and Technology (ICST) (2018)
D. Huang, S. Zhang, Y. Zhang, EEG-based emotion recognition using empirical wavelet transform, in 2017 4th International Conference on Systems and Informatics (ICSAI) (2017)
Y. Wang, N. Wang, Y. Li, H. Li, J. Wang, Abnormal sensory gating in schizophrenia: the evidence from Lempel-Ziv complexity analysis in EEG, in International Conference on Biomedical Engineering & Informatics (IEEE, New York, 2011)
C.W. Granger, Investigating casual relations by econometric model and cross-spectral model. Econometrica 37, 424–438 (1969)
M. Wu, Y. Wang, A feature selection algorithm of music genre classification based on ReliefF and SFS, in IEEE/ACIS International Conference on Computer & Information Science (IEEE, New York, 2015)
C.-C. Chang , C.-J. Lin, LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2(3), 27:1–27:27 (2011)
S. Pincus, Approximate entropy (ApEn) as a complexity measure. Chaos Interdiscipl. J. Nonlinear Sci. 5(1), 110–C17 (1995)
L. Li, W. Chen, X. Shao, Z. Wang, Analysis of amplitude-integrated EEG in the newborn based on approximate entropy. IEEE Trans. Biomed. Eng. 57(10), 2459–C66 (2010)
P.C. Petrantonakis, L.J. Hadjileontiadis, Adaptive emotional information retrieval from EEG signals in the time-frequency domain. IEEE Trans. Sig. Proc. 60(5), 2604–2616 (2012)
F. Zhang, H. Meng, M. Li, Emotion extraction and recognition from music, in International Conference on Natural Computation (IEEE, New York, 2016)
Y. Zhu, S. Wang, Q. Ji, Emotion recognition from users’ EEG signals with the help of stimulus VIDEOS, in IEEE International Conference on Multimedia & Expo (IEEE, New York, 2014)
O. Xie, Z.T. Liu, X.W. Ding, Electroencephalogram emotion recognition based on a stacking classification model, in 2018 37th Chinese Control Conference (CCC) (2018), pp. 5544–5548
Acknowledgements
This work supported by The Key Program of the National Natural Science Foundation of China (Grant No. 61432004); The National Natural Science Foundation of China (Grant No. 61474035, 61502140); The fund of Affective Computing and Advanced Intelligent Machine Anhui Province Key Laboratory (Grant No. ACAIM180101); NSFC-Shenzhen Joint Foundation (Key Project) (Grant No. U1613217).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Chen, T., Ju, S., Ren, F., Fan, M., An, X. (2020). Emotion Recognition Based on EEG Signals Using LIBSVM as the Classifier. In: Yuan, X., Elhoseny, M. (eds) Urban Intelligence and Applications. Studies in Distributed Intelligence . Springer, Cham. https://doi.org/10.1007/978-3-030-45099-1_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-45099-1_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-45098-4
Online ISBN: 978-3-030-45099-1
eBook Packages: Computer ScienceComputer Science (R0)