Abstract
Communication between human and computer is highly demandable in different applications. Possessing of cognitive skills of a human for human-computer interaction (HCI) is a non-trivial task. Classification of human emotion involving artificial intelligence is an emerging field. HCI finds applications in smart home, industry, personal health and for different purposes. One such HCI task is an automated human emotion recognition system. In this paper, new human emotion classification method based on Electroencephalogram (EEG) signal is proposed that leverages singular value decomposition (SVD) and Multivariate SynchroSqueezing Transform (MSST). Highly random, non-stationary EEG signal illustrates the electrical activity of the brain and contains useful information. To extract the hidden information/features, Multivariate SynchroSqueezing Transform is exploited. It is an adaptive, invertible transform to improve the quality of the time-frequency representation (TFR) by considering it along the frequency axis. Selected channels of EEG signal are decomposed by Multivariate SynchroSqueezing Transform to capture the frequency components and its amplitudes at any specific time slot. Then, singular value of the matrix is extracted by SVD as the feature vector. Then the most contributing features are selected using AdaBoost ensemble of decision tree classifiers which also leads to a reduction in feature dimensionality. And this reduced feature model acts as input to AdaBoost classifier in One against All (OAA) strategy to discriminate the emotional states in both two dimensional and three-dimensional model comprising Valence, Arousal and Dominance. Experimental results on DEAP dataset show that the proposed method yields classification accuracy of 97% for 2D emotional model and gives better performance than the state-of-art systems by nearly 7%.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
R. Plutchik, Emotion: A Psycho Evolutionary Synthesis (Harper and Row, New York, 1980)
P. Ekman, W.V. Friesen, M. O’Sullivan, A. Chan, I. Diacoyanni-Tarlatzis, K. Heider, P.E. Ricci-Bitti, Universals and cultural differences in the judgments of facial expressions of emotion. J. Pers. Soc. 53(4), 712–717 (1987)
A. Mert, A. Akan, Emotion recognition from EEG signals by using multivariate empirical mode decomposition. Pattern Anal. Appl. 81–89 (2018)
A.G. Aguinaga, A.L. Ramirez, M.R.B. Flores, Classification model of arousal and valence mental states by EEG signals analysis and Brodmann correlations. Int. J. Adv. Comput. Sci. Appl. 6(6) (2015)
Y. Liu, O. Sourina, EEG-based dominance level recognition for emotion-enabled interaction, in IEEE International Conference on Multimedia and Expo (2012)
Y. Liu, O. Sourina, EEG databases for emotion recognition, in International Conference on Cyberworlds (2013)
Y. Liu, O. Sourina, Real time fractal based valence level recognition from EEG. Trans. Comput. Sci. 101–120 (2013)
Y. Liu, O. Sourina, EEG-based subject dependent emotion recognition algorithm using fractal dimension, in IEEE International Conference on Systems, Man, and Cybernetics (2014)
Y. Liu, O. Sourina, M.R. Hafiyyandi, EEG-based emotion-adaptive advertising, in Humaine Association Conference on Affective Computing and Intelligent Interaction (2013)
S. Walter, J. Kim, D. Hrabal, S.C. Crawcour, H. Kessler, H.C. Traue, Transsituational individual-specific biopsychological classification of emotions. IEEE Trans. Syst. Man Cybern. Syst. 43(4) (2013)
Z. Guendil, Z. Lachiri, C. Maaoui, Computational framework for emotional VAD prediction using regularized Extreme Learning Machine. Int. J. Multimed. Inf. Retr. 6(3), 251–261 (2017)
G.K. Verma, U.S. Tiwary, Multimodal fusion framework: a multiresolution approach for emotion classification and recognition from physiological signals. NeuroImage 102, 162–172 (2014)
G.K. Verma, U.S. Tiwary, Affect representation and recognition in 3D continuous valence-arousal-dominance space. Multimed. Tools Appl. 1–25 (2016)
N.E. Huang, Z. Shen, S.R. Long, M.C. Wu, H.H. Shih, Q. Zheng, N.C. Yen, The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series anaylsis. Proc. R. Soc. Lond. 454, 903–995 (1998)
D. Ur Rehman, D.P. Mandic, Filter bank property of multivariate empirical mode decomposition. IEEE Trans. Signal Process. 59, 2421–2426 (2011)
A. Khasnobish, S. Bhattacharya, G. Singh, A. Jati, A. Konar, D.N. Tibarewala, R. Janarthanan, The role of empirical mode decomposition on emotion classification using stimulated EEG signals. Adv. Comput. Inf. Technol. 178, 55–62 (2013)
N. Zhuang, Y. Zeng, L. Tong, C. Zhang, H. Zhang, B. Yan, Emotion recognition from EEG Signals using multidimensional information in EMD domain. Biomed. Res. Int. 2017, 1–9 (2017)
C. Guitton, Emotions Estimation From EEG Recordings (Imperial College of Science, Technology & Medicine, Department of Electrical & Electronic Engineering, London, 2010)
H. Xu, K.N. Plataniotis, Application of multivariate empirical mode decomposition in EEG signals for subject independent affective states classification. Int. J. Commun. 9, 91–97 (2015)
N. Ur Rahman, C. Park, N.E. Huang, D.P. Mandic, EMD via MEMD: multivariate noise aided computation of standard EMD. Adv. Adapt. Data Anal. 5, 1350007, 25 pp (2013)
I. Daubechies, J. Lu, H.T. Wu, Synchrosqueezed wavelet transforms: an empirical mode decomposition like tool. Appl. Comput. Harmon. Anal. 243–261 (2011)
Z. Huang, J. Zhang, T. Zhao, Y. Sun, Synchrosqueezing S-Transform and its application in seismic spectral decomposition. IEEE Trans. Geosci. Remote Sens. 54(2), 817–825 (2016)
H.-T. Wu, Adaptive Analysis of Complex Data Sets (Princeton University, New Jersey, USA, 2019)
A. Ahrabian, D. Looney, L. Stanković, D.P. Mandic, Synchrosqueezing-based time frequency analysis of multivariate data, Signal Process. 331–341 (2015)
J.M. Lilly, S.C. Olhede, Wavelet ridge estimation of jointly modulated multivariate oscillations, in Conference Record of the Forty Third Asilomar Conference on Signals, Systems and Computers (2009)
J.M. Lilly, S.C. Olhede, Analysis of modulated multivariate oscillations. IEEE Trans. Signal Process. 2, 600–612 (2012)
S. Olhede, A.T. Walden, The Hilbert spectrum via wavelet projections. R. Soc. 460(2044), 955–975 (2004)
P. Ozel, A. Akan, B. Yilmaz, Synchrosqueezing transform based feature extraction from EEG signals for emotional state prediction. Biomed. Signal Process. Control 52, 152–161 (2019)
A. Mert, A. Akan, Emotion recognition based on time–frequency distribution of EEG signals using multivariate synchrosqueezing transform. Digit. Signal Process. (In Press)
S. Koelstra, C. Muhl, M. Soleymani, J.-S. Lee, A. Yazdani, T. Ebrahimi et al., Deap: a database for emotion analysis; using physiological signals. IEEE Trans. Affect. Comput. 3, 18–31 (2012)
H.C. Andrews, C.L. Patterson, Singular value decompositions and digital image processing. IEEE Trans. Acoust. Speech Signal Process. ASSP-24, 26–53 (1976)
V. Bolón-Canedo, A. Alonso-Betanzos, Ensembles for feature selection: a review and future trends. Inf. Fusion 52, 1–12 (2019). https://doi.org/10.1016/j.inffus.2018.11.008
X.-C. Yin, K. Huang, H.-W. Hao, DE2: dynamic ensemble of ensembles for learning nonstationary data. Neurocomputing 165, 14–22 (2015). https://doi.org/10.1016/j.neucom.2014.06.092
F. Pedregosa, et al., Scikit-learn: machine learning in python. JMLR 12, 2825–2830 (2011)
V. Bajaj, R.B. Pachori, Detection of human emotions using features based on the multiwavelet transform of EEG signals. Brain Comput. Interfaces 74, 215–240 (2015)
Z. Lan, O. Sourina, L. Wang, Y. Liu, Real-time EEG-based emotion monitoring using stable features. Vis. Comput. 32, 347–358 (2016). https://doi.org/10.1007/s00371-015-1183-y
S. Taran, V. Bajaj, Emotion recognition from single-channel EEG signals using a two-stage correlation and instantaneous frequency-based filtering method. Comput. Methods Programs Biomed. 173, 157–165 (2019). ISSN 0169-2607. https://doi.org/10.1016/j.cmpb.2019.03.015
W.-L. Zheng, A. Cichocki, EmotionMeter: a multimodal framework for recognizing human emotions. IEEE Trans. Cybern. 1–13
D.D. Chakladar, S. Chakraborty, EEG based emotion classification using ‘Correlation Based Subset Selection’. Biol. Inspired Cogn. Archit. 24, 98–106 (2018)
T. Chen et al., Emotion recognition using empirical mode decomposition and approximation entropy. Comput. Electr. Eng. 72, 383–392 (2018)
G.K. Verma, U.S. Tiwary, Affect representations and recognition in 3D continuous valence-arousal-dominance space. Multimed. Tools Appl. 76(2), 2159–2183 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Veena, S.T., Sumaiya, M.N. (2020). Human Emotion Classification Using EEG Signals by Multivariate SynchroSqueezing Transform. In: Hemanth, D. (eds) Human Behaviour Analysis Using Intelligent Systems. Learning and Analytics in Intelligent Systems, vol 6. Springer, Cham. https://doi.org/10.1007/978-3-030-35139-7_9
Download citation
DOI: https://doi.org/10.1007/978-3-030-35139-7_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-35138-0
Online ISBN: 978-3-030-35139-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)