Emotion Classification through Nonlinear EEG Analysis Using Machine Learning Methods
International Clinical Neuroscience Journal,
Vol. 5 No. 4 (2018),
,
Page 135-149
Abstract
Background: Emotion recognition, as a subset of affective computing, has received considerable attention in recent years. Emotions are key to human-computer interactions. Electroencephalogram (EEG) is considered a valuable physiological source of information for classifying emotions. However, it has complex and chaotic behavior.
Methods: In this study, an attempt is made to extract important nonlinear features from EEGs with the aim of emotion recognition. We also take advantage of machine learning methods such as evolutionary feature selection methods and committee machines to enhance the classification performance. Classification performed concerning both arousal and valence factors.
Results: Results suggest that the proposed method is successful and comparable to the previous works. A recognition rate equal to 90% achieved, and the most significant features reported. We apply the final classification scheme to 2 different databases including our recorded EEGs and a benchmark dataset to evaluate the suggested approach.
Conclusion: Our findings approve of the effectiveness of using nonlinear features and a combination of classifiers. Results are also discussed from different points of view to understand brain dynamics better while emotion changes. This study reveals useful insights about emotion classification and brain-behavior related to emotion elicitation.
- Emotion Recognition
- Phase Space Reconstruction
- Nonlinear EEG Analysis
- Committee Machine
- Evolutionary Feature Selection Methods
How to Cite
References
Zheng WL, Zhu JY, Lu BL. Identifying stable patterns over time for emotion recognition from EEG. IEEE Transactions on Affective Computing. 2017 Jun 5.
Shahnaz C, Hasan SS. Emotion recognition based on wavelet analysis of Empirical Mode Decomposed EEG signals responsive to music videos. InRegion 10 Conference (TENCON), 2016 IEEE 2016 Nov 22, Singapore, Singapore. IEEE. 424-427
Mauss IB, Robinson MD. Measures of emotion: A review. Cognition and emotion. 2009 Feb 1;23(2):209-37.
James W. What is an emotion?. Mind. 1884 Apr 1;9(34):188-205.
Zheng W. Multichannel EEG-based emotion recognition via group sparse canonical correlation analysis. IEEE Transactions on Cognitive and Developmental Systems. 2017 Sep;9(3):281-90.
Jatupaiboon N, Pan-ngum S, Israsena P. Real-time EEG-based happiness detection system. The Scientific World Journal. 2013;2013.
Zheng WL, Lu BL. Investigating critical frequency bands and channels for EEG-based emotion recognition with deep neural networks. IEEE Transactions on Autonomous Mental Development. 2015 Sep;7(3):162-75.
Hoseingholizade S, Golpaygani MR, Monfared AS. Studying emotion through nonlinear processing of EEG. Procedia-Social and Behavioral Sciences. 2012 Jan 1;32:163-9.
Jafari S, Sprott JC, Golpayegani SM. Layla and Majnun: a complex love story. Nonlinear Dynamics. 2016 Jan 1;83(1-2):615-22.
Xu T, Zhou Y, Wang Z, Peng Y. Learning Emotions EEG-based Recognition and Brain Activity: A Survey Study on BCI for Intelligent Tutoring System. Procedia Computer Science. 2018 Dec 31;130:376-82.
Alarcao SM, Fonseca MJ. Emotions recognition using EEG signals: A survey. IEEE Transactions on Affective Computing. 2017 Jun 12.IEEE.
Soroush MZ, Maghooli K, Setarehdan SK, Nasrabadi AM. A Review on EEG Signals Based Emotion Recognition. International Clinical Neuroscience Journal.2017;4(4):118-29.
Yuvaraj R, Murugappan M, Ibrahim NM, Sundaraj K, Omar MI, Mohamad K, Palaniappan R. Detection of emotions in Parkinson's disease using higher order spectral features from brain's electrical activity. Biomedical Signal Processing and Control. 2014 Nov 1;14:108-16.
McCarthy RA, Warrington EK. Cognitive neuropsychology: A clinical introduction. Academic press.San Diego. 2013 Oct 22.
Stam CJ, Pijn JP, Suffczynski P, Da Silva FL. Dynamics of the human alpha rhythm: evidence for non-linearity?. Clinical Neurophysiology. 1999 Oct 1;110(10):1801-13.
Gao J, Hu J, Tung WW. Facilitating joint chaos and fractal analysis of biosignals through nonlinear adaptive filtering. PloS one. 2011 Sep 6;6(9):e24331.
Balli T, Palaniappan R. Classification of biological signals using linear and nonlinear features. Physiological measurement. 2010 May 26;31(7):903-20.
Chua KC, Chandran V, Acharya UR, Lim CM. Application of higher order spectra to identify epileptic EEG. Journal of medical systems. 2011 Dec 1;35(6):1563-71.
Shen M, Chan FH, Sun L, Beadle PJ. Parametric bispectral estimation of EEG signals in different functional states of the brain. IEE Proceedings-Science, Measurement and Technology. 2000 Nov;147(6):374-7.
. Jenke R, Peer A, Buss M. Feature extraction and selection for emotion recognition from EEG. IEEE Transactions on Affective Computing. 2014 Jul 1;5(3):327-39.
Valenza G, Lanata A, Scilingo EP. The role of nonlinear dynamics in affective valence and arousal recognition. IEEE transactions on affective computing. 2012 Apr;3(2):237-49.
Alcaraz R, García-Martínez B, Zangróniz R, Martínez-Rodrigo A. Recent Advances and Challenges in Nonlinear Characterization of Brain Dynamics for Automatic Recognition of Emotional States. InInternational Work-Conference on the Interplay Between Natural and Artificial Computation 2017 Jun 19.Springer, Cham.213-222.
García-Martínez B, Martínez-Rodrigo A, Alcaraz R, Fernández-Caballero A, González P. Nonlinear Methodologies Applied to Automatic Recognition of Emotions: An EEG Review. InInternational Conference on Ubiquitous Computing and Ambient Intelligence 2017 Nov 7. Springer, Cham. 754-765.
Soroush MZ, Maghooli K, Soroush PZ, Tahvilian P, Bagherzadeh S. EEG-Based Emotion Recognition through Nonlinear Analysis.2018;7(78):62-9.
Soroush MZ, Maghooli K, Setarehdan SK, Nasrabadi AM. A novel method of eeg-based emotion recognition using nonlinear features variability and Dempster–Shafer theory. Biomedical Engineering: Applications, Basis and Communications. 2018 Aug 27;30(04):1850026.
Hatamikia S, Nasrabadi AM. Recognition of emotional states induced by music videos based on nonlinear feature extraction and som classification. InBiomedical Engineering (ICBME), 2014 21th Iranian Conference on 2014 Nov 26 . IEEE. 333-337.
Yuvaraj R, Murugappan M, Ibrahim NM, Sundaraj K, Omar MI, Mohamad K, Palaniappan R. Optimal set of EEG features for emotional state classification and trajectory visualization in Parkinson's disease. International Journal of Psychophysiology. 2014 Dec 1;94(3):482-95.
Khalili Z, Moradi MH. Emotion recognition system using brain and peripheral signals: using correlation dimension to improve the results of EEG. InNeural Networks, 2009. IJCNN 2009. International Joint Conference on 2009 Jun 14. IEEE. 1571-1575.
Wang XW, Nie D, Lu BL. Emotional state classification from EEG data using machine learning approach. Neurocomputing. 2014 Apr 10;129:94-106.
Jie X, Cao R, Li L. Emotion recognition based on the sample entropy of EEG. Bio-medical materials and engineering. 2014 Jan 1;24(1):1185-92.
Hosseinifard B, Moradi MH, Rostami R. Classifying depression patients and normal subjects using machine learning techniques and nonlinear features from EEG signal. Computer methods and programs in biomedicine. 2013 Mar 1;109(3):339-45.
Murugappan M, Nagarajan R, Yaacob S. Combining spatial filtering and wavelet transform for classifying human emotions using EEG Signals. Journal of Medical and Biological Engineering. 2011 Feb 1;31(1):45-51.
Sourina O, Liu Y. A Fractal-based Algorithm of Emotion Recognition from EEG using Arousal-Valence Model.In: Proceeding of the International Conference on Bio-Inspired Systems and Signal Processing, 2011 Jan 26; 209-214.
Chen DW, Han N, Chen JJ, Guo H. Novel algorithm for measuring the complexity of electroencephalographic signals in emotion recognition. Journal of Medical Imaging and Health Informatics. 2017 Feb 1;7(1):203-10.
Lan Z, Sourina O, Wang L, Liu Y. Real-time EEG-based emotion monitoring using stable features. The Visual Computer. 2016 Mar 1;32(3):347-58.
Liu Y, Sourina O. EEG-based subject-dependent emotion recognition algorithm using fractal dimension. InSystems, Man and Cybernetics (SMC), 2014 IEEE International Conference on 2014 Oct 5. IEEE. 3166-3171.
Natarajan K, Acharya R, Alias F, Tiboleng T, Puthusserypady SK. Nonlinear analysis of EEG signals at different mental states. BioMedical Engineering OnLine. 2004 Dec;3(1):7.
Maity AK, Pratihar R, Mitra A, Dey S, Agrawal V, Sanyal S, Banerjee A, Sengupta R, Ghosh D. Multifractal detrended fluctuation analysis of alpha and theta EEG rhythms with musical stimuli. Chaos, Solitons & Fractals. 2015 Dec 1;81:52-67.
Bahari F, Janghorbani A. Eeg-based emotion recognition using recurrence plot analysis and k nearest neighbor classifier. InBiomedical Engineering (ICBME), 2013 20th Iranian Conference on 2013 Dec 18. IEEE.228-233.
Zhuang N, Zeng Y, Tong L, Zhang C, Zhang H, Yan B. Emotion recognition from EEG signals using multidimensional information in EMD domain. BioMed research international. 2017;2017.
Li Y, Huang J, Zhou H, Zhong N. Human Emotion Recognition with Electroencephalographic Multidimensional Features by Hybrid Deep Neural Networks. Applied Sciences. 2017 Oct 13;7(10):1060.
Ang AQ, Yeong YQ, Wee W. Emotion Classification from EEG Signals Using Time-Frequency-DWT Features and ANN. Journal of Computer and Communications. 2017 Mar 8;5(03):75.
Mangala Gowri SG, Cyril Prasanna Raj P. Energy density feature extraction using different wavelets for emotion detection. Int J Appl Eng Res. 2018;13(1):520–7.
Eysenck SB, Eysenck HJ, Barrett P. A revised version of the psychoticism scale. Personality and individual differences. 1985 Jan 1;6(1):21-9.
Morris JD. Observations: SAM: the Self-Assessment Manikin; an efficient cross-cultural measurement of emotional response. Journal of advertising research. 1995 Nov 1;35(6):63-8.
Delorme A, Makeig S. EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis. Journal of neuroscience methods. 2004 Mar 15;134(1):9-21.
Sai CY, Mokhtar N, Arof H, Cumming P, Iwahashi M. Automated Classification and Removal of EEG Artifacts With SVM and Wavelet-ICA. IEEE journal of biomedical and health informatics. 2018 May;22(3):664-70.
Cao K, Guo Y, Su SW. A review of motion related EEG artifact removal techniques. InSensing Technology (ICST), 2015 9th International Conference on 2015 Dec 8. IEEE. 600-604.
Rahman FA, Othman MF, Shaharuddin NA. A review on the current state of artifact removal methods for electroencephalogram signals. InControl Conference (ASCC), 2015 10th Asian 2015 May 31. IEEE. 1-6.
Islam MK, Rastegarnia A, Yang Z. Methods for artifact detection and removal from scalp EEG: a review. Neurophysiologie Clinique/Clinical Neurophysiology. 2016 Nov 1;46(4-5):287-305.
Abdullah AK, Zhu ZC. Blind Source Separation Based of Brain Computer Interface System: A review. Research Journal of Applied Sciences, Engineering and Technology. 2014 Jan 20;7(3):484-94.
Vázquez RR, Velez-Perez H, Ranta R, Dorr VL, Maquin D, Maillard L. Blind source separation, wavelet denoising and discriminant analysis for EEG artefacts and noise cancelling. Biomedical Signal Processing and Control. 2012 Jul 1;7(4):389-400.
Klemm M, Haueisen J, Ivanova G. Independent component analysis: comparison of algorithms for the investigation of surface electrical brain activity. Medical & biological engineering & computing. 2009 Apr 1;47(4):413-23.
Vorobyov S, Cichocki A. Blind noise reduction for multisensory signals using ICA and subspace filtering, with application to EEG analysis. Biological Cybernetics. 2002 Apr 1;86(4):293-303.
Ng SC, Raveendran P. Enhanced Rhythm Extraction Using Blind Source Separation and Wavelet Transform. IEEE Transactions on Biomedical Engineering. 2009 Aug;56(8):2024-34.
Sweeney KT, McLoone SF, Ward TE. The use of ensemble empirical mode decomposition with canonical correlation analysis as a novel artifact removal technique. IEEE transactions on biomedical engineering. 2013;60(1):97-105.
Castellanos NP, Makarov VA. Recovering EEG brain signals: artifact suppression with wavelet enhanced independent component analysis. Journal of neuroscience methods. 2006 Dec 15;158(2):300-12.
Hamaneh MB, Chitravas N, Kaiboriboon K, Lhatoo SD, Loparo KA. Automated removal of EKG artifact from EEG data using independent component analysis and continuous wavelet transformation. IEEE Transactions on Biomedical Engineering. 2014 Jun;61(6):1634-41.
Coifman RR, Donoho DL. Translation-invariant de-noising. InWavelets and statistics 1995. Springer, New York, NY. 125-150.
Akhtar MT, Mitsuhashi W, James CJ. Employing spatially constrained ICA and wavelet denoising, for automatic removal of artifacts from multichannel EEG data. Signal processing. 2012 Feb 1;92(2):401-16.
Kennel MB, Brown R, Abarbanel HD. Determining embedding dimension for phase-space reconstruction using a geometrical construction. Physical review A. 1992 Mar 1;45(6):3403.
Fraser AM, Swinney HL. Independent coordinates for strange attractors from mutual information. Physical review A. 1986 Feb 1;33(2):1134.
Atkinson J, Campos D. Improving BCI-based emotion recognition by combining EEG feature selection and kernel classifiers. Expert Systems with Applications. 2016 Apr 1;47:35-41.
Shayegh F, Sadri S, Amirfattahi R, Ansari-Asl K. A model-based method for computation of correlation dimension, Lyapunov exponents and synchronization from depth-EEG signals. Computer methods and programs in biomedicine. 2014 Jan 1;113(1):323-37.
Naji M, Firoozabadi M, Azadfallah P. Classification of music-induced emotions based on information fusion of forehead biosignals and electrocardiogram. Cognitive Computation. 2014 Jun 1;6(2):241-52.
Marwan N, Romano MC, Thiel M, Kurths J. Recurrence plots for the analysis of complex systems. Physics reports. 2007 Jan 1;438(5-6):237-329.
Zbilut JP, Webber Jr CL. Embeddings and delays as derived from quantification of recurrence plots. Physics letters A. 1992 Dec 7;171(3-4):199-203.
Webber Jr CL, Zbilut JP. Dynamical assessment of physiological systems and states using recurrence plot strategies. Journal of applied physiology. 1994 Feb 1;76(2):965-73.
Guo R, Wang Y, Yan J, Yan H. Recurrence quantification analysis on pulse morphological changes in patients with coronary heart disease. Journal of Traditional Chinese Medicine. 2012 Dec 1;32(4):571-7.
Liu W, Zheng WL, Lu BL. Multimodal emotion recognition using multimodal deep learning. arXiv preprint arXiv:1602.08225. 2016 Feb 26.
Sharma R, Pachori RB, Acharya UR. Application of entropy measures on intrinsic mode functions for the automated identification of focal electroencephalogram signals. Entropy. 2015 Feb 3;17(2):669-91.
Pincus SM. Approximate entropy as a measure of system complexity. Proceedings of the National Academy of Sciences. 1991 Mar 15;88(6):2297-301.
Peng CK, Havlin S, Stanley HE, Goldberger AL. Quantification of scaling exponents and crossover phenomena in nonstationary heartbeat time series. Chaos: An Interdisciplinary Journal of Nonlinear Science. 1995 Mar;5(1):82-7.
Soroush MZ, Maghooli K, Setarehdan SK, Nasrabadi AM. A novel method of eeg-based emotion recognition using nonlinear features variability and Dempster–Shafer theory. Biomedical Engineering: Applications, Basis and Communications. 2018 Aug 27;30(04):1850026.
Yang J, Honavar V. Feature subset selection using a genetic algorithm. InFeature extraction, construction and selection 1998 (pp. 117-136). Springer, Boston, MA.
Shi Y, Eberhart R. A modified particle swarm optimizer. InEvolutionary Computation Proceedings, 1998. IEEE World Congress on Computational Intelligence., The 1998 IEEE International Conference on 1998 May 4. IEEE. 69-73.
Lim CP, Jain LC. Advances in swarm intelligence. InInnovations in Swarm Intelligence 2009. Springer, Berlin, Heidelberg. 1-7
Lee K, Joo J, Yang J, Honavar V. Experimental comparison of feature subset selection using GA and ACO algorithm. InInternational Conference on Advanced Data Mining and Applications 2006 Aug 14. Springer, Berlin, Heidelberg. 465-472
Morvant E, Habrard A, Ayache S. Majority vote of diverse classifiers for late fusion. InJoint IAPR International Workshops on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Pattern Recognition (SSPR) 2014 Aug 20. Springer, Berlin, Heidelberg. 153-162.
Koelstra S, Muhl C, Soleymani M, Lee JS, Yazdani A, Ebrahimi T, Pun T, Nijholt A, Patras I. Deap: A database for emotion analysis; using physiological signals. IEEE Transactions on Affective Computing. 2012 Jan;3(1):18-31.
- Abstract Viewed: 2303 times
- PDF Downloaded: 1219 times