The Role of Empirical Mode Decomposition on Emotion Classification Using Stimulated EEG Signals

  • Anwesha Khasnobish
  • Saugat Bhattacharyya
  • Garima Singh
  • Arindam Jati
  • Amit Konar
  • D. N. Tibarewala
  • R. Janarthanan
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 178)


An efficient scheme of emotion recognition using EEG signals is an initiation to our quest for developing emotionally intelligent systems and devices, in order to enhance the performance quality of the same. Classification of emotions, both euphoric and negative, using stimulated EEG signals acquired from subjects whose different emotional states were elicited using audio-visual stimuli. The underlying strategy involved the extraction of Power spectral density(PSD) and empirical mode decomposition (EMD) features from the raw EEG data and their classification using linear discriminant analysis (LDA) and linear support vector machine (SVM) thereby classifying the emotions into their respective emotion classes: neutral, happy and sad, with an average classification accuracy of 76.46%,where the neutral state has been classified most efficiently, with an average classification accuracy of 80.86%. The classification accuracy increases with EMD features with reduction in time and computational complexity. LDA is found to perform better than LSVM with EMD features.


EEG Emotion recognition PSD EMD LDA SVM 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Chakraborty, A., Konar, A.: Emotional Intelligence: A Cybernetic Approach, 1st edn. SCI. Springer, Hiedelberg (2009)Google Scholar
  2. 2.
    Cornelius, R.R.: Theoretical approaches to emotion. In: ISCA Workshop on Speech and Emotion, Belfast (2000)Google Scholar
  3. 3.
    Pantic, M., Rothkrantz, L.J.M.: Toward an Affect-Sensitive Multimodal Human-Computer Interaction. Invited Speaker on the Proceedings of IEEE 91(9) (2003)Google Scholar
  4. 4.
    Chanel, G., Kronegg, J., Grandjean, D., Pun, T.: Emotion Assessment: Arousal Evaluation Using EEG’s and Peripheral Physiological Signals. In: Gunsel, B., Jain, A.K., Tekalp, A.M., Sankur, B. (eds.) MRCS 2006. LNCS, vol. 4105, pp. 530–537. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  5. 5.
    Picard, R.W., Vyzas, E., Healey, J.: Toward machine emotional intelligence: Analysis of affective physiological state. IEEE Trans. on Pattern Analysis and Machine Intelligence 23(10), 1175–1191 (2001)CrossRefGoogle Scholar
  6. 6.
    Gott, P.S., Hughes, E.C., Whipple, K.: Voluntary control of two lateralized conscious states: validation by electrical and behavioral studies. Neuropsychologia 22, 65–72 (1984)CrossRefGoogle Scholar
  7. 7.
    Murugappan, M., Rizon, M., Nagarajan, R., Yaacob, S., Zunaidi, I., Hazry, D.: EEG Feature Extraction for Classifying Emotions using FCM and FKM. J. Comp. Comm. 1, 21–25 (2007)Google Scholar
  8. 8.
    Das, S., Halder, A., Bhowmik, P., Chakraborty, A., Konar, A., Janarthan, R.: A Support Vector Machine Classifier of Emotion from Voice and Facial Expression Data. In: Proc. IEEE 2009 World Congress on Nature and Biologically Inspired Computing (NaBIC 2009), pp. 1010–1015 (2009)Google Scholar
  9. 9.
    Lotte, F., et al.: A review of classification algorithms for EEG-based Brain-computer interfaces. J. Neural Eng. 4 (2007)Google Scholar
  10. 10.
    Rezaei, S., Tavakolian, K., Nasrabadi, A.M., Setarehdan, S.K.: Different classification techniques considering brain computer interface applications. J. Neural Eng. 3(2), 139–144 (2006)CrossRefGoogle Scholar
  11. 11.
    Srinivasa, K.G., Venugopal, K.R., Patnaik, K.R.: Feature Extraction Using Fuzzy C-Means Clustering for Data Mining Systems. Int. J. Comp. Sc. & Network Sec. 6, 230–236 (2006)Google Scholar
  12. 12.
    Niemic, C.P.: Studies of emotion: A theoretical and empirical review of psychophysiological studies of emotion. J. Undergraduate Research, 15–18 (2002)Google Scholar
  13. 13.
    Gross, J.J., Levenson, R.W.: Emotion elicitation using films. Cognition and Emotion 9, 87–108 (1995)CrossRefGoogle Scholar
  14. 14.
    Zhang, Q., Lee, M.: Analysis of positive and negative emotions in natural scene using brain activity and gist. Neurocomputing 72(4-6), 1302–1306 (2008)CrossRefGoogle Scholar
  15. 15.
    Stoica, P., Moses, R.: Introduction to Spectral Analysis. Prentice Hall (1997)Google Scholar
  16. 16.
    Proakis, J.G., Malonakis, D.G.: Digital Signal Processing: Principles, Algorithm and Applications, 3rd edn. Prentice Hall (1996)Google Scholar
  17. 17.
    Sanei, S., Chambers, J.A.: Brain Computer Interfacing, EEG Signal Processing, pp. 239–265. John Wiley & Sons (2007)Google Scholar
  18. 18.
    Oppenheim, A., Schafer, R.: Digital Signal Processing. Prentice Hall (1975)Google Scholar
  19. 19.
    Fabian, J.T., Anke, M.B.: Biomedical Signal Analysis: Contemporary Methods and Applications. The MIT Press, Cambridge (2010)Google Scholar
  20. 20.
    Huang, N.E., et al.: The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc. R. Soc. Lond. A 454, 903–995 (1998)MATHCrossRefGoogle Scholar
  21. 21.
    Long, S.R., et al.: The Hilbert techniques: an alternate approach for non-steady time series analysis. IEEE Geoscience Remote Sensing Soc. Lett. 3, 6–11 (1995)Google Scholar
  22. 22.
    Alpaydin, E.: Introduction to machine learning. MIT Press, Cambridge (2004)Google Scholar
  23. 23.
    Webb, A.R.: Statistical Pattern Recognition, 2nd edn. John Wiley and Sons (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Anwesha Khasnobish
    • 1
  • Saugat Bhattacharyya
    • 1
  • Garima Singh
    • 2
  • Arindam Jati
    • 2
  • Amit Konar
    • 2
  • D. N. Tibarewala
    • 1
  • R. Janarthanan
    • 3
  1. 1.School of Bioscience and EngineeringJadavpur UniversityKolkataIndia
  2. 2.Dept. of Electronics and Telecommunication EngineeringJadavpur UniversityKolkataIndia
  3. 3.Dept. of Information TechnologyJaya Engineering CollegeChennaiIndia

Personalised recommendations