Pattern Analysis and Applications

, Volume 21, Issue 1, pp 81–89 | Cite as

Emotion recognition from EEG signals by using multivariate empirical mode decomposition

Theoretical Advances


This paper explores the advanced properties of empirical mode decomposition (EMD) and its multivariate extension (MEMD) for emotion recognition. Since emotion recognition using EEG is a challenging study due to nonstationary behavior of the signals caused by complicated neuronal activity in the brain, sophisticated signal processing methods are required to extract the hidden patterns in the EEG. In addition, multichannel analysis is another issue to be considered when dealing with EEG signals. EMD is a recently proposed iterative method to analyze nonlinear and nonstationary time series. It decomposes a signal into a set of oscillations called intrinsic mode functions (IMFs) without requiring a set of basis functions. In this study, a MEMD-based feature extraction method is proposed to process multichannel EEG signals for emotion recognition. The multichannel IMFs extracted by MEMD are analyzed using various time and frequency domain techniques such as power ratio, power spectral density, entropy, Hjorth parameters and correlation as features of valance and arousal scales of the participants. The proposed method is applied to the DEAP emotional EEG data set, and the results are compared with similar previous studies for benchmarking.


Empirical mode decomposition Multivariate empirical mode decomposition Emotion recognition Electroencephalogram 



This work was partially supported by The Research Fund of The University of Istanbul, Project numbers 45259 and 54959.

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.


  1. 1.
    Alam SMS, Bhuiyan MI (2013) Detection of seizure and epilepsy using higher order statistics in the EMD domain. IEEE J Biomed Health Inf 17(2):312–318. doi: 10.1109/JBHI.2012.2237409 CrossRefGoogle Scholar
  2. 2.
    Bos DO (2006) EEG-based emotion recognition: the influence of visual and auditory stimuli. Available:
  3. 3.
    Daimi SN, Saha G (2014) Classification of emotions induced by music videos and correlation with participants rating. Expert Syst Appl 41:6057–6065. doi: 10.1016/j.eswa.2014.03.050 CrossRefGoogle Scholar
  4. 4.
    Eftekhar A, Toumazou C, Drakakis EM (2013) Empirical mode decomposition: real-time implementation and applications. J Signal Process Syst 73(1):43–58. doi: 10.1007/s11265-012-0726-y CrossRefGoogle Scholar
  5. 5.
    Flandrin P, Goncalves P (2004) Emprical mode decompositions as data-driven wavelet-like expansions. Int J Wavel Multiresolut Inf Process 02:477–496. doi: 10.1142/S0219691304000561 CrossRefMATHGoogle Scholar
  6. 6.
    Hjorth B (1970) Eeg analysis based on time domain properties. Electroencephalogr Clin Neurophysiol 29(3):306–310CrossRefGoogle Scholar
  7. 7.
    Huang NE, Shen Z, Long SR, Wu MC, Shih HH, Zheng Q, Yen NC, Tung CC, Liu HH (1998) The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc R Soc A Math Phys Eng Sci 454:903–995. doi: 10.1098/rspa.1998.0193 MathSciNetCrossRefMATHGoogle Scholar
  8. 8.
    Hyvarinen A, Oja E (2000) Independent component analysis: algorithms and applications. Neural Netw 13:411–430. doi: 10.1016/S0893-6080(00)00026-5 CrossRefGoogle Scholar
  9. 9.
    Jirayucharoensak S, Pan-Ngum S, Israsena P (2014) EEG-based emotion recognition using deep learning network with principal component based covariate shift adaptation. Sci World J. doi: 10.1155/2014/627892 Google Scholar
  10. 10.
    Koelstra S, Mühl C, Soleymani M, Lee JS, Yazdani A, Ebrahimi T, Pun T, Nijholt A, Patras I (2012) DEAP: a database for emotion analysis; using physiological signals. IEEE Trans Affect Comput 3:18–31. doi: 10.1109/T-AFFC.2011.15 CrossRefGoogle Scholar
  11. 11.
    Lin YP, Wang CH, Jung TP, Wu TL, Jeng SK, Duann JR, Chen JH (2010) EEG-based emotion recognition in music listening. IEEE Trans Biomed Eng 57:1798–1806. doi: 10.1109/TBME.2010.2048568 CrossRefGoogle Scholar
  12. 12.
    Mert A, Akan A (2014) Detrended fluctuation thresholding for empirical mode decomposition based denoising. Digit Signal Process 32:48–56. doi: 10.1016/j.dsp.2014.06.006 CrossRefGoogle Scholar
  13. 13.
    Mert A, Niyazi K, Bilgili E, Akan A (2014) Breast cancer detection with reduced feature set. Comput Math Methods Med. Article ID 265138:11 pagesGoogle Scholar
  14. 14.
    Molla M, Hirose K, Hasan M (2015) Voiced/non-voiced speech classification using adaptive thresholding with bivariate EMD. Pattern Anal Appl. doi: 10.1007/s10044-015-0449-3 Google Scholar
  15. 15.
    Morris JD (1995) Observations: Sam: the self-assessment manikin; an efficient cross-cultural measurement of emotional response. J Advert Res 35(6):63–68Google Scholar
  16. 16.
    Pachori RB, Bajaj V (2011) Analysis of normal and epileptic seizure EEG signals using empirical mode decomposition. Comput Methods Progr Biomed 104:373–381. doi: 10.1016/j.cmpb.2011.03.009 CrossRefGoogle Scholar
  17. 17.
    Rached TS, Perkusich A (2013) Emotion recognition based on brain–computer interface systems. In: Fazel-Rezai R (ed) Brain–computer interface systems—recent progress and future prospects. InTech, RijekaGoogle Scholar
  18. 18.
    Rehman N, Mandic DP (2009) Multivariate empirical mode decomposition. Proc R Soc A Math Phys Eng Sci 466:1291–1302. doi: 10.1098/rspa.2009.0502 MathSciNetCrossRefMATHGoogle Scholar
  19. 19.
    Rilling G, Flandrin P (2008) One or two frequencies? The empirical mode decomposition answers. IEEE Trans Signal Process 56:85–95MathSciNetCrossRefGoogle Scholar
  20. 20.
    Rilling G, Flandrin P, Gonçalves P, Lilly JM (2007) Bivariate empirical mode decomposition. IEEE Signal Process Lett. doi: 10.1109/LSP.2007.904710 Google Scholar
  21. 21.
    Russell JA (1980) A circumplex model of affect. J Personal Soc Psychol 39:1161–1178. doi: 10.1037/h0077714 CrossRefGoogle Scholar
  22. 22.
    Saini I, Singh D, Khosla A (2014) Electrocardiogram beat classification using empirical mode decomposition and multiclass directed acyclic graph support vector machine. Comput Electr Eng 40(5):1774–1787. doi: 10.1016/j.compeleceng.2014.04.004 CrossRefGoogle Scholar
  23. 23.
    Soleymani M, Pantic M, Pun T (2012) Multimodal emotion recognition in response to videos. IEEE Trans Affect Comput 3:211–223. doi: 10.1109/T-AFFC.2011.37 CrossRefGoogle Scholar
  24. 24.
    Ur Rehman N, Mandic DP (2010) Empirical mode decomposition for trivariate signals. IEEE Trans Signal Process 58:1059–1068. doi: 10.1109/TSP.2009.2033730 MathSciNetCrossRefGoogle Scholar
  25. 25.
    Ur Rehman N, Mandic DP (2011) Filter bank property of multivariate empirical mode decomposition. IEEE Trans Signal Process 59:2421–2426. doi: 10.1109/TSP.2011.2106779 MathSciNetCrossRefGoogle Scholar
  26. 26.
    Wang XW, Nie D, Lu BL (2014) Emotional state classification from EEG data using machine learning approach. Neurocomputing 129:94–106. doi: 10.1016/j.neucom.2013.06.046 CrossRefGoogle Scholar
  27. 27.
    Wu CH, Chang HC, Lee PL, Li KS, Sie JJ, Sun CW, Yang CY, Li PH, Deng HT, Shyu KK (2011) Frequency recognition in an SSVEP-based brain computer interface using empirical mode decomposition and refined generalized zero-crossing. J Neurosci Methods 196:170–181. doi: 10.1016/j.jneumeth.2010.12.014 CrossRefGoogle Scholar
  28. 28.
    Xu Z, Huang B, Li K (2010) An alternative envelope approach for empirical mode decomposition. Digit Signal Process 20:77–84CrossRefGoogle Scholar
  29. 29.
    Yanli Y, Changyun M, Jiahao D (2013) An analytical expression for empirical mode decomposition based on b-spline interpolation. Circ Syst Signal Proces. doi: 10.1007/s00034-013-9592-5 MathSciNetGoogle Scholar

Copyright information

© Springer-Verlag London 2016

Authors and Affiliations

  1. 1.Department of Mechatronics EngineeringBursa Technical UniversityYildirim, BursaTurkey
  2. 2.Department of Electrical and Electronics EngineeringIstanbul UniversityAvcilar, IstanbulTurkey

Personalised recommendations