Skip to main content
SpringerLink
Log in

A hybrid cascade method for EEG classification

  • Short Paper
  • Published:
Pattern Analysis and Applications Aims and scope Submit manuscript

Abstract

The classification of EEG signals is an essential step in the design of brain–computer interface. In order to optimize this step, a method for EEG classification using a cascade technique is proposed. This classification process is implemented in two steps. In the first stage, the feature extraction is accomplished using a discrete wavelet transform (DWT), followed by a feature selection via a filter method in order to select pertinent features from the original feature set. Therefore, reduced feature vectors are presented as input to the classifier. In the second step, features are extracted from the misclassified trials resulting from the first step. Then, the most relevant features are selected. Eventually, the feature vectors are classified. Two configurations of cascade classifiers are tested. In each of them, the classifier used in the first step of the classification scheme is different from the one applied in the second step. Moreover, regarding feature extraction, two cases are studied. In the first case, the same wavelet function is applied in the two steps of the classification process, whereas in the second case, two different wavelet functions are applied successively in the two steps of the classification procedure. The proposed classification scheme was applied on EEG signals of motor imagery dataset III available in BCI competition II, leading to good classification results compared to the existent methods.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

References

  1. Palaniappan R (2005) Brain computer interface design using band powers extracted during mental tasks. In: Proceedings of the 2 international IEEE EMBS conference on neural engineering, Arlington, Virginia, pp 16–19

  2. Brodu N, Lotte F, Lécuyer A (2011) Comparative study of band-power extraction techniques for motor imagery classification. In: IEEE symposium on computational intelligence, cognitive algorithms, mind, and brain (SSCI’2011 CCMB), pp 1–6

  3. Anderson CW, Sijerčíc Z (1996) Classification of EEG signals from four subjects during five mental tasks. In: Solving engineering problems with neural networks: proceedings of the conference on engineering applications in neural networks (EANN ‘96), Turku, Finland, pp 407–414

  4. Adeli H, Zhou Z, Dadmehr N (2003) Analysis of EEG records in an epileptic patient using wavelet transform. J Neurosci Methods 123(1):69–87

    Article  Google Scholar 

  5. Akay M (1995) Wavelet in biomedical engineering. Ann Biomed Eng 23:529–530

    Article  Google Scholar 

  6. Taghizadeh-Sarabi M, Daliri MR, Salehzadeh Niksirat K (2015) Decoding objects of basic categories from electroencephalographic signals using wavelet transform and support vector machines, Brain topography. Brain Topogr 28:33–46

    Article  Google Scholar 

  7. Qin Lei (2005) A wavelet-based time–frequency analysis approach for classification of motor imagery for brain–computer interface applications. J Neural Eng 2:65–72

    Article  Google Scholar 

  8. Behroozi M, Daliri MR, Shekarchi B (2015) EEG phase patterns reflect the representation of semantic categories of objects. Med Biol Eng Comput 54:205–221

    Article  Google Scholar 

  9. Novakovic J, Strbac P, Bulatovic D (2011) Toward optimal feature selection using ranking methods and classification algorithms. Yugosl J Oper Res 21(1):119–135

    Article  MathSciNet  MATH  Google Scholar 

  10. Lotte F (2014) A tutorial on EEG signal processing techniques for mental state recognition in brain–computer interfaces. In: Miranda E-R, Castet J (eds) Guide to brain–computer music interfacing. Springer, Berlin, p ha1-01055103

    Google Scholar 

  11. Dash M, Liu H (1997) Feature selection for classification. Intell Data Anal 1:131–156

    Article  Google Scholar 

  12. Millán J-d- R, Franzé M, Mouriño J, Cincotti F, Babiloni F (2002) Relevant EEG features for the classification of spontaneous motor-related tasks. Biol Cybern 86(2):89–95

    Article  MATH  Google Scholar 

  13. Taghizadeh-Sarabi M, Niksirat KS, Khanmohammadi S, Nazari M (2013) EEG-based analysis of human driving performance in turning left and right using Hopfield neural network. SpringerPlus 2:662

    Article  Google Scholar 

  14. Koprinska I (2010) Feature selection for brain–computer interfaces. In: New frontiers in applied data mining, pp 106–117

  15. Rejer I, Lorenz K (2013) Genetic algorithm and forward selection for feature selection in EEG feature space. J Theor Appl Comput Sci 7(2):72–82

    Google Scholar 

  16. Kołodziej M, Majkowski A, Rak RJ (2011) A new method of EEG classification for BCI with feature extraction based on higher order statistics of wavelet components and selection with genetic algorithms. In: Dobnikar A, Lotrič U, Šter B (eds) ICANNGA 2011, part I, LNCS. Springer: Berlin 6593:280–289

  17. Theodoridis S, Koutroumbas K (1999) Pattern recognition. Academic Press, Cambridge, pp 341–342

    MATH  Google Scholar 

  18. Haury A-C, Gestraud P, Vert J-P (2011) The influence of feature selection methods on accuracy, stability and interpretability of molecular signatures. PLoS ONE 6(12):e28210. https://doi.org/10.1371/journal.pone.0028210

    Article  Google Scholar 

  19. Daliri MR (2013) Kernel earth mover’s distance for EEG classification. Clin EEG Neurosci 44(3):182–187

    Article  Google Scholar 

  20. Jafakesh S, Jahromy FZ, Daliri MR (2016) Decoding of object categories from brain signals using cross frequency coupling methods. Biomed Signal Process Control 27:60–67

    Article  Google Scholar 

  21. Jain AK, Duin RPW, Mao J (2000) Statistical pattern recognition: a review. TPAMI 22:4–37

    Article  Google Scholar 

  22. http://www.bbci.de/competition/ii/; data set III, BCI Competition II, motor imagery

  23. Jasper H (1958) The ten–twenty electrode system of the international federation. Electroencephalogr Clin Neurophysiol 20:371–375

    Google Scholar 

  24. Pfurtscheller G, Neuper C, Flotzinger D, Pregenzer M (1997) EEG based discrimination between imagination of right and left hand movement. Electroencephalogr Clin Neurophysiol 103:642–651

    Article  Google Scholar 

  25. Pfurtscheller G, Jr-A Stancfik, Edlinger G (1997) On the existence of different types of central beta rhythms below 30 Hz. Electroencephalogr Clin Neurophysiol 102:316–325

    Article  Google Scholar 

  26. Pfurtscheller G, Lopes da Silva FH (1999) Event-related EEG/MEG synchronization and desynchronization: basic principles. Clin Neurophysiol 110:1842–1857

    Article  Google Scholar 

  27. Majkowski A, Kolodziej M, Rak RJ (2012) Implementation of automatic feature selection methods for ICO realization. In: 2012 IEEE international instrumentation and measurement technology conference (I2MTC)

  28. Wang S, Chen H, Li S, Zhang D (2007) Feature extraction from tumor gene expression profiles using DCT and DFT. In: Neves J, Santos M, Machado J (eds): EPIA 2007, LNAI. Springer: Berlin, 4874: 485–496

  29. Vapnik VN (1998) Statistical learning theory. Wiley, New York

    MATH  Google Scholar 

  30. Chang C-C, Lin C-J (2001) LIB-SVM: a library for support vector machines. Software available at http://www.csie.ntu.edu.tw/cjlin/libsvm

  31. Garrett D, Peterson D, Anderson Ch, Thaut M (2003) Comparison of linear, nonlinear, and feature selection methods for EEG signal classification. IEEE Trans Neural Syst Rehabil Eng 11(2):141–145

    Article  Google Scholar 

  32. Rejer I (2015) Genetic algorithm with aggressive mutation for feature selection in BCI feature space. Pattern Anal Appl 18:485–492. https://doi.org/10.1007/s10044-014-0425-3

    Article  MathSciNet  Google Scholar 

  33. Azimirad V, Alimohammadi M, Joudi A, Eslami A, Farhoudi M (2015) Analysis of PSO, AIS and GA-based optimal wavelet-neural network classifier in brain–robot interface. IRBM 36(4):240–249

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Laboratory of Signal Image and Information Technology, (LSITI), Department of Electrical Engineering, National School of Engineering of Tunis (ENIT), Tunis El Manar University, BP. 37 Le Belvédère, 1002, Tunis, Tunisia

    Ines Homri & Slim Yacoub

Authors
  1. Ines Homri
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Slim Yacoub
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ines Homri.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Homri, I., Yacoub, S. A hybrid cascade method for EEG classification. Pattern Anal Applic 22, 1505–1516 (2019). https://doi.org/10.1007/s10044-018-0737-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10044-018-0737-9

Keywords

Search

Navigation