Classifying Epileptic EEG Signals with Delay Permutation Entropy and Multi-scale K-Means

  • Guohun Zhu
  • Yan Li
  • Peng (Paul) Wen
  • Shuaifang Wang
Chapter
Part of the Advances in Experimental Medicine and Biology book series (AEMB, volume 823)

Abstract

Most epileptic EEG classification algorithms are supervised and require large training datasets, that hinder their use in real time applications. This chapter proposes an unsupervised Multi-Scale K-means (MSK-means) algorithm to distinguish epileptic EEG signals and identify epileptic zones. The random initialization of the K-means algorithm can lead to wrong clusters. Based on the characteristics of EEGs, the MSK-means algorithm initializes the coarse-scale centroid of a cluster with a suitable scale factor. In this chapter, the MSK-means algorithm is proved theoretically superior to the K-means algorithm on efficiency. In addition, three classifiers: the K-means, MSK-means and support vector machine (SVM), are used to identify seizure and localize epileptogenic zone using delay permutation entropy features. The experimental results demonstrate that identifying seizure with the MSK-means algorithm and delay permutation entropy achieves 4. 7 % higher accuracy than that of K-means, and 0. 7 % higher accuracy than that of the SVM.

Keywords

Unsupervised learning Delay permutation entropy MSK-means SVM Seizure detection Epileptogenic focus location 

References

  1. 1.
    R.G. Andrzejak, K. Lehnertz, F. Mormann, C. Rieke, P. David, C.E. Elger, Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: dependence on recording region and brain state. Phys. Rev. E 64(6), 061907 (2001)Google Scholar
  2. 2.
    R.G. Andrzejak, K. Schindler, C. Rummel, Nonrandomness, nonlinear dependence, and nonstationarity of electroencephalographic recordings from epilepsy patients. Phys. Rev. E 86(4), 046206 (2012)Google Scholar
  3. 3.
    R.G. Andrzejak, K. Schindler, C. Rummel, The Bern-Barcelona EEG database, http://ntsa.upf.edu/downloads/andrzejak-rg-schindler-k-rummel-c-2012-nonrandomness-nonlinear-dependence-and. Accessed 10 Aug 2013
  4. 4.
    D. Arthur, S. Vassilvitskii, k-means++: the advantages of careful seeding, in Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, Philadelphia, 2007, pp. 1027–1035Google Scholar
  5. 5.
    B. Bahmani, B. Moseley, A. Vattani, R. Kumar, S. Vassilvitskii, Scalable k-means++. Proc. VLDB Endow. 5(7), 622–633 (2012)CrossRefGoogle Scholar
  6. 6.
    C. Bandt, B. Pompe, Permutation entropy: a natural complexity measure for time series. Phys. Rev. Lett. 88(17), 174102 (2002)Google Scholar
  7. 7.
    E. Ben-Jacob, T. Doron, T. Gazit, E. Rephaeli, O. Sagher, V.L. Towle, Mapping and assessment of epileptogenic foci using frequency-entropy templates. Phys. Rev. E 76(5), 051903 (2007)Google Scholar
  8. 8.
    J.H. Cho, H.C. Kang, Y.J. Jung, J.Y. Kim, H.D. Kim, D.S. Yoon, Y.H. Lee, C.H. Im, Localization of epileptogenic zones in Lennox-Gastaut syndrome using frequency domain source imaging of intracranial electroencephalography: a preliminary investigation. Physiol. Meas. 34(2), 247–263 (2013)CrossRefGoogle Scholar
  9. 9.
    M. Costa, A.L. Goldberger, C.K. Peng, Multiscale entropy analysis of complex physiologic time series. Phys. Rev. Lett. 89(6), 068102 (2002)Google Scholar
  10. 10.
    G. Goffin, S. Dedeurwaerdere, K. Van Laere, W. Van Paesschen, Neuronuclear assessment of patients with epilepsy. Semin. Nucl. Med. 38(4), 227–239 (2008)CrossRefGoogle Scholar
  11. 11.
    L. Guo, D. Rivero, J. Dorado, C.R. Munteanu, A. Pazos, Automatic feature extraction using genetic programming: an application to epileptic EEG classification. Expert Syst. Appl. 38(8), 10425–10436 (2011)CrossRefGoogle Scholar
  12. 12.
    T.R. Henry, R.L. Van Heertum, Positron emission tomography and single photon emission computed tomography in epilepsy care. Semin. Nucl. Med. 33(2), 88–104 (2003)CrossRefGoogle Scholar
  13. 13.
    A. Karatzoglou, D. Meyer, K. Hornik, Support vector machines in R. J. Stat. Softw. 15(9), 1–28 (2006)Google Scholar
  14. 14.
    R.C. Knowlton, R.A. Elgavish, A. Bartolucci, B. Ojha, N. Limdi, J. Blount, J.G. Burneo, L. Ver Hoef, L. Paige, E. Faught, P. Kankirawatana, K. Riley, R. Kuzniecky, Functional imaging: II. Prediction of epilepsy surgery outcome. Ann. Neurol. 64(1), 35–41 (2008)Google Scholar
  15. 15.
    P. Krsek, M. Kudr, A. Jahodova, V. Komarek, B. Maton, S. Malone, I. Miller, P. Jayakar, T. Resnick, M. Duchowny, Localizing value of ictal SPECT is comparable to MRI and EEG in children with focal cortical dysplasia. Epilepsia 54(2), 351–358 (2013)CrossRefGoogle Scholar
  16. 16.
    J. Liu, G. Zhu, M. Xi, A k-means algorithm based on the radius. J. Guilin Univ. Electron. Technol. 33(2), 134–138 (2013)Google Scholar
  17. 17.
    J.B. MacQueen, Some methods of classification and analysis of multivariate observations, in Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, Berkeley, 1967, pp. 281–297Google Scholar
  18. 18.
    M. Matilla-García, M. Ruiz Marín, Detection of non-linear structure in time series. Econ. Lett. 105(1), 1–6 (2009)CrossRefMATHGoogle Scholar
  19. 19.
    F. Mormann, R.G. Andrzejak, C.E. Elger, K. Lehnertz, Seizure prediction: the long and winding road. Brain 130(2), 314–333 (2007)CrossRefGoogle Scholar
  20. 20.
    N. Nicolaou, J. Georgiou, Detection of epileptic electroencephalogram based on permutation entropy and support vector machines. Expert Syst. Appl. 39(1), 202–209 (2012)CrossRefGoogle Scholar
  21. 21.
    U. Orhan, M. Hekim, M. Ozer, EEG signals classification using the K-means clustering and a multilayer perceptron neural network model. Expert Syst. Appl. 38(10), 13475–13481 (2011)CrossRefGoogle Scholar
  22. 22.
    K. Polat, S. Günes, Classification of epileptiform EEG using a hybrid system based on decision tree classifier and fast Fourier transform. Appl. Math. Comput. 187(2), 1017–1026 (2007)CrossRefMATHMathSciNetGoogle Scholar
  23. 23.
    A. Popov, O. Avilov, O. Kanaykin, Saturation of electroencephalogram permutation entropy for large time lags, in IEEE XXXIII International Scientific Conference Electronics and Nanotechnology (ELNANO), Kiev, 16–19 Apr 2013, pp. 251–254Google Scholar
  24. 24.
    F. Rosenow, H. Lüders, Presurgical evaluation of epilepsy. Brain 124(9), 1683–1700 (2001)CrossRefGoogle Scholar
  25. 25.
    S. Siuly, Y. Li, P. Wen, Clustering technique-based least square support vector machine for EEG signal classification. Comput. Methods Programs Biomed. 104(3), 358–372 (2011)CrossRefGoogle Scholar
  26. 26.
    Y. Song, P. Liò, A new approach for epileptic seizure detection: sample entropy based feature extraction and extreme learning machine. J. Biomed. Sci. Eng. 3(6), 556–567 (2010)CrossRefGoogle Scholar
  27. 27.
    M.V. Spanaki, S.S. Spencer, M. Corsi, J. MacMullan, J. Seibyl, I.G. Zubal, Sensitivity and specificity of quantitative difference SPECT analysis in seizure localization. J. Nucl. Med.: Off. Publ. Soc. Nucl. Med., 40(5), 730–736 (1999)Google Scholar
  28. 28.
    A. Subasi, Automatic detection of epileptic seizure using dynamic fuzzy neural networks. Expert Syst. Appl. 31(2), 320–328 (2006)CrossRefMathSciNetGoogle Scholar
  29. 29.
    P. van Mierlo, E. Carrette, H. Hallez, R. Raedt, A. Meurs, S. Vandenberghe, D. Van Roost, P. Boon, S. Staelens, K. Vonck, Ictal-onset localization through connectivity analysis of intracranial EEG signals in patients with refractory epilepsy. Epilepsia 54(8), 1409–1418 (2007)CrossRefGoogle Scholar
  30. 30.
    A. Vattani, k-means requires exponentially many iterations even in the plane. Discret. Comput. Geom. 45(4), 596–616 (2011)Google Scholar
  31. 31.
    J. Wu, W. Sutherling, S. Koh, N. Salamon, R. Jonas, S. Yudovin, R. Sankar, W. Shields, G. Mathern, Magnetic source imaging localizes epileptogenic zone in children with tuberous sclerosis complex. Neurology 66(8), 1270–1272 (2006)CrossRefGoogle Scholar
  32. 32.
    G. Zhu, Y. Li, P.P. Wen, Analysing epileptic EEGs with a visibility graph algorithm, in 5th International Conference on Biomedical Engineering and Informatics (BMEI2012), Chongqing, 16–18 Oct 2012, pp. 432–436Google Scholar
  33. 33.
    G. Zhu, Y. Li, P.P. Wen, S. Wang, M. Xi, Epileptogenic focus detection in intracranial EEG based on delay permutation entropy. AIP Conf. Proc. 1559, 31–36 (2013)CrossRefGoogle Scholar
  34. 34.
    G. Zhu, Y. Li, P. Wen, S. Wang, N. Zhong, Unsupervised classification of epileptic EEG signals with multi scale K-means algorithm, in Brain and Health Informatics, Maebashi, ed. by K. Imamura, S. Usui, T. Shirao, T. Kasamatsu, L. Schwabe, N. Zhong. Lecture Notes in Computer Science, vol. 8211 (Springer, Cham, 2013), pp. 158–167Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Guohun Zhu
    • 1
    • 2
  • Yan Li
    • 1
  • Peng (Paul) Wen
    • 1
  • Shuaifang Wang
    • 1
  1. 1.Faculty of Health, Engineering and SciencesUniversity of Southern QueenslandToowoombaAustralia
  2. 2.School of Electronic Engineering and AutomationGuilin University of Electronic TechnologyGuilin, GuangxiChina

Personalised recommendations