Time Series Feature Evaluation in Discriminating Preictal EEG States

  • Dimitris Kugiumtzis
  • Angeliki Papana
  • Alkiviadis Tsimpiris
  • Ioannis Vlachos
  • Pål G. Larsson
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4345)


Statistical discrimination of states in the preictal EEG is attempted using a large number of measures from linear and nonlinear time series analysis. The measures are organized in two categories: correlation measures, such as autocorrelation and mutual information at specific lags and new measures derived from oscillations of the EEG time series, such as mean oscillation peak and mean oscillation period. All measures are computed on successive segments of multichannel EEG windows selected from early, intermediate and late preictal states from four epochs. Hypothesis tests applied for each channel and epoch showed good discrimination of the preictal states and allowed for the selection of optimal measures. These optimal measures, together with other standard measures (skewness, kurtosis, largest Lyapunov exponent) formed the feature set for feature-based clustering and the feature-subset selection procedure showed that the best preictal state classification was obtained with the same optimal features.


Mutual Information Epileptic Seizure Feature Subset Correlation Measure Large Lyapunov Exponent 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Hirsch, E., Andermann, F., Chauvel, P., Engel, J., da Lopes Silva, F., Luders, H.: Generalized Seizures: from Clinical Phenomenology to Underlying Systems and Networks. Elsevier, Paris (2006)Google Scholar
  2. 2.
    Song, I.-H., Lee, S.-M., Kim, I.-Y., Lee, D.-S., Kim, S.I.: Mutifractal analysis of electroencephalogram time series in humans. In: Cabestany, J., Prieto, A.G., Sandoval, F. (eds.) IWANN 2005. LNCS, vol. 3512, pp. 921–926. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  3. 3.
    Paluš, M., Komárek, V., Procházka, T., Hrncír, Z., Šterbová, K.: Synchronization and information flow in EEGs of epileptic patients. IEEE Engineering in Medicine and Biology Magazine 20(5), 65–71 (2001)CrossRefGoogle Scholar
  4. 4.
    Steuer, R., Ebeling, W., Bengner, T., Dehnicke, C., Hättig, H., Meencke, H.-J.: Entropy and complexity analysis of intracranially recorded EEG. International Journal of Bifurcation and Chaos in Applied Sciences and Engineering 14(2), 815–823 (2004)zbMATHCrossRefGoogle Scholar
  5. 5.
    Iasemidis, L.D., Shiau, D.-S., Pardalos, P.M., Chaovalitwongse, W., Narayanan, K., Prasad, A., Tsakalis, K., Carney, P.R., Sackellares, J.C.: Long-term prospective on-line real-time seizure prediction. Clinical Neurophysiology 116(3), 532–544 (2005)CrossRefGoogle Scholar
  6. 6.
    Lai, Y.-C., Harrison, M.A.F., Frei, M.G., Osorio, I.: Controlled test for predictive power of Lyapunov exponents: Their inability to predict epileptic seizures. Chaos 14(3), 630–642 (2004)zbMATHCrossRefMathSciNetGoogle Scholar
  7. 7.
    Maiwald, T., Winterhalder, M., Aschenbrenner-Scheibe, R., Voss, H.U., Schulze-Bonhage, A., Timmer, J.: Comparison of three nonlinear seizure prediction methods by means of the seizure prediction characteristic. Physica D 194(3-4), 357–368 (2004)zbMATHCrossRefGoogle Scholar
  8. 8.
    Kugiumtzis, D., Larsson, P.G.: Linear and nonlinear analysis of EEG for the prediction of epileptic seizures. In: Lehnertz, K., Arnhold, J., Grassberger, P., Elger, C.E. (eds.) Chaos in Brain?, Proceedings of the 1999 Workshop, pp. 329–332. World Scientific, Singapore (2000)CrossRefGoogle Scholar
  9. 9.
    Mormann, F., Kreuz, T., Andrzejak, R.G., David, P., Lehnertz, K., Elger, C.E.: Epileptic seizures are preceded by a decrease in synchronization. Epilepsy Research 53(3), 173–185 (2003)CrossRefGoogle Scholar
  10. 10.
    Schelter, B., Winterhalder, M., Maiwald, T., Brandt, A., Schad, A., Schulze-Bonhage, A., Timmer, J.: Testing statistical significance of multivariate time series analysis techniques for epileptic seizure prediction. Chaos 16(1), 013108 (2006)CrossRefGoogle Scholar
  11. 11.
    Chillemi, S., Balocchi, R., Di Garbo, A., D’Attellis, C.E., Gigola, S., Kochen, S., Silva, W.: Discriminating preictal from interictal states by using coherence measures. In: Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology, vol. 3, pp. 2319–2322 (2003)Google Scholar
  12. 12.
    Jouny, C.C., Franaszczuk, P.J., Bergey, G.K.: Signal complexity and synchrony of epileptic seizures: Is there an identifiable preictal period? Clinical Neurophysiology 116(3), 552–558 (2005)CrossRefGoogle Scholar
  13. 13.
    Dikanev, T., Smirnov, D., Wennberg, R., Velazquez, J.L.P., Bezruchko, B.: EEG nonstationarity during intracranially recorded seizures: Statistical and dynamical analysis. Clinical Neurophysiology 116(8), 1796–1807 (2005)CrossRefGoogle Scholar
  14. 14.
    Stam, C.J.: Nonlinear dynamical analysis of EEG and MEG: Review of an emerging field. Clinical Neurophysiology 116, 2266–2301 (2005)CrossRefGoogle Scholar
  15. 15.
    Velazquez, J.L.P.: Brain, behaviour and mathematics: Are we using the right approaches? Physica D 212(3-4), 161–182 (2005)CrossRefMathSciNetGoogle Scholar
  16. 16.
    Mormann, F., Kreuz, T., Rieke, R.G., Andrzejak, C., Kraskov, A., David, P., Elger, C.E., Lehnertz, K.: On the predictability of epileptic seizures. Clinical Neurophysiology 116(3), 569–587 (2005)CrossRefGoogle Scholar
  17. 17.
    Chavez, M., Besserve, M., Adam, C., Martinerie, J.: Towards a proper estimation of phase synchronization from time series. Journal of Neuroscience Methods 154(1-2), 149–160 (2006)CrossRefGoogle Scholar
  18. 18.
    Darbellay, G.A.: An estimator of the mutual information based on a criterion for conditional independence. Computational Statistics and Data Analysis 32(1), 1–17 (1999)CrossRefMathSciNetGoogle Scholar
  19. 19.
    Kugiumtzis, D.A., Kehagias, E.C.A., Neuhaüser, H.: Statistical analysis of the extreme values of stress time series from the Portevin Le Châtelier effect. Physical Review E 70(3), 036110 (2004)CrossRefGoogle Scholar
  20. 20.
    Hubert, L., Arabie, P.: Comparing partitions. Journal of Classification 2, 193–218 (1985)CrossRefGoogle Scholar
  21. 21.
    Aha, D.W., Bankert, R.L.: A comparative evaluation of sequential feature selection algorithms. In: Fisher, D., Lenz, H. (eds.) Proceedings of the Fifth International Workshop on Artificial Intelligence and Statistics, pp. 1–7 (1995)Google Scholar
  22. 22.
    Tsimpiris, A., Kugiumtzis, D.: Clustering of oscillating dynamical systems from time series data bases. In: Electronic Proceedings of the International Workshop on Knowledge Extraction and Modeling, Capri, Italy (2006)Google Scholar
  23. 23.
    Hegger, R., Kantz, H., Schreiber, T.: Practical implementation of nonlinear time series methods: The TISEAN package. Chaos 9, 413 (1999)zbMATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Dimitris Kugiumtzis
    • 1
  • Angeliki Papana
    • 1
  • Alkiviadis Tsimpiris
    • 1
  • Ioannis Vlachos
    • 1
  • Pål G. Larsson
    • 2
  1. 1.Aristotle University of ThessalonikiThessalonikiGreece
  2. 2.National Center for EpilepsySandvikaNorway

Personalised recommendations