access icon free Real-time mining of epileptic seizure precursors via nonlinear mapping and dissimilarity features

We propose a novel approach for detecting precursors to epileptic seizures in intracranial electroencephalograms (iEEGs), which is based on the analysis of system dynamics. In the proposed scheme, the largest Lyapunov exponent (LLE) of wavelet entropy of the segmented EEG signals are considered as the discriminating features. Such features are processed by a support vector machine classifier, whose outcomes (the label and its probability for each LLE) are post-processed and fed into a novel decision function to determine whether the corresponding segment of the EEG signal contains a precursor to an epileptic seizure. The proposed scheme is applied to the Freiburg data set, and the results show that seizure precursors are detected in a time frame that unlike other existing schemes is very much convenient to patients, with the sensitivity of 100% and negligible false positive detection rates.

Inspec keywords: medical signal detection; electroencephalography; support vector machines; entropy; Lyapunov methods; wavelet transforms; biomedical transducers; signal classification

Other keywords: epileptic seizure prediction; decision function; EEG signal segmentation; wavelet entropy; intracranial electroencephalograms; time frame detection; LLE; system dynamics analysis; nonlinear analysis; largest Lyapunov exponent; precursor detection; iEEG; Freiburg data set; support vector machine classifier

Subjects: Knowledge engineering techniques; Patient diagnostic methods and instrumentation; Function theory, analysis; Digital signal processing; Signal detection; Integral transforms; Electrodiagnostics and other electrical measurement techniques; Biology and medical computing; Integral transforms; Bioelectric signals

References

    1. 1)
    2. 2)
    3. 3)
    4. 4)
      • 22. Available at http://www.epilepsy.uni-freiburg.de/freiburg-seizure-prediction-project/eeg-database/2003.
    5. 5)
    6. 6)
    7. 7)
    8. 8)
    9. 9)
    10. 10)
      • 2. Nesaei, S., Nesaei, S.: ‘Comparison of phase synchrony information flow in human EEG through wavelet phase synchronization analysis’. Proc. Tenth Int. IEEE Signal Processing (ICSP2010), Beijing, China, 2010.
    11. 11)
    12. 12)
      • 23. Available at http://www.iwsp4.org/patients.htm. Accessed January 2010.
    13. 13)
      • 27. Panda, R., Khobragade, P.S., Jambhule, P.D., Jengthe, S.N., Pal, P.R., Gandhi, T.K.: ‘Classification of EEG signal using wavelet transform and support vector machine for epileptic seizure detection’. Proc. Conf. Systems in Medicine and Biology, Kharagpour, India, 2010.
    14. 14)
      • 12. Direito, B., Dourado, A., Sales, F.: ‘Combining energy and wavelet transform for epileptic seizure prediction in an advanced computational system’. Proc. First Int. Conf. Biomedical Engineering and Informatics (IEEE BMEI), Sanya, Hainan, China, May 2008, pp. 380385.
    15. 15)
    16. 16)
    17. 17)
    18. 18)
    19. 19)
    20. 20)
    21. 21)
    22. 22)
    23. 23)
    24. 24)
    25. 25)
      • 13. Mikowski, P.W., LeCun, Y., Madhavan, D., Kuzniecky, R.: ‘Comparing SVM and convolution networks for epileptic seizure prediction from intracranial EEG’. Proc. IEEE Workshop Machine Learning Signal Processing (MLSP 2008), Concun, Mexico, October 2008, pp. 244249.
    26. 26)
    27. 27)
    28. 28)
    29. 29)
      • 28. Zhao, J., Zhou, W., Liu, K., Cai, K.: ‘Application of SVM and wavelet analysis in EEG classification’, Medline, 2011, 28, (2), pp. 7779.
    30. 30)
      • 30. Cao, L.: ‘Determining minimum embedding dimension from scalar time series’, in Soofi, A., Cao, L. (Eds.): ‘Modelling and forecasting financial data’ (Springer US, 2002), pp. 4360.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-spr.2013.0297
Loading

Related content

content/journals/10.1049/iet-spr.2013.0297
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Errata
An Erratum has been published for this content:
Erratum