Skip to main content
SpringerLink
Log in

Classification of Epilepsy Using High-Order Spectra Features and Principle Component Analysis

  • ORIGINAL PAPER
  • Published:
Journal of Medical Systems Aims and scope Submit manuscript

Abstract

The classification of epileptic electroencephalogram (EEG) signals is challenging because of high nonlinearity, high dimensionality, and hidden states in EEG recordings. The detection of the preictal state is difficult due to its similarity to the ictal state. We present a framework for using principal components analysis (PCA) and a classification method for improving the detection rate of epileptic classes. To unearth the nonlinearity and high dimensionality in epileptic signals, we extract principal component features using PCA on the 15 high-order spectra (HOS) features extracted from the EEG data. We evaluate eight classifiers in the framework using true positive (TP) rate and area under curve (AUC) of receiver operating characteristics (ROC). We show that a simple logistic regression model achieves the highest TP rate for class “preictal” at 97.5% and the TP rate on average at 96.8% with PCA variance percentages selected at 100%, which also achieves the most AUC at 99.5%.

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
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

References

  1. Acharya, U. R., Chua, C. K., Lim, T. C., Dorithy, and Suri, J. S., Automatic identification of epileptic EEG signals using nonlinear parameters. J. Mech. Med. Biol. 9(4):539–553, 2009.

  2. Andrzejak, R. G., Lehnertz, K., Rieke, C., Mormann, F., David, P., and Elger, C. E., 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, 2001.

  3. Aschenbrenner-Scheibe, R., Maiwald, T., Winterhalder, M., Voss, H. U., Timmer, J., and Schulze-Bonhage, A., How well can epileptic seizures be predicted? An evaluation of a nonlinear method. Brain 12:2616–2626, 2003.

    Article  Google Scholar 

  4. Babloyantz, A., and Destexhe, A., Low-dimensional chaos in an instance of epilepsy. Proc Nat’l Acad Sci USA 18(10):3513–3517, 1986.

    Article  Google Scholar 

  5. Breiman, L., Random Forests. Mach Learn 45:5–32, 2001.

    Article  MATH  Google Scholar 

  6. Cataltepe, Z., Genc, H. M., and Pearson, T., A PCA/ICA based feature selection method and its application for corn fungi detection, 15th European Signal Processing Conference (EUSIPCO 2007). EURASIP, Poznan, pp. 970–974, 2007.

    Google Scholar 

  7. Chua, K. C., Chandran, V., Acharya, U. R., and Lim, C. M., Higher order spectral (HOS) analysis of epileptic EEG signals, 29th IEEE-EMBS-2007, Lyon, 6495–6498, 2007.

  8. Chua, K. C., Chandran, V., Acharya, U. R., and Lim, C. M., Automatic identification of epileptic electroencephalography signals using higher-order spectra. Proc Inst Mech Eng H J Eng Med 223(4):485–495, 2009.

    Article  Google Scholar 

  9. Chua, K. C., Chandran, V., Acharya, U. R., Lim, C. M., Application of higher order spectra to identify epileptic EEG. J. Med. Syst., 2010, (In Press).

  10. Chua, K. C., Chandran, V., Acharya, U. R., and Lim, C. M., Analysis of epileptic EEG signals using higher order spectra. J Med Eng Technol UK 33(1):42–50, 2009.

    Article  Google Scholar 

  11. Cockerell, O. C., Hart, Y. M., Sander, J. W. A. S., Goodridge, D. M. G., Shorvon, S. D., and Johnson, A. L., Mortality from epilepsy: Results from a prospective population-based study. Lancet 344:918–921, 1994.

    Article  Google Scholar 

  12. EEG time series database. http://www.meb.unibonn.de/epileptologie/science/physik/eegdata

  13. Acharya, U. R., Chua, E. C. P., Chua, K. C., Lim, C. M., and Tamura, T., Analysis and automatic identification of sleep stages using higher order spectra. Int J Neural Syst 20(6):509–521, 2010.

    Article  Google Scholar 

  14. Faust, O., Acharya, U. R., and Lim, C. M., Automatic identification of epileptic and background EEG signals using frequency domain parameters. Int J Neural Syst 20(2):159–176, 2010.

    Article  Google Scholar 

  15. Frank, E., Wang, Y., Inglis, S., Holmes, G., and Witten, I. H., Using model trees for classification. Mach Learn 32(1):63–76, 1998.

    Article  MATH  Google Scholar 

  16. Freeman, W. J., Simulation of chaotic EEG patterns with a dynamic model of the olfactory system. Biol Cybern 56:139–150, 1987.

    Article  Google Scholar 

  17. Golub, G. H., and Van Loan, C. F., Matrix computations. Johns Hopkins University Press, Baltimore, 1989.

    MATH  Google Scholar 

  18. Guler, N. F., Ubey, E. D., and Guler, I., Recurrent neural network employing Lyapunovexponents for EEG signals classification. Exp Syst Appl 29(3):506–514, 2005.

    Article  Google Scholar 

  19. Hosmer, D. W., and Lemeshow, S., Applied Logistic Regression. Wiley, New York, 1989.

    Google Scholar 

  20. Iasemidis, L. D., Zaveri, H. P., Sachellares, J. C., and Williams, W. J., Linear and nonlinear modeling of ECoG in temporal lobe epilepsy. Proceedings of the 25th annual rocky mountain bioengineering symposium 24:187–193, 1988.

    Google Scholar 

  21. Rodriguez, J. J., Kuncheva, L. I., and Alonso, C. J., Rodriguez, Ludmila I. Kuncheva, and Carlos J. Alonso, “Rotation Forest: A New Classifier Ensemble Method”. IEEE Trans Pattern Anal Mach Intell 28:1619–1620, 2006.

    Article  Google Scholar 

  22. Landwehr, N., Hall, M., and Frank, E., Logistic model trees. Mach Learn 59:161–205, 2005.

    Article  MATH  Google Scholar 

  23. Kannathal, N., Lim, C. M., Acharya, U. R., and Sadasivan, P. K., Entropies for detection of epilepsy in EEG. Comput Methods Programs Biomed 80(3):187–194, 2005.

    Article  Google Scholar 

  24. Kannathal, N., Acharya, U. R., Lim, C. M., and Sadasivan, P. K., Characterization of EEG—A comparative study. Comp Meth Prog Biomed 80(1):17–23, 2005.

    Article  Google Scholar 

  25. Ya Kaplan, A., and Shishkin, S. L., Application of the change-point analysis to the investigation of the brain’s electrical activity, [book auth.]. In: Brodsky, B. E., and Darkhovsky, B. S. (Eds.), Nonparametric statistical disgnosis: Problems and methods. Kluwer Academic Publishers, Dordrecht, pp. 333–388, 2000.

    Google Scholar 

  26. Lagerlund, T. D., Sharbrough, F. W., and Busacker, N. E., Spatial filtering of multichannel electroencephalographic recordings through principal component analysis by singular velue decomposition. J Clin Neurophysiol 14(1):73–82, 1997.

    Article  Google Scholar 

  27. Li, G. Z., Bu, H. L., Yang, M. Q., Zeng, X. Q., and Yang, J. Y., “Selecting subsets of newly extracted features from PCA and PLS in microarray data analysis” IEEE 7th International Conference on Bioinformatics and Bioengineering at Harvard Medical School. BMC Genomics, Boston, pp. 14–17, 2008.

    Google Scholar 

  28. Lange, H. H., Lieb, J. P., Engel, J., Jr., and Crandall, P. H., Temporo-spatial paterns of preictal spike activity in human temporal lobe epilepsy. Electroencephalogr Clin Neurophysiol 56:543–555, 1983.

    Article  Google Scholar 

  29. Lotte, F., Congedo, M., Lecuyer, A., Lamarche, F., and Arnaldi, B., A review of classification algorithms for EEG-based brain-computer interfaces. J Neural Eng 4:R1–R13, 2007.

    Article  Google Scholar 

  30. Malhi, A., and Gao, R. X., PCA-based feature selection scheme for machine defect classification. IEEE Trans Instrum Meas 53:1517–1525, 2004.

    Article  Google Scholar 

  31. Martinerie, J., Adam, C., Quyen, M. L. V., Baulac, M., Clemenceau, S., Renault, B., and Varela, F. J., Epileptic seizures can be anticipated by non-linear analysis. Nature Med 4(10):1173–1176, 1998.

    Article  Google Scholar 

  32. Mayer-Kress, G., and Layne, S. P., Dimensionality of the human electroencephalogram. Ann NY Acad Sci 504:62–87, 1987.

    Article  Google Scholar 

  33. Mohoney, C. M. W., and Drineas, P., Unsupervised feature selection for principal component analysis boutsidis. KDD’08, Las Vegas, Nevada: ACM, 2008, pp. 61–69.

  34. Mormann, F., Thomas, K., Chrisophy, R., Andrzejak, R., Kraskov, A., David, P., Elger, C. E., and Lehnertz, K., On the predictability of epileptic seizures. Clin Neurophysiol 116:569–587, 2005.

    Article  Google Scholar 

  35. Mormann, F., Andrzejak, R. G., Elger, C. E., and Lehnertz, K., Seizure prediction: The long and winding road. Brain 130:314–333, 2007.

    Article  Google Scholar 

  36. Ng, T. T., Chang, S. F., Sun, Q., Blind detection of photomontage using higher order statistics. IEEE Int. Symp. Circuits Syst. (ISCAS), 2004.

  37. Nigam, V. P., and Graupe, D., A neural-network-based detection of epilepsy. Neurol Res 26(6):55–60, 2004.

    Article  Google Scholar 

  38. Pijn, J. P., Neerven, J. V., Noest, A., and Silva, F. L., Chaos or noises in EEG signals; dependence on state and brain site. Electroencephalogr Clin Neurophysiol 79:371–381, 1991.

    Article  Google Scholar 

  39. Polat, K., and Guenes, S., Classification of epileptiform EEG using a hybrid systems based on decision tree classifier and fast fourier transform. Appl Math Comput 32(2):625–631, 2007.

    Google Scholar 

  40. Quinlan, R. J., “Learning with Continuous Classes” 5th Australian Joint Conference on Artificial Intelligence, pp. 343–348, 1992.

  41. Sadati, N., Mohseni, H. R., and Magshoudi, A., Epileptic Seizure Detection Using Neural Fuzzy Networks. Proc. IEEE Int. Conf. Fuzzy Syst., Canada 596–600, 2006.

  42. Shoeb, A. H., “Application of machine learning to epileptic seizure onset detection and treatment”, MIT PhD thesis, 2009. http://dspace.mit.edu/handle/1721.1/54669

  43. Skarda, C. A., and Freeman, W. J., How brains make chaos in order to make sense of the world. Behav Brain Sci 19:161–195, 1987.

    Article  Google Scholar 

  44. Srinivasan, V., Eswaran, C., and Sriraam, N., Approximate entropy-based epileptic EEG detection using artificial neural networks. IEEE Trans Inf Technol Biomed 11(3):288–295, 2007.

    Article  Google Scholar 

  45. Subasi, A., EEG signal classification using wavelet feature and a mixture of expert model. Expert Syst Appl 32(4):1084–1093, 2006.

    Article  Google Scholar 

  46. Subasi, A., Signal classification using wavelet feature extraction and a mixture of expert model. Exp Syst Appl 32(4):1084–1093, 2007.

    Article  Google Scholar 

  47. Subasia, A., and Ercelebi, E., Classification of EEG signals using neural network and logistic regression. Comput Methods Programs Biomed 78:87–99, 2005.

    Article  Google Scholar 

  48. Wang, Y., and Witten, I. H., Induction of model trees for predicting continuous classes. Poster papers of the 9th European Conference on Machine Learning, 1997.

  49. Witten, I. H., and Frank, E., Data Mining: Practical Machine Learning Tools and Techniques. Morgan Kaufmann, 2005.

  50. Zhang, J., Zheng, C., Jiang, D., et al., Bispectrum analysis of focal ischemic cerebral EEG signal. Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society 20:2023–2026, 1998.

    Google Scholar 

  51. Zhou, S. M., Gan, J. Q., and Sepulveda, F., Classifying mental tasks based on features of higher-order statistics from EEG signals in brain-computer interface. Inf Sci 178(6):1629–1640, 2008.

    Article  Google Scholar 

Download references

Acknowledgment

The current work is funded by the NSF EPSCoR CyberTools project under award #EPS-0701491.

Author information

Authors and Affiliations

  1. Department of Computer Science, Louisiana Tech University, Ruston, LA, 71272, USA

    Xian Du & Sumeet Dua

  2. School of Medicine, Louisiana State University Health Sciences Center, New Orleans, 70112, LA, USA

    Sumeet Dua

  3. Department of Electrical and Computer Engineering, Ngee Ann Polytechnic, Singapore, 599489, Singapore

    Rajendra U. Acharya & Chua Kuang Chua

Authors
  1. Xian Du
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sumeet Dua
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Rajendra U. Acharya
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Chua Kuang Chua
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Sumeet Dua.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Du, X., Dua, S., Acharya, R.U. et al. Classification of Epilepsy Using High-Order Spectra Features and Principle Component Analysis. J Med Syst 36, 1731–1743 (2012). https://doi.org/10.1007/s10916-010-9633-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10916-010-9633-6

Keywords

Search

Navigation