Classification of Normal and Epileptic Seizure EEG Signals Based on Empirical Mode Decomposition - Complex System Modelling and Control Through Intelligent Soft Computations - page 379

obtained geometrical patterns help to compute the area of analytic signal
representation in complex plane with 95 % CTM and 95 % con dence area of ellipse

in SODP. It has been found that these two area parameters have signi

cantly higher
values for seizure EEG signals as compared to normal EEG signals. The perfor-
mance of LS-SVM classi er is best when RBF kernel has been employed to create

decision boundary between two classes (normal and seizure) and consequently have
provided 100 % classi cation accuracy. The features of the proposed method are

suitable for real time implementation of an expert system for detection of the epi-
leptic seizure in EEG signals. This system can act as an important diagnostic tool for
clinician to detect the epilpesy automatically by analysing EEG signals.
In future, performance of the proposed methodology can be evaluated for
classi cation between different classes of EEG signals like normal, inter-ictal and

ictal EEG signals. The future direction of research may also include the application
of the proposed methodology for identi

cation of different psychological states of
brain from EEG signals. Moreover, it would be of interest to study the expert
system based on the proposed methodology for classi cation of other signals like

electromyogram (EMG) signals, center of pressure (COP) signals, electrocardio-
gram (ECG), and speech signals corresponding to normal and abnormal conditions.

References

Accardo, A., Af nito, M., Carrozzi, M., & Bouquet, F. (1997). Use of the fractal dimension for the
analysis of electroencephalographic time series. Biological Cybernetics, 77, 339 - 350.
Acharya, U. R., Sree, S. V., Alvin, A. P. C., & Suri, J. S. (2012). Use of principal component
analysis for automatic classification of epileptic EEG activities in wavelet framework. Expert
Systems with Applications, 39(10), 9072 9078.

Acharya, U. R., Sree, S. V., Swapna, G., Martis, R. J., & Suri, J. S. (2013). Automated EEG
analysis of epilepsy: A review. Knowledge-Based Systems, 45, 147

-

165.
Adeli, H., Ghosh-Dastidar, S., & Dadmehr, N. (2007). A wavelet-chaos methodology for analysis
of EEGs and EEG sub-bands to detect seizure and epilepsy. IEEE Transactions on Biomedical
Engineering, 54(2), 205

-

211.
Altunay, S., Telatar, Z., & Erogul, O. (2010). Epileptic EEG detection using the linear prediction
error energy. Expert Systems with Applications, 37(8), 5661

-

5665.
Amoud, H., Snoussi, H., Hewson, D. J., and Duch ê ne, J. (2007). Hilbert-Huang transformation:
Application to postural stability analysis. In: 29th Annual International Conference of the IEEE
Engineering in Medicine and Biology Society (pp. 1562 - 1565), Lyon, France , 29 - 23 Aug
2007.
Andrzejak, R. G., et al. (2001). Indications of nonlinear deterministics and finite-dimensional
structures in time series of brain electrical activity: Dependence on recording region and brain
state. Physical Review E, 64(6), 061907.
Aurlien, H., et al. (2004). EEG background activity described by a large computerized database.
Clinical Neurophysiology, 115(3), 665

-

673.
Azar, A. T., & El-Said, S. A. (2014). Performance analysis of support vector machines classifier in
breast cancer mammography recognition. Neural Computings and Applications. 24(5),
1163

-

1177. doi: 10.1007/S00521-012-1324-4 .
Bajaj, V., & Pachori, R. B. (2012). Classification of seizure and nonseizure EEG signals using
empirical mode decomposition. IEEE Transactions on Information Technology in Biomedi-
cine, 16(6), 1135

-

1142.

-