Diagnosis of Epilepsy from EEG signals using Hilbert Huang

Sandra Ibrić, Samir Avdaković, Ibrahim Omerhodžić, Nermin Suljanović, Aljo Mujčić



In this paper application of Hilbert-Huang transform (HHT) to electroencephalogram (EEG) signals analysis is presented, in order to simplify diagnosis of epilepsy. HHT consists of empirical mode decomposition (EMD) and Hilbert spectral analysis. Hilbert marginal spectrum represents a contribution of total amplitude (or energy) over various frequency values. This approach is used for analyzing 200 EEG signals, where half of all signals are from healthy subjects and the other half are signals of subjects with epileptic syndrome without seizure. It is showed that this method provides clear distinctions in visualisation of EEG signals of healthy and ill subjects, so that it can efficiently identificate epilepsy syndrome. Further, this approach can be a foundation for development of simple automated EEG signal classifiers in the aspect of recognition subjects with epilepsy syndrome and find its place in standard clinical practice.

Keywords: EEG, epilepsy, Hilbert Huang transform, Hilbert marginal spectrum


Full Text:



Avdakovic S., Omerhodzic I., Badnjevic A. and Boskovic

D., Diagnosis of Epilepsy from EEG signals using Global

Wawelet Power Spectrum,6th European Conference of the

International Federation for Medical and Biological EngineeringIFMBE

Proceedings Volume 45, 2015, pp 481-484

Hui Li, Yuping Zang and Haiqu Zheng (2008) Hilbert-

Huang transform and marginal spectrum for detection and

diagnosis of localized defects in roller bearings, Journal of

Mechanical Science and Technology 23 (2009) 291~301

ShayanMotamedi-Fakhret et al (2014), Signal processing

techniques applied to human sleep EEG signals—A review.

Biomedical Signal Processing and Control 10: 21-33

Huang, N., Shen, Z., Long, S., Wu, M., Shih, E., Zheng,

Q., Tung, C., Liu, H., (1998), The Empirical Mode Decomposition

Method and the Hilbert Spectrum for Non-Stationary

Time Series Analysis: Proceedings of the Royal Society of

London, A454, 903–995.

Huang, N., Wu, M.C., Long, S.R., Shen, S.S.P., Qu, W.,

Gloersen, P., Fan, K.L. (2003) A Confidence Limit for the

Empirical Mode Decomposition and Hilbert Spectral Analysis.

Proceedings of the Royal Society of London, A459,


Huang, N., Wu, Z., Long, S., Arnold, K., Chen, X., Blank,

K., (2009), On Instantaneous Frequency. Advances in Adaptive

Data Analysis, 1, 177–229.

Andrzejak RG, Lehnertz K, Rieke C, Mormann F, David

P, Elger CE. 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 Stat Nonlin Soft Matter Phys 2001; 64(6 Pt

:061907. Online available at: http://epileptologie-bonn.



Flandrin, P., Rilling, G. Goncalves, P. (2004), Empirical

Mode Decomposition as a Filter Bank. IEEE Signal Process.

Lett., 11, 112–114.

Battista, B., Knapp, C., McGee, T., Goebel, V. (2007).

Application of the Empirical Mode Decomposition and

Hilbert-Huang Transform to Seismic Reflection Data. Geophysics,

(2), H29–H37, doi: 10.1190/1.2437700.

Krbot, M. Električna aktivnost mozga i njezina primjena upreoperativnoj

procjeni lateralizacije govornefunkcije u pacijenata

s epilepsijom, FER Zagreb

Adeli H. Ghosh-Dastidar S, Dadmehr (2007). A wavelet-

chaos methodology for analysis of EEGs and EEG subbands

to detect seizure and epilepsy. IEEE Trans Biomed

Eng. 54(2):205-11.

Ibrahim Omerhodzic, Samir Avdakovic, Amir Nuhanovic,

Kemal Dizdarevic and Kresimir Rotim (2012). Energy Distribution

of EEG Signal Components by Wavelet Transform,

Wavelet Transforms and Their Recent Applications in

Biology and Geoscience, Dr. Dumitru Baleanu (Ed.), ISBN:

-953-51-0212-0, InTech, DOI: 10.5772/37914.

Omerhodzic I, Avdakovic S, Nuhanovic A, Dizdarevic

K. Energy distribution of EEG signals: EEG signal wavelet-

neural network classifier. World Academy of Science, Engineering

and Technology 2010; 61: 1190-5


  • There are currently no refbacks.