Epileptic Seizures Detection based on Empirical Mode Decomposition and Hilbert-Huang transform of EEG Signal
DOI:
https://doi.org/10.21928/juhd.v1n2y2015.pp295-299Keywords:
Empirical Mode Decomposition, Hilbert-Huang transform, EEG Signal, Support Vector MachinesAbstract
The electrical activities of brain fluctuate frequently and can be analyzed using electroencephalogram (EEG) signals. We present a new method for classification of ictal and seizure-free intracranial EEG recordings. The proposed method uses the application of multivariate empirical mode decomposition (MEMD) algorithm combines with the Hilbert transform as the Hilbert-Huang transform (HHT) and analyzing spectral energy of the intrinsic mode function of the signal. EMD uses the characteristics of signals to adaptively decompose them to several intrinsic mode functions (IMFs). Hilbert transforms (HTs) are then used to transform the IMFs into instantaneous frequencies (IFs), to obtain the signals time-frequency-energy distributions. Classification of the EEG signal that is epileptic seizure exists or not has been done using support vector machine. The algorithm was tested in 6 intracranial channels EEG records acquired in 9 patients with refractory epilepsy and validated by the Epilepsy Center of the University Hospital of Freiburg. The experimental results show that the proposed method efficiently detects the presence of epileptic seizure in EEG signals and also showed a reasonable accuracy in detection.
References
[2] Ouali M. S., Ait-Kadi D., and Rezg N. Fault diagnosis model based on Petri net with fuzzy colors. Computers and Industrial Engineering , 37(12):173176, 1999.
[3] Y. Power and P. A. Bahri. A two-step supervisory fault diagnosis framework. Computers and Chemical Engineering, 28(11):21312140, 200.
[4] Lefebvre D., Delherm C., Fault detection and isolation of discrete event systems with Petri net models, IEEE TASE, Vol. 4, nu. 1, pp. 114118, January 2007.
[5] Lefebvre D., Delherm C., Diagnosis of DES with Petri nets models, accepted for publication IEEE TASE , 2006.
[6] C.A. Petri. Kommunication mit Automaten. PhD thesis, Institut fur Instrumentelle Mathematik, Schriften des IIM, No. 3, Bonn, Germany, 1962. [cited at p. 4, 24]
[7] Bello, M. G. “Enhanced training algorithms, and integrated training/architecture selection for multi layer perceptron networks,” IEEE Trans.on Neural Net., vol. 3, pp. 864-875, 1992.
[8] Rumelhart, D. E., Hinton, G. E. and Williams, R. J, “Learning internal representations by error propagation,” In Parallel Distributed Processing, Cambridge, MA: MIT Press, vol 1, pp. 318-362.
[9] Werbos, P. J. “Back-propagation: Past and future,” Proceeding of International Conference on Neural Networks, San Diego, CA, 1, pp.343-354, 1988.
[10] Salvetti, A. and Wilamowski, B. M., “Introducing Stochastic Process within the backpropagation Algorithm for Improved Convergence”, presented at ANNIE'94 – Artificial Neural Networks in Engineering, st. Louis, Missouri, USA, November 13-16, 1994; also in Intelligent Engineering Systems Through Artificial Neural Networks vol 4, pp. 205- 209, ed. C. H. Dagli, B. R. Fernandez, J. Gosh, R.T. S. Kumara, ASME PRESS, New York 1994.
[11] Hagan, M. T. and Menhaj, M., “Training feedforward networks with the Marquardt algorithm”, IEEE Transactions on Neural Networks, vol.5, no. 6, pp. 989- 993, 1994.
[12] S. Ould El Mehdi, E. Leclercq and D. Lefebvre, Petri nets design and identification for the diagnosis of discrete event systems, IAR-ACD Annual Meeting Nancy, workshop on Advanced Control and Diagnosis, 2006.
