Diagnosing epileptic seizures by EEG signals using multilayer perceptron

E. S. Guido *

Department of Electrical Engineering, School of Engineering at São Carlos and Institute of Physics at Sao Carlos, University of São Paulo, SP, Brazil

Abstract

The aim of this study is to select appropriate electroencephalography (EEG) signals which can distinguish between healthy, convulsive, and epileptic signals. The proposed model can achieve this end with a high accuracy. A set of EEG signals for five different conditions was used. It was adopted from the University of Bonn, Germany. Using discrete wavelet transform, EEG signals were decomposed into their frequency sub-bands for extracting their optimal features. Having extracted the features, EEG signals were divided into target groups using multilayer perceptron (MLP). The proposed model achieved an accuracy of 98.33% in diagnosing and categorizing epileptic EEG signals. Since the visual and experimental analysis of EEG signals have limitations, the proposed method can play a vital role in helping physicians and specialists.

Keywords

Convulsive, Electroencephalography, MLP, Confusion matrix

Digital Object Identifier (DOI)

https://doi.org/10.21833/AEEE.2019.01.001

Article history

Received 1 October 2018, Received in revised form 1 January 2019, Accepted 2 January 2019

Full text

DownloadAvailable in PDF
Portable Document Format

How to cite

Guido ES (2019). Diagnosing epileptic seizures by EEG signals using multilayer perceptron. Annals of Electrical and Electronic Engineering, 2(1): 1-5

References (25)

  1. Aarabi A, Fazel-Rezai R, and Aghakhani Y (2009). A fuzzy rule-based system for epileptic seizure detection in intracranial EEG. Clinical Neurophysiology, 120(9): 1648-1657. https://doi.org/10.1016/j.clinph.2009.07.002   [Google Scholar]  
  2. Abibullaev B, Kim MS, and Seo HD (2010). Seizure detection in temporal lobe epileptic EEGs using the best basis wavelet functions. Journal of Medical Systems, 34(4): 755-765. https://doi.org/10.1007/s10916-009-9290-9   [Google Scholar] 
  3. Adeli H, Ghosh-Dastidar S, and Dadmehr N (2007). A wavelet-chaos methodology for analysis of EEGs and EEG subbands to detect seizure and epilepsy. IEEE Transactions on Biomedical Engineering, 54(2): 205-211. https://doi.org/10.1109/TBME.2006.886855   [Google Scholar] 
  4. Andrzejak RG, Lehnertz K, Mormann F, Rieke, C, David P, and Elger CE (2001). Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: Dependence on recording region and brain state. Physical Review E, 64(6): 061907. https://doi.org/10.1103/PhysRevE.64.061907   [Google Scholar] 
  5. Chan AM, Sun FT, Boto EH, and Wingeier BM (2008). Automated seizure onset detection for accurate onset time determination in intracranial EEG. Clinical Neurophysiology, 119(12): 2687-2696. https://doi.org/10.1016/j.clinph.2008.08.025   [Google Scholar] 
  6. Deburchgraeve W, Cherian PJ, De Vos M, Swarte RM, Blok JH, Visser GH, and Van Huffel S (2008). Automated neonatal seizure detection mimicking a human observer reading EEG. Clinical Neurophysiology, 119(11): 2447-2454. https://doi.org/10.1016/j.clinph.2008.07.281   [Google Scholar]  
  7. Dreiseitl S and Ohno-Machado L (2002). Logistic regression and artificial neural network classification models: A methodology review. Journal of Biomedical Informatics, 35(5): 352-359. https://doi.org/10.1016/S1532-0464(03)00034-0   [Google Scholar] 
  8. Durka PJ (2003). From wavelets to adaptive approximations: time-frequency parametrization of EEG. Biomedical Engineering Online, 2(1): 1-30. https://doi.org/10.1186/1475-925X-2-1   [Google Scholar] 
  9. Guo L, Rivero D, Dorado J, Rabunal JR, and Pazos A (2010). Automatic epileptic seizure detection in EEGs based on line length feature and artificial neural networks. Journal of Neuroscience Methods, 191(1): 101-109. https://doi.org/10.1016/j.jneumeth.2010.05.020   [Google Scholar] 
  10. Iasemidis LD (2003). Epileptic seizure prediction and control. IEEE Transactions on Biomedical Engineering, 50(5): 549-558. https://doi.org/10.1109/TBME.2003.810705   [Google Scholar] 
  11. Kannathal N, Choo ML, Acharya UR, and Sadasivan PK (2005). Entropies for detection of epilepsy in EEG. Computer Methods and Programs in Biomedicine, 80(3): 187-194. https://doi.org/10.1016/j.cmpb.2005.06. 012   [Google Scholar] 
  12. Khan YU, Farooq O, and Sharma P (2012). Automatic detection of seizure onset in pediatric EEG. International Journal of Embedded Systems and Applications, 2(3): 81-89. https://doi.org/10.5121/ijesa.2012.2309   [Google Scholar] 
  13. Livingstone DJ and Totowa NJ (2008). Artificial neural networks methods and application. 1th Edition, Hummana Press, New York, USA.   [Google Scholar]
  14. Meier R, Dittrich H, Schulze-Bonhage A, and Aertsen A (2008). Detecting epileptic seizures in long-term human EEG: A new approach to automatic online and real-time detection and classification of polymorphic seizure patterns. Journal of Clinical Neurophysiology, 25(3): 119-131. https://doi.org/10.1097/WNP.0b013e3181775993   [Google Scholar] 
  15. Mormann F, Kreuz T, Andrzejak RG, David P, Lehnertz K, and Elger CE (2003). Epileptic seizures are preceded by a decrease in synchronization. Epilepsy Research, 53(3): 173-185. https://doi.org/10.1016/S0920-1211(03)00002-0   [Google Scholar] 
  16. Niederhauser JJ, Esteller R, Echauz J, Vachtsevanos G, and Litt B (2003). Detection of seizure precursors from depth-EEG using a sign periodogram transform. IEEE Transactions on Biomedical Engineering, 50(4): 449-458. https://doi.org/10.1109/TBME.2003.809497   [Google Scholar]  
  17. Osorio I and Frei MG (2009). Real-time detection, quantification, warning, and control of epileptic seizures: The foundations for a scientific epileptology. Epilepsy and Behavior, 16(3): 391-396. https://doi.org/10.1016/j.yebeh.2009.08.024   [Google Scholar] 
  18. Polat K and Güneş S (2007). Classification of epileptiform EEG using a hybrid system based on decision tree classifier and fast Fourier transform. Applied Mathematics and Computation, 187(2): 1017-1026. https://doi.org/10.1016/j.amc.2006.09.022   [Google Scholar] 
  19. Shoeb A, Edwards H, Connolly J, Bourgeois B, Treves ST, and Guttag J (2004). Patient-specific seizure onset detection. Epilepsy and Behavior, 5(4): 483-498.   [Google Scholar]
  20. Sörnmo L and Laguna P (2005). Bioelectrical signal processing in cardiac and neurological applications. Vol. 8, Academic Press, Cambridge, Massachusetts, USA.   [Google Scholar]
  21. Stein AG, Eder HG, Blum DE, Drachev A, and Fisher RS (2000). An automated drug delivery system for focal epilepsy. Epilepsy Research, 39(2): 103-114. https://doi.org/10.1016/S0920-1211(99)00107-2   [Google Scholar] 
  22. Subasi A (2005). Epileptic seizure detection using dynamic wavelet network. Expert Systems with Applications, 29(2): 343-355. https://doi.org/10.1016/j.eswa.2005.04.007   [Google Scholar] 
  23. Tong S and Thakor NV (2009). Quantitative EEG analysis methods and clinical applications. Artech House, Norwood, Massachusetts, USA.   [Google Scholar] 
  24. Yuan Q, Zhou W, Li S, and Cai D (2011). Epileptic EEG classification based on extreme learning machine and nonlinear features. Epilepsy Research, 96(1): 29-38. https://doi.org/10.1016/j.eplepsyres.2011.04.013   [Google Scholar] 
  25. Zini G and d'Onofrio G (2003). Neural network in hematopoietic malignancies. Clinica Chimica Acta, 333(2): 195-201. https://doi.org/10.1016/S0009-8981(03)00186-4   [Google Scholar]