Classification and Feature Extraction of Electroencephalogram Signals for Epilepsy Using PCA, ICA, DWT and SVM Methods

Subject Areas : Renewable energy

Javad Ebrahimnejad ¹ (electrical engineering faculty, Najafabad azad university, Najafabad, Iran)
Mahkam Kahkesh ² (Digital Processing and Machine Vision Research center, Najafabad Branch, Islamic Azad University, Najafabad, Iran PhD Student of Control Engineering- Dept. of Electrical Engineering, Najafabad Branch, Islamic Azad University, Najafabad,)
Alireza Naghsh ³ (Digital Processing and Machine Vision Research center, Najafabad Branch, Islamic Azad University, Najafabad, Iran Assistant Professor – Dept. of Electrical Engineering, Najafabad Branch, Islamic Azad University, Najafabad, Isfahan, Iran)

Received: 2018-05-21 Accepted : 2018-09-12 Published : 2019-02-04

Keywords: EEG, PCA, epilepsy, EMD, ICA,

Abstract :

The purpose of this article is to classify electroencephalogram signals into two types of epilepsy and healthy.To achieve the highest accuracy, various techniques have been used. The desired characteristics of these signals can be extracted by Wavelet Transform and Empirical Mode Decomposition methods.These two methods are compared in terms of impact in the classification process. To reduce the dimensions of the feature space, Independent and principal Component Analysis methods can be used. Then, in order to reduce the effect of noise on electroencephalogram signal analysis, a smoothing method can be applied.Finally, by using Support Vector machine classifier, the existing data classified.These steps were tested for an existing data set, including 5 groups of single channel electroencephalogram signals. Results show that the empirical decomposition method has high efficiency and accuracy to extract the characteristics and classification of signals. Accordingly, the accuracy and sensitivity of both combinations of "empirical mode decomposition - independent component analysis" and "empirical mode decomposition - principal component analysis", after data smoothing, as a new approach to extraction and classification of features are 100%. The output of this system is used to control and treat the disease.

References:

[1] M.P. Hosseini, D. Pompili, K. Elisevich, H. Soltanian-Zadeh, "Optimized deep learning for EEG big data and seizure prediction BCI via internet of things", IEEE Trans. on Big Data, Vol. 3, No. 4, pp.392-404, Dec. 2017.

[2] J.A. Chambers, S. Sanei, "EEG signal processing",Vol. 1, No. 1, pp.1-215, Center of Digital Signal Processing Cardiff University, UK: John Wiley & Sons Ltd., 2007.

[3] A. Subasi, M.I. Gursoy, "EEG signal classification using PCA, ICA, LDA and support vector machines",Expert Systems with Applications, Vol. 37, No. 12, pp.8659-8666, Dec. 2010.

[4] B.H. Brinkmann et al., "Forecasting seizures using intracranial EEG measures and SVM in naturally occurring canine epilepsy",PloS one,Vol. 10, No. 8, pp.1-12, Aug. 2015, Available: https://doi.org/10.1371/journal.pone.0133900

[5] Z. Zhang,K.K. Parhi, "Low-complexity seizure prediction from iEEG/sEEG using spectral power and ratios of spectral power",IEEE transactions on biomedical circuits and systems,Vol. 10, No. 3, pp.693-706, Jun. 2016.

[6] N. Wang, M.R. Lyu, "Extracting and selecting distinctive EEG features for efficient epileptic seizure prediction", IEEE Journal of Biomedical and Health Informatics, Vol. 19, No. 5, pp.1648-1659, Sep. 2015.

[7] D. Coyle, G. Prasad, T.M. McGinnity, "Faster self-organizing fuzzy neural network training and a hyperparameter analysis for a brain–computer interface", IEEE Trans. on Systems, Man, and Cybernetics, Part B (Cybernetics), Vol. 39, No. 6, pp.1458-1471, Dec. 2009.

[8] M. Bagheri et al., "A study on the performance of classifiers and extracted features in discriminating EEG patterns of mental activities related to four main directions", Journal of Arak University of Medical Sciences, Vol. 18, No. 12, pp.11-23, Dec. 2016.

[9] A. McDonald et al., "Empirical Mode Decomposition of the atmospheric wave field", Annales Geophysicae,Vol. 25, No. 2, pp.375-384, Mar. 2007.

[10] J.C. Nunes, E. Deléchelle, "Empirical mode decomposition: Applications on signal and image processing", Advances in Adaptive Data Analysis, Vol. 1, No. 1, pp.125-175, Jan. 2009.

[11] A. Bouzalmat, J. Kharroubi, A. Zarghili, "Comparative study of PCA, ICA, LDA using SVM classifier", Journal of Emerging Technologies in Web Intelligence, Vol. 6, No. 1, pp.64-68, Feb. 2014.

[12] R.E. Kass, V. Ventura, C. Cai, "Statistical smoothing of neuronal data", Network Computation in Neural Systems, Vol. 14, No. 1, pp.5-16, Feb. 2003.

[13] K.P. Bennett, C. Campbell, "Support vector machines: hype or hallelujah?", Acm Sigkdd Explorations Newsletter, Vol. 2, No. 2, pp.1-13, Dec. 2000.

[14] R.J. Oweis, E.W. Abdulhay, "Seizure classification in EEG signals utilizing Hilbert-Huang transform", Biomedical engineering online, Vol. 10, No. 1, pp.38, Dec. 2011.

[15] K.D. Tzimourta, L.G. Astrakas, M.G. Tsipouras,"Wavelet based classification of epileptic seizures in EEG signals", IEEE 30th International Symposium on Computer-Based Medical Systems (CBMS), pp.35-39, 2017.

[16] H. LotfaliNejad, R. Keshvari, S. Shabroo, H.Moghaddas, "Comparison of MLP and RBF Neural Network Trends in Diagnosis of Epilepsy", National Conference on Electrical Engineering and Sustainable Development, Mashhad, Khavaran Higher Education Institute, 2013.

[17] M. Behnam, H. Pourghasem, "Epileptic seizure detection based on wavelet transform statistics map and EMD method for hilbert-huang spectral analyzing in gamma frequency band of EEG signals", Journal of Intelligent Procedures in Electrical Technology, Vol. 6, No. 22, pp.23-36, Jan. 2015.

[18] M. Hajian, A. Akbari Foroud, H. Norouzian, "Static voltage stability analysis by using svm and neural network", Journal of Intelligent Procedures in Electrical Technology, Vol. 4, No. 13, pp.3-14, Apr. 2013.