An Improved Method for Classification of Epileptic EEG Signals based on Spectral Features using k-NN

International Journal of Electronics and Communication Engineering

© 2015 by SSRG - IJECE Journal

Volume 2 Issue 7

Year of Publication : 2015

Authors : Anu V. S.and Paul Thomas

10.14445/23488549/IJECE-V2I7P108

How to Cite?

Anu V. S.and Paul Thomas, "An Improved Method for Classification of Epileptic EEG Signals based on Spectral Features using k-NN," SSRG International Journal of Electronics and Communication Engineering, vol. 2,  no. 7, pp. 22-25, 2015. Crossref, https://doi.org/10.14445/23488549/IJECE-V2I7P108

Abstract:

In this paper, a method for classification of epileptic EEG signals based on k-NN classifier is discussed. This scheme provides an improved performance in terms of sensitivity, specificity and accuracy. EEG signal is decomposed into sub bands using multi-wavelet transform and spectral features such as mean spectral magnitude, spectral entropy, and spectral squared entropies are extracted. The distributions of these features for normal and epileptic EEG signal are clustered in different regions which can be utilized to yield good classification result. The results show that classification of these features using k-NN achieved an accuracy of 98.585%. In order to evaluate the efficiency of the proposed method, classification is also done using ANN and SVM which yielded an accuracy of 98.415% and 87.5% respectively

Keywords:

Epilepsy, Spectral Features, k-NN classifier, Artificial Neural Network, Support Vector Machine

References:

[1]K Lehnertz, F Mormann, T Kreuz, et al. “Seizure prediction by nonlinear EEG analysis” IEEE Engineering in Medicine and Biology Magazine 22(1), 57–63 (2003). 
[2]A Subasi, “Epileptic seizure detection using dynamic wavelet network. Expert Systems with Applications” 29(2), 343–355 (2005). 
[3]Yatindra Kumar, M.L Dewal and R.S Anand, "Wavelet Entropy Based EEG Analysis for Seizure Detection" in Biomedical Engineering and Informatics (BMEI), 2013 International Conference pp. 878-882.
[4]Subasi A. “Epileptic seizure detection using dynamic wavelet network”; Expert Systems with Applications 2005; 29(2):343–55.
[5]Subasi A. “EEG signal classification using wavelet feature extraction and a mixture of expert model”; Expert Systems with Applications 2007; 32(4): 1084–93.
[6]Kalayci T, Ozdamar O. “Wavelet preprocessing for automated neural network detection of EEG spikes”  IEEE Engineering in Medicine and Biology Magazine 1995; 14(2):160-6.
[7]Ling Guo, Daniel Rivero, Alejandro Pazos. “Epileptic seizure detection using multiwavelet transform based approximate entropy and artificial neural networks”; Journal of Neuroscience Methods 193 (2010) 156–163.
[8]Zisheng Zhang, Student Member, IEEE, and Keshab K. Parhi, Fellow, IEEE, “Seizure Detection using Wavelet Decomposition of the Prediction Error Signal from a Single Channel of Intra-Cranial EEG”; 2014, IEEE.
[9]V Srinivasan, C Eswaran, N Sriraam, Approximate entropy-based epileptic EEG detection using artificial neural networks. IEEE Transactions on Information Technology in Biomedicine 11(3), 288–295 (2007). 
[10]V Srinivasan, C Eswaran, AN Sriraam, Artificial neural network based epileptic detection using time-domain and frequency-domain features. Journal of Medical Systems 29(6), 647–660 (2005).
[11]S Ghosh-Dastidar, H Adeli, N Dadmehr, Mixed-band wavelet-chaos-neural network methodology for epilepsy and epileptic seizure detection. IEEE Transactions on Biomedical Engineering 54(9), 1545–1551 (2007).  
[12]S Ghosh-Dastidar, H Adeli, N Dadmehr, Principal component analysis-enhanced cosine radial basis function neural network for robust epilepsy and seizure detection. IEEE Transactions on Biomedical Engineering 55(2), 512–518 (2008). 
[13]AAlkan, E Koklukaya, A Subasi, Automatic seizure detection in EEG using logistic regression and artificial neural network. Journal of Neuroscience Methods 148(2), 167–176 (2005).  
[14]N Acır, İ Öztura, M Kuntalp, B Baklan, C Güzeliş, Automatic detection of epileptiform events in EEG by a three-stage procedure based on artificial neural networks. IEEE Transactions on Biomedical Engineering 52(1), 30–40 (2005).  
[15]Andrzejak R, Lehnertz K, Mormann F, Rieke C, David P, Elger C. “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 2001;64(6):061907-1–8.
[16]Chua K. C, Chandran V, RajendraAcharya, Lim C. M. “Automatic Identification of Epilepsy by HOS and Power Spectrum parameters using EEG Signals: A comparative study” in 30 th Annual International IEEE EMBS Conference Vancouver,BritishColumbia,Canada,August 20-24, 2008.
[17]Oliver Sutton, “ Introduction to k Nearest Neighbor Classification and Condensed Nearest Neighbor Data Reduction”; February, 2012.
[18]S. M. ShafiulAlam and M. I. H. Bhuiyan, Member, IEEE, “Detection of Seizure and Epilepsy Using Higher Order Statistics in the EMD Domain”; IEEE Journal of Biomedical and Health Informatics, Vol. 17, No. 2, March 2013.