Automated diagnosis of epileptic electroencephalogram using independent component analysis and discrete wavelet transform for different electroencephalogram durations
Restricted accessResearch articleFirst published online March, 2013
Automated diagnosis of epileptic electroencephalogram using independent component analysis and discrete wavelet transform for different electroencephalogram durations
Epilepsy is a disorder of the brain depicted by recurrent seizures. Electroencephalogram signals can be used to study the characteristics of epileptic seizures. In this study, we propose a method for the automated classification of electroencephalogram into normal, interictal and ictal classes using 6, 12, 18 and 23.6 s of data. We employed discrete wavelet transform to decompose electroencephalogram signals into frequency sub-bands. These discrete wavelet transform coefficients were then subjected to independent component analysis for reducing the data dimension. The independent component analysis features were then fed to six classifiers, namely, decision tree, K-nearest neighbor, probabilistic neural network, fuzzy, Gaussian mixture model and support vector machine to select the best classifier. We observed that the support vector machine classifier with radial basis function kernel function gave the best results with an average accuracy of 96%, sensitivity of 96% and specificity of 97% for 23.6 s of electroencephalogram data. Our results show that as the duration of the data increases, the classification accuracy increases. This proposed technique can be used as an automatic seizure monitoring software to aid the doctors in providing timely quality care for the patients suffering from epilepsy.
CoyleDMcGinnityTMPrasadG. Improving the separability of multiple EEG features for a BCI by neural-time-series-prediction-preprocessing. Biomed Signal Proces2010; 5(3): 196–204.
5.
InceNFGoksuFTewfikAH. Adapting subject specific motor imagery EEG patterns in space–time–frequency for a brain computer interface. Biomed Signal Proces2009; 4(3): 236–246.
6.
RuizRASRantaRLouis-DorrV. EEG montage analysis in the Blind Source Separation framework. Biomed Signal Proces2010; 6(1): 77–84.
RezekIARobertsSJ. Stochastic complexity measures for physiological signal analysis. IEEE Trans Biomed Eng1998; 45(9): 1186–1191.
9.
SchraagSBothnerUGajrajR. The performance of electroencephalogram bispectral index and auditory evoked potential index to predict loss of consciousness during propofol infusion. Anesth Analg1999; 89(5): 1311–1315.
10.
StamCJVan der LeijEMHKeunenRWM. Nonlinear EEG changes in postanoxic encephalopathy. Theor Biosci1999; 118: 209–218.
11.
SubhaDPJosephKPAcharyaUR. EEG signal processing: a survey. J Med Syst2010; 34(2): 195–212.
12.
RavelliFAntoliniR. Complex dynamics underlying the human electroencephalogram. Biol Cybern1992; 67: 57–65.
13.
AndrzejakRGLehnertzKRieke MormannF. Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: dependence on recording region and brain state. Phys Rev E2001; 64: 558061907.
14.
VitterliM. Wavelet and filter banks: theory and design. IEEE T Signal Proces1992; 40(9): 2207–2232.
15.
MeyerY. Wavelets and applications. Paris/Berlin: Masson/Springer-Verlag, 1992.
16.
AdeliHZhouZDadmehrN. Analysis of EEG records in an epileptic patient using wavelet transform. J Neurosci Methods2003; 123(1): 69–87.
17.
SubasiAGursoyMI. EEG signal classification using PCA, ICA, LDA and support vector machines. Expert Syst Appl2010; 37: 8659–8666.
18.
DudaROHartPEStorkDG. Pattern classification. New York, NY, USA, John Wiley & Sons Inc., 2006.
HanJKamberMPeiJ. Data mining: concepts and techniques. San Fransisco, CA, USA, Morgan Kaufmann, 2005.
22.
HaykinS. Neural networks and learning machines. New Jersey, USA, Prentice Hall, 2008.
23.
BilmesJAGentleA. Tutorial of the EM algorithm and its application to parameter estimation for Gaussian mixture and hidden Markov models. Berkeley, CA, USA, International Computer Science Institute, 1998.
24.
VapnikV. Statistical learning theory. New York, NY, USA, Wiley-Interscience, 1998.
25.
PetitmenginCBaulacMNavarroV. Seizure anticipation: are neurophenomenological approaches able to detect preictal symptoms?Epilepsy Behav2006; 9(2): 298–306.
26.
ChuaCKChandranVAcharyaUR. Application of higher order spectra to identify epileptic EEG. J Med Syst2011; 35(6): 1563–1571.
27.
KannathalNLimCMAcharyaUR. Entropies for detection of epilepsy in EEG. Comput Methods Programs Biomed2005; 80(3): 187–194.
28.
LehnertzKElgerCE. Can epileptic seizures be predicted? Evidence from nonlinear time series analyses of brain electrical activity. Phys Rev Lett1988; 80: 5019–5023.
29.
MartinerieJAdamCLe van QuyenM. Can epileptic crisis be anticipated?Nat Med1998; 4: 1173–1176.
Ghosh-DastidarSAdeliH. Improved spiking neural networks for EEG classification and epilepsy and seizure detection. Integr Comput-Aid E2007; 14(3): 187–212.
32.
Ghosh-DastidarSAdeliHDadmehrN. Mixed band wavelet-chaos-neural network methodology for epilepsy and epileptic seizure detection. IEEE Trans Biomed Eng2007; 54(9): 1545–1551.
33.
Ghosh-DastidarSAdeliHDadmehrN. Principal component analysis enhanced cosine radial basis function neural network for robust epilepsy and seizure detection. IEEE Trans Biomed Eng2008; 55(2): 512–518.
34.
Ghosh-DastidarSAdeliH. A new supervised learning algorithm for multiple spiking neural networks with application in epilepsy and seizure detection. Neural Netw2009; 22(10): 1419–1431.
35.
ChuaCKChandranVAcharyaUR. Automatic identification of epileptic EEG signals using higher order spectra. Proc IMechE, Part H: J Engineering in Medicine2009; 223(4): 485–495.
36.
AcharyaURChuaKCLimTC. Automatic identification of epileptic EEG signals using nonlinear parameters. J Mech Med Biol2009; 9(4): 539–553.
37.
FaustOAcharyaURLimCM. Automatic identification of epileptic and background EEG signals using frequency domain parameters. Int J Neural Syst2010; 20(2): 159–176.
38.
AcharyaURSreeSVChattopadhyayS. Application of recurrence quantification analysis for the automated identification of epileptic EEG signals. Int J Neural Syst2011; 21(3): 199–211.
39.
AcharyaURSreeSVSuriJS. Automatic detection of epileptic EEG signals using higher order cumulant features. Int J Neural Syst2011; 21(5): 1–12.
40.
AcharyaURMolinariFSreeSV. Automated diagnosis of epileptic EEG using entropies. Biomed Signal Proces2012; 7(4): 401–408.
41.
AcharyaURSreeSVSuriJS. Use of principal component analysis for automatic detection of epileptic EEG activities. Expert Syst Appl2012; 30(10): 9072–9078.
42.
MartisRJAcharyaURJenTH. Application of empirical mode decomposition (EMD) for automated detection of epilepsy using EEG signals. Int J Neural Syst. 2012. DOI: 10.1142/S012906571250027.
43.
AcharyaURSreeSVAlvinAPC. Application of non linear and wavelet based features for the automated identification of epileptic EEG signals. Int J Neural Syst2012; 22: 1250002.
