The classification of EEG signals using discretization-based entropy and the adaptive neuro-fuzzy inference system

A novel feature extraction called discretization-based entropy is proposed for use in the classification of EEG signals. To this end, EEG signals are decomposed into frequency subbands using the discrete wavelet transform (DWT), the coefficients of these subbands are discretized into the desired number of intervals using the discretization method, the entropy values of the discretized subbands are calculated using the Shannon entropy method, and these are then used as the inputs of the adaptive neuro-fuzzy inference system (ANFIS). The equal width discretization (EWD) and equal frequency discretization (EFD) methods are used for the discretization. In order to evaluate their performances in terms of classification accuracy, three different experiments are implemented using different combinations of healthy segments, epileptic seizure-free segments, and epileptic seizure segments. The experiments show that the EWD-based entropy approach achieves higher classification accuracy rates than the EFD-based entropy approach.

PDF

___

[1] Acharya UR, Molinari F, Sree SV, Chattopadhyay S, Ng KH, Suri JS. Automated diagnosis of epileptic EEG using entropies. Biomed Signal Proces 2012; 7: 401408.
[2] Pravin Kumar S, Sriraam N, Benakop PG, Jinaga BC. Entropies based detection of epileptic seizures with artificial neural network classifiers. Expert Syst Appl 2010; 37: 32843291.
[3] Aarabi A, Fazel-Rezai R, Aghakhani Y. A fuzzy rule-based system for epileptic seizure detection in intracranial EEG. Clin Neurophysiol 2009; 120: 16481657.
[4] Rivero D, Guo L, Seoane JA, Dorado J. Using genetic algorithms and k-nearest neighbor for automatic frequency band selection for signal classification. IET Signal Process 2012; 6: 186194.
[5] Guler I, Ubeyli ED. Adaptive neuro-fuzzy inference system for classification of EEG signals using wavelet coefficients. J Neurosci Meth 2005; 148: 113121.
[6] Subasi A. Application of adaptive neuro-fuzzy inference system for epileptic seizure detection using wavelet feature extraction. Comput Biol Med 2007; 37: 227244.
[7] Adeli H, Zhou Z, Dadmehr N. Analysis of EEG records in an epileptic patient using wavelet transform. J Neurosci Meth 2003; 123: 6987.
[8] Ubeyli ED. Combined neural network model employing wavelet coefficients for EEG signals classification. Digit Signal Process 2009; 19: 297308.
[9] Ubeyli ED. Analysis of EEG signals by combining eigenvector methods and multiclass support vector machines. Comput Biol Med 2008; 38: 1422.
[10] Ocak H. Automatic detection of epileptic seizures in EEG using discrete wavelet transform and approximate entropy. Expert Syst Appl 2009; 36: 20272036.
[11] Naghsh-Nilchi AR, Aghashahi M. Epilepsy seizure detection using eigen-system spectral estimation and multiple layer perceptron neural network. Biomed Signal Proces 2010; 5: 147157.
[12] Subasi A. EEG signal classification using wavelet feature extraction and a mixture of expert model. Expert Syst Appl 2007; 32: 10841093.
[13] Srinivasan V, Eswaran C, Sriraam N. Artificial neural network based epileptic detection using time-domain and frequency-domain features. J Med Syst 2005; 29: 647660.
[14] Srinivasan V, Eswaran C, Sriraam N. Approximate entropy-based epileptic EEG detection using artificial neural networks. IEEE T Inf Technol B 2007; 11: 288295
[15] Kannathal N, Lim CM, Acharya UR, Sadasivan PK. Entropies for detection of epilepsy in EEG. Comput Meth Prog Bio 2005; 80: 187194.
[16] Nigam VP, Graupe D. A neural-network-based detection of epilepsy. Neurol Res 2004; 26: 5560.
[17] Khan YU, Sepulveda F. Brain-computer interface for single trial EEG classification for wrist movement imagery using spatial filtering in the gamma band. IET Signal Process 2010; 4: 510517.
[18] Hsu CN, Huang HJ, Wong TT. Implications of the dirichlet assumption for discretization of continuous variables in naive Bayesian classifiers. Mach Learn 2003; 53: 235263.
[19] Andrzejak RG, Lehnertz K, Mormann F, Rieke C, David P, Elger CE. Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: dependence on recording region and brain state. Phys Rev E 2001; 64: 061907-1061907-8.
[20] Gonzalez RC, Woods RE. Digital Image Processing. 3rd ed. Upper Saddle River, NJ, USA: Pearson Prentice Hall, 2008.
[21] Orhan U, Hekim M, Ozer M. Epileptic seizure detection using probability distribution based on equal frequency discretization. J Med Syst 2012; 36: 22192224.
[22] Jang JSR. ANFIS: Adaptive-network based fuzzy inference systems. IEEE T Syst Man Cyb 1993; 23: 665685.
[23] Orhan U, Hekim M, Ozer M. EEG signals classification using the K-means clustering and a multilayer perceptron neural network model. Expert Syst Appl 2011; 38: 1347513481.
[24] Bishop CM. Neural Networks for Pattern Recognition. Oxford, UK: Oxford University Press, 2007.
[25] Altunay S, Telatar Z, Erogul O. Epileptic EEG detection using the linear prediction error energy. Expert Syst Appl 2010; 37: 56615665.
[26] Kocyigit Y, Alkan A, Erol H. Classification of EEG recordings by using fast independent component analysis and artificial neural network. J Med Syst 2008; 32: 1720.