Mixed-Band Wavelet-Chaos-Neural Network Methodology for Epilepsy and Epileptic Seizure Detection

A novel wavelet-chaos-neural network methodology is presented for classification of electroencephalograms (EEGs) into healthy, ictal, and interictal EEGs. Wavelet analysis is used to decompose the EEG into delta, theta, alpha, beta, and gamma sub-bands. Three parameters are employed for EEG representation: standard deviation (quantifying the signal variance), correlation dimension, and largest Lyapunov exponent (quantifying the non-linear chaotic dynamics of the signal). The classification accuracies of the following techniques are compared: 1) unsupervised-means clustering; 2) linear and quadratic discriminant analysis; 3) radial basis function neural network; 4) Levenberg-Marquardt backpropagation neural network (LMBPNN). To reduce the computing time and output analysis, the research was performed in two phases: band-specific analysis and mixed-band analysis. In phase two, over 500 different combinations of mixed-band feature spaces consisting of promising parameters from phase one of the research were investigated. It is concluded that all three key components of the wavelet-chaos-neural network methodology are important for improving the EEG classification accuracy. Judicious combinations of parameters and classifiers are needed to accurately discriminate between the three types of EEGs. It was discovered that a particular mixed-band feature space consisting of nine parameters and LMBPNN result in the highest classification accuracy, a high value of 96.7%.

[1]  C. Elger,et al.  Seizure prediction by non‐linear time series analysis of brain electrical activity , 1998, The European journal of neuroscience.

[2]  Donald C. Wunsch,et al.  Recurrent neural network based prediction of epileptic seizures in intra- and extracranial EEG , 2000, Neurocomputing.

[3]  H. Adeli,et al.  Analysis of EEG records in an epileptic patient using wavelet transform , 2003, Journal of Neuroscience Methods.

[4]  Leon D. Iasemidis,et al.  Epileptic seizure prediction and control , 2003, IEEE Transactions on Biomedical Engineering.

[5]  K Lehnertz,et al.  Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: dependence on recording region and brain state. , 2001, Physical review. E, Statistical, nonlinear, and soft matter physics.

[6]  Hojjat Adeli,et al.  Machine Learning: Neural Networks, Genetic Algorithms, and Fuzzy Systems , 1994 .

[7]  Hojjat Adeli,et al.  Machine Learning: Neural Networks , 1994 .

[8]  Leonidas D. Iasemidis,et al.  The evolution with time of the spatial distribution of the largest Lyapunov exponent on the human epileptic cortex , 1991 .

[9]  J. Sackellares,et al.  Time dependencies in the occurrences of epileptic seizures , 1994, Epilepsy Research.

[10]  Piotr J Durka,et al.  From wavelets to adaptive approximations: time-frequency parametrization of EEG , 2003, Biomedical engineering online.

[11]  Hojjat Adeli,et al.  Wavelet‐Clustering‐Neural Network Model for Freeway Incident Detection , 2003 .

[12]  W. Art Chaovalitwongse,et al.  Adaptive epileptic seizure prediction system , 2003, IEEE Transactions on Biomedical Engineering.

[13]  Hojjat Adeli,et al.  A Wavelet-Chaos Methodology for Analysis of EEGs and EEG Subbands to Detect Seizure and Epilepsy , 2007, IEEE Transactions on Biomedical Engineering.

[14]  Martin T. Hagan,et al.  Neural network design , 1995 .

[15]  N. K. Bose,et al.  Neural Network Fundamentals with Graphs, Algorithms and Applications , 1995 .

[16]  M. Goldstein,et al.  Multivariate Analysis: Methods and Applications , 1984 .

[17]  F. H. Lopes da Silva,et al.  Dynamics of local neuronal networks: control parameters and state bifurcations in epileptogenesis. , 1994, Progress in brain research.