Wavelet/mixture of experts network structure for EEG signals classification

Mixture of experts (ME) is a modular neural network architecture for supervised learning. This paper illustrates the use of ME network structure to guide model selection for classification of electroencephalogram (EEG) signals. Expectation-maximization (EM) algorithm was used for training the ME so that the learning process is decoupled in a manner that fits well with the modular structure. The EEG signals were decomposed into time-frequency representations using discrete wavelet transform and statistical features were calculated to depict their distribution. The ME network structure was implemented for classification of the EEG signals using the statistical features as inputs. To improve classification accuracy, the outputs of expert networks were combined by a gating network simultaneously trained in order to stochastically select the expert that is performing the best at solving the problem. Three types of EEG signals (EEG signals recorded from healthy volunteers with eyes open, epilepsy patients in the epileptogenic zone during a seizure-free interval, and epilepsy patients during epileptic seizures) were classified with the accuracy of 93.17% by the ME network structure. The ME network structure achieved accuracy rates which were higher than that of the stand-alone neural network models.

[1]  O Ozdamar,et al.  Detection of spikes with artificial neural networks using raw EEG. , 1998, Computers and biomedical research, an international journal.

[2]  Elif Derya Übeyli,et al.  Adaptive neuro-fuzzy inference system for classification of EEG signals using wavelet coefficients , 2005, Journal of Neuroscience Methods.

[3]  Kaoru Arakawa,et al.  Separation of a Nonstationary Component from the EEG by a Nonlinear Digital Filter , 1986, IEEE Transactions on Biomedical Engineering.

[4]  Michael I. Jordan,et al.  Hierarchical Mixtures of Experts and the EM Algorithm , 1994, Neural Computation.

[5]  J. Frost,et al.  Context-based automated detection of epileptogenic sharp transients in the EEG: elimination of false positives , 1989, IEEE Transactions on Biomedical Engineering.

[6]  Ke Chen,et al.  Improved learning algorithms for mixture of experts in multiclass classification , 1999, Neural Networks.

[7]  I A Basheer,et al.  Artificial neural networks: fundamentals, computing, design, and application. , 2000, Journal of microbiological methods.

[8]  M. Zweig,et al.  Receiver-operating characteristic (ROC) plots: a fundamental evaluation tool in clinical medicine. , 1993, Clinical chemistry.

[9]  W R Webber,et al.  Practical detection of epileptiform discharges (EDs) in the EEG using an artificial neural network: a comparison of raw and parameterized EEG data. , 1994, Electroencephalography and clinical neurophysiology.

[10]  P Guedes de Oliveira,et al.  Spike detection based on a pattern recognition approach using a microcomputer. , 1983, Electroencephalography and clinical neurophysiology.

[11]  Bidyut Baran Chaudhuri,et al.  Efficient training and improved performance of multilayer perceptron in pattern classification , 2000, Neurocomputing.

[12]  J Gotman,et al.  State-dependent spike detection: concepts and preliminary results. , 1991, Electroencephalography and clinical neurophysiology.

[13]  J. Gotman,et al.  State dependent spike detection: validation. , 1992, Electroencephalography and clinical neurophysiology.

[14]  Metin Akay,et al.  Wavelet applications in medicine , 1997 .

[15]  Xia Hong,et al.  A Mixture of Experts Network Structure Construction Algorithm for Modelling and Control , 2001, Applied Intelligence.

[16]  David West,et al.  An improved neural classification network for the two-group problem , 1999, Comput. Oper. Res..

[17]  W.J. Tompkins,et al.  A patient-adaptable ECG beat classifier using a mixture of experts approach , 1997, IEEE Transactions on Biomedical Engineering.

[18]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

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

[20]  W.R. Fright,et al.  A multistage system to detect epileptiform activity in the EEG , 1993, IEEE Transactions on Biomedical Engineering.

[21]  Ingrid Daubechies,et al.  The wavelet transform, time-frequency localization and signal analysis , 1990, IEEE Trans. Inf. Theory.

[22]  Geoffrey E. Hinton,et al.  Adaptive Mixtures of Local Experts , 1991, Neural Computation.

[23]  J Gotman,et al.  Automatic EEG analysis during long-term monitoring in the ICU. , 1998, Electroencephalography and clinical neurophysiology.

[24]  Skander Soltani,et al.  On the use of the wavelet decomposition for time series prediction , 2002, ESANN.

[25]  A J Gabor,et al.  Automated interictal EEG spike detection using artificial neural networks. , 1992, Electroencephalography and clinical neurophysiology.

[26]  Elif Derya Übeyli,et al.  A mixture of experts network structure for modelling Doppler ultrasound blood flow signals , 2005, Comput. Biol. Medicine.

[27]  I. Bankman,et al.  Automatic EEG spike detection: what should the computer imitate? , 1993, Electroencephalography and clinical neurophysiology.

[28]  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.

[29]  Michael Unser,et al.  A review of wavelets in biomedical applications , 1996, Proc. IEEE.

[30]  Ah Chung Tsoi,et al.  Classification of EEG signals using the wavelet transform , 1997, Proceedings of 13th International Conference on Digital Signal Processing.