Classification of Epilepsy Using High-Order Spectra Features and Principle Component Analysis

The classification of epileptic electroencephalogram (EEG) signals is challenging because of high nonlinearity, high dimensionality, and hidden states in EEG recordings. The detection of the preictal state is difficult due to its similarity to the ictal state. We present a framework for using principal components analysis (PCA) and a classification method for improving the detection rate of epileptic classes. To unearth the nonlinearity and high dimensionality in epileptic signals, we extract principal component features using PCA on the 15 high-order spectra (HOS) features extracted from the EEG data. We evaluate eight classifiers in the framework using true positive (TP) rate and area under curve (AUC) of receiver operating characteristics (ROC). We show that a simple logistic regression model achieves the highest TP rate for class “preictal” at 97.5% and the TP rate on average at 96.8% with PCA variance percentages selected at 100%, which also achieves the most AUC at 99.5%.

[1]  A. Schulze-Bonhage,et al.  How well can epileptic seizures be predicted? An evaluation of a nonlinear method. , 2003, Brain : a journal of neurology.

[2]  J. Martinerie,et al.  Epileptic seizures can be anticipated by non-linear analysis , 1998, Nature Medicine.

[3]  Robert H. Halstead,et al.  Matrix Computations , 2011, Encyclopedia of Parallel Computing.

[4]  Ian H. Witten,et al.  Induction of model trees for predicting continuous classes , 1996 .

[5]  U. Rajendra Acharya,et al.  Entropies for detection of epilepsy in EEG , 2005, Comput. Methods Programs Biomed..

[6]  David W. Hosmer,et al.  Applied Logistic Regression , 1991 .

[7]  Juan José Rodríguez Diez,et al.  Rotation Forest: A New Classifier Ensemble Method , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  V. Srinivasan,et al.  Approximate Entropy-Based Epileptic EEG Detection Using Artificial Neural Networks , 2007, IEEE Transactions on Information Technology in Biomedicine.

[9]  M Congedo,et al.  A review of classification algorithms for EEG-based brain–computer interfaces , 2007, Journal of neural engineering.

[10]  Zehra Cataltepe,et al.  A PCA/ICA based feature selection method and its application for corn fungi detection , 2007, 2007 15th European Signal Processing Conference.

[11]  Ian Witten,et al.  Data Mining , 2000 .

[12]  C. M. Lim,et al.  Automatic identification of epileptic electroencephalography signals using higher-order spectra , 2009, Proceedings of the Institution of Mechanical Engineers. Part H, Journal of engineering in medicine.

[13]  Francisco Sepulveda,et al.  Classifying mental tasks based on features of higher-order statistics from EEG signals in brain-computer interface , 2008, Inf. Sci..

[14]  Robert X. Gao,et al.  PCA-based feature selection scheme for machine defect classification , 2004, IEEE Transactions on Instrumentation and Measurement.

[15]  A. Babloyantz,et al.  Low-dimensional chaos in an instance of epilepsy. , 1986, Proceedings of the National Academy of Sciences of the United States of America.

[16]  U. Rajendra Acharya,et al.  AUTOMATIC IDENTIFICATION OF EPILEPTIC EEG SIGNALS USING NONLINEAR PARAMETERS , 2009 .

[17]  F. H. Lopes da Silva,et al.  Chaos or noise in EEG signals; dependence on state and brain site. , 1991, Electroencephalography and clinical neurophysiology.

[18]  Eibe Frank,et al.  Logistic Model Trees , 2003, Machine Learning.

[19]  J. R. Quinlan.  Learning With Continuous Classes , 1992 .

[20]  C. M. Lim,et al.  Higher Order Spectral (HOS) Analysis Of Epileptic EEG Signals , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[21]  W. Freeman,et al.  How brains make chaos in order to make sense of the world , 1987, Behavioral and Brain Sciences.

[22]  W. Freeman.  Simulation of chaotic EEG patterns with a dynamic model of the olfactory system , 1987, Biological Cybernetics.

[23]  A. Kraskov,et al.  On the predictability of epileptic seizures , 2005, Clinical Neurophysiology.

[24]  S. L. Shishkin,et al.  Application of the change-point analysis to the investigation of the brain’s electrical activity , 2000 .

[25]  Abdulhamit Subasi,et al.  EEG signal classification using wavelet feature extraction and a mixture of expert model , 2007, Expert Syst. Appl..

[26]  J. W. A. S. Sander,et al.  Mortality from epilepsy: results from a prospective population-based study , 1994, The Lancet.

[27]  Daniel Graupe,et al.  A neural-network-based detection of epilepsy , 2004, Neurological research.

[28]  U. Rajendra Acharya,et al.  Automatic Identification of Epileptic and Background EEG Signals Using Frequency Domain Parameters , 2010, Int. J. Neural Syst..

[29]  Ji-Wu Zhang,et al.  Bispectrum analysis of focal ischemic cerebral EEG signal , 1998, Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Vol.20 Biomedical Engineering Towards the Year 2000 and Beyond (Cat. No.98CH36286).

[30]  Elif Derya Übeyli,et al.  Recurrent neural networks employing Lyapunov exponents for EEG signals classification , 2005, Expert Syst. Appl..

[31]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[32]  Christos Boutsidis,et al.  Unsupervised feature selection for principal components analysis , 2008, KDD.

[33]  U. Rajendra Acharya,et al.  Analysis and Automatic Identification of Sleep Stages Using Higher Order Spectra , 2010, Int. J. Neural Syst..

[34]  U. Rajendra Acharya,et al.  Application of Higher Order Spectra to Identify Epileptic EEG , 2011, Journal of Medical Systems.

[35]  Yong Wang,et al.  Using Model Trees for Classification , 1998, Machine Learning.

[36]  GOTTFRIED MAYER‐KRESS AND,et al.  Dimensionality of the Human Electroencephalogram , 1987, Annals of the New York Academy of Sciences.

[37]  Hamid Reza Mohseni,et al.  Epileptic Seizure Detection Using Neural Fuzzy Networks , 2006, 2006 IEEE International Conference on Fuzzy Systems.

[38]  Abdulhamit Subasi,et al.  Classification of EEG signals using neural network and logistic regression , 2005, Comput. Methods Programs Biomed..

[39]  Shih-Fu Chang,et al.  Blind detection of photomontage using higher order statistics , 2004, 2004 IEEE International Symposium on Circuits and Systems (IEEE Cat. No.04CH37512).

[40]  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.

[41]  Jack Y. Yang,et al.  Selecting subsets of newly extracted features from PCA and PLS in microarray data analysis , 2008, BMC Genomics.

[42]  F. Mormann,et al.  Seizure prediction: the long and winding road. , 2007, Brain : a journal of neurology.

[43]  Ali H. Shoeb,et al.  Application of machine learning to epileptic seizure onset detection and treatment , 2009 .

[44]  C. M. Lim,et al.  Characterization of EEG - A comparative study , 2005, Comput. Methods Programs Biomed..

[45]  C. M. Lim,et al.  Analysis of epileptic EEG signals using higher order spectra , 2009, Journal of medical engineering & technology.

[46]  T. Lagerlund,et al.  Spatial filtering of multichannel electroencephalographic recordings through principal component analysis by singular value decomposition. , 1997, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[47]  J P Lieb,et al.  Temporo-spatial patterns of pre-ictal spike activity in human temporal lobe epilepsy. , 1983, Electroencephalography and clinical neurophysiology.

[48]  Kemal Polat,et al.  Classification of epileptiform EEG using a hybrid system based on decision tree classifier and fast Fourier transform , 2007, Appl. Math. Comput..