Comparison of Ensemble Machine Learning Methods for Automated Classification of Focal and Non-Focal Epileptic EEG Signals

This research presents the epileptic focus region localization during epileptic seizures by applying different signal processing and ensemble machine learning techniques in intracranial recordings of electroencephalogram (EEG). Multi-scale Principal Component Analysis (MSPCA) is used for denoising EEG signals and the autoregressive (AR) algorithm will extract useful features from the EEG signal. The performances of the ensemble machine learning methods are measured with accuracy, F-measure, and the area under the receiver operating characteristic (ROC) curve (AUC). EEG-based focus area localization with the proposed methods reaches 98.9% accuracy using the Rotation Forest classifier. Therefore, our results suggest that ensemble machine learning methods can be applied to differentiate the EEG signals from epileptogenic brain areas and signals recorded from non-epileptogenic brain regions with high accuracy.

[1]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

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

[3]  Jasmin Kevric,et al.  The Impact of Mspca Signal De-Noising In Real-Time Wireless Brain Computer Interface System , 2015, SOCO 2015.

[4]  N. Thakor,et al.  Spectral analysis methods for neurological signals , 1998, Journal of Neuroscience Methods.

[5]  Ralph G Andrzejak,et al.  Nonrandomness, nonlinear dependence, and nonstationarity of electroencephalographic recordings from epilepsy patients. , 2012, Physical review. E, Statistical, nonlinear, and soft matter physics.

[6]  Sushilkumar Kalmegh,et al.  Analysis of WEKA Data Mining Algorithm REPTree, Simple Cart and RandomTree for Classification of Indian News , 2015 .

[7]  H. M. Weinmann,et al.  Handbook of EEG and clinical neurophysiology , 1978 .

[8]  Abdulhamit Subasi,et al.  Effect of multiscale PCA de-noising on EMG signal classification for diagnosis of neuromuscular disorders , 2014, Journal of Medical Systems.

[9]  Anne M. Denton,et al.  Lazy Classifiers Using P-trees , 2002, CAINE.

[10]  Robert P. W. Duin,et al.  Bagging, Boosting and the Random Subspace Method for Linear Classifiers , 2002, Pattern Analysis & Applications.

[11]  Banu Onaral,et al.  Biomedical Signals: Origin and Dynamic Characteristics; Frequency-Domain Analysis , 1999 .

[12]  Victor Mitrana,et al.  Uniformly bounded duplication languages , 2005, Discret. Appl. Math..

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

[14]  Michael W. Berry,et al.  Lecture Notes in Data Mining , 2006 .

[15]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[16]  U. Rajendra Acharya,et al.  An automatic detection of focal EEG signals using new class of time-frequency localized orthogonal wavelet filter banks , 2017, Knowl. Based Syst..

[17]  Klaus Lehnertz,et al.  Epilepsy and Nonlinear Dynamics , 2008, Journal of biological physics.

[18]  Abdulhamit Subasi,et al.  Comparison of subspace-based methods with AR parametric methods in epileptic seizure detection , 2006, Comput. Biol. Medicine.

[19]  J. Edward Jackson,et al.  A User's Guide to Principal Components. , 1991 .

[20]  Pradip Sircar,et al.  A novel approach for automated detection of focal EEG signals using empirical wavelet transform , 2016, Neural Computing and Applications.

[21]  Yan Li,et al.  Epileptogenic focus detection in intracranial EEG based on delay permutation entropy , 2013 .

[22]  Edmund R. Malinowski,et al.  Factor Analysis in Chemistry , 1980 .

[23]  Lorentz Jäntschi,et al.  The Eigenproblem Translated for Alignment of Molecules , 2019, Symmetry.

[24]  B. Bakshi.  Multiscale PCA with application to multivariate statistical process monitoring , 1998 .

[25]  Stanislaw Osowski,et al.  Epileptic seizure characterization by Lyapunov exponent of EEG signal , 2007 .

[26]  อนิรุธ สืบสิงห์,et al.  Data Mining Practical Machine Learning Tools and Techniques , 2014 .

[27]  A. Borisenko,et al.  Coulomb clusters of dust particles in a cusp magnetic trap under microgravity conditions. , 2012, Physical review. E, Statistical, nonlinear, and soft matter physics.

[28]  Rodrigo Quian Quiroga,et al.  Nonlinear multivariate analysis of neurophysiological signals , 2005, Progress in Neurobiology.

[29]  Victor Mitrana,et al.  A New Characterization of NP, P, and PSPACE with Accepting Hybrid Networks of Evolutionary Processors , 2010, Theory of Computing Systems.

[30]  Geoffrey I. Webb,et al.  MultiBoosting: A Technique for Combining Boosting and Wagging , 2000, Machine Learning.

[31]  Margaret H. Dunham,et al.  Data Mining: Introductory and Advanced Topics , 2002 .

[32]  Abdulhamit Subasi,et al.  Comparison of EMD, DWT and WPD for the localization of epileptogenic foci using Random Forest classifier , 2019, Measurement.

[33]  Stanislaw Osowski,et al.  Single-class SVM classifier for localization of epileptic focus on the basis of EEG , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[34]  J Pardey,et al.  A review of parametric modelling techniques for EEG analysis. , 1996, Medical engineering & physics.

[35]  S. Bolboacă,et al.  Performances of Shannon’s Entropy Statistic in Assessment of Distribution of Data , 2017 .

[36]  Ayako Ochi,et al.  Systematic approach to dipole localization of interictal EEG spikes in children with extratemporal lobe epilepsies , 2000, Clinical Neurophysiology.

[37]  Natheer Khasawneh,et al.  Automated sleep stage identification system based on time-frequency analysis of a single EEG channel and random forest classifier , 2012, Comput. Methods Programs Biomed..

[38]  S. Rigatti.  Random Forest. , 2017, Journal of insurance medicine.

[39]  Eric Bauer,et al.  An Empirical Comparison of Voting Classification Algorithms: Bagging, Boosting, and Variants , 1999, Machine Learning.

[40]  Ronald G. Emerson,et al.  Spike detection II: automatic, perception-based detection and clustering , 1999, Clinical Neurophysiology.

[41]  Marc R. Nuwer,et al.  Quantification and localization of EEG interictal spike activity in patients with surgically removed epileptogenic foci , 2012, Clinical Neurophysiology.

[42]  Victor Mitrana,et al.  All NP-Problems Can Be Solved in Polynomial Time by Accepting Networks of Splicing Processors of Constant Size , 2006, DNA.

[43]  Satoru Goto,et al.  On-line spectral estimation of nonstationary time series based on AR model parameter estimation and order selection with a forgetting factor , 1995, IEEE Trans. Signal Process..

[44]  Anindya Bijoy Das,et al.  Discrimination and classification of focal and non-focal EEG signals using entropy-based features in the EMD-DWT domain , 2016, Biomed. Signal Process. Control..

[45]  Daniela Rosca,et al.  Orhonormal wavelet bases on the 3D ball via volume preserving map from the regular octahedron , 2019, ArXiv.

[46]  Xiaoying Tang,et al.  Analysis of Frequency Domain of EEG Signals in Clinical Location of Epileptic Focus , 2013, Clinical EEG and neuroscience.

[47]  Donna Rudd.  Bioelectrical Signal Processing in Cardiac and Neurological Applications [Book Review] , 2007 .

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

[49]  Tin Kam Ho,et al.  The Random Subspace Method for Constructing Decision Forests , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[50]  C. Stam,et al.  Nonlinear dynamical analysis of EEG and MEG: Review of an emerging field , 2005, Clinical Neurophysiology.