A high-performance seizure detection algorithm based on Discrete Wavelet Transform (DWT) and EEG

In the past decade, Discrete Wavelet Transform (DWT), a powerful time-frequency tool, has been widely used in computer-aided signal analysis of epileptic electroencephalography (EEG), such as the detection of seizures. One of the important hurdles in the applications of DWT is the settings of DWT, which are chosen empirically or arbitrarily in previous works. The objective of this study aimed to develop a framework for automatically searching the optimal DWT settings to improve accuracy and to reduce computational cost of seizure detection. To address this, we developed a method to decompose EEG data into 7 commonly used wavelet families, to the maximum theoretical level of each mother wavelet. Wavelets and decomposition levels providing the highest accuracy in each wavelet family were then searched in an exhaustive selection of frequency bands, which showed optimal accuracy and low computational cost. The selection of frequency bands and features removed approximately 40% of redundancies. The developed algorithm achieved promising performance on two well-tested EEG datasets (accuracy >90% for both datasets). The experimental results of the developed method have demonstrated that the settings of DWT affect its performance on seizure detection substantially. Compared with existing seizure detection methods based on wavelet, the new approach is more accurate and transferable among datasets.

[1]  J. Helen Cross,et al.  Apractical clinical definition of epilepsy , 2014 .

[2]  Elif Derya íbeyli.  Analysis of EEG signals by combining eigenvector methods and multiclass support vector machines , 2008 .

[3]  J. Gotman,et al.  Wavelet based automatic seizure detection in intracerebral electroencephalogram , 2003, Clinical Neurophysiology.

[4]  Weidong Zhou,et al.  Automatic Seizure Detection Using Wavelet Transform and SVM in Long-Term Intracranial EEG , 2012, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[5]  Mauro Ursino,et al.  A wavelet-based energetic approach for the analysis of biomedical signals: Application to the electroencephalogram and electro-oculogram , 2009, Appl. Math. Comput..

[6]  Olivier Chapelle,et al.  Training a Support Vector Machine in the Primal , 2007, Neural Computation.

[7]  S. Spencer,et al.  Intracranial EEG Seizure‐Onset Patterns in Neocortical Epilepsy , 2000, Epilepsia.

[8]  Clodoaldo Ap. M. Lima,et al.  Automatic EEG signal classification for epilepsy diagnosis with Relevance Vector Machines , 2009, Expert Syst. Appl..

[9]  Daniel Rivero,et al.  Automatic epileptic seizure detection in EEGs based on line length feature and artificial neural networks , 2010, Journal of Neuroscience Methods.

[10]  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.

[11]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[12]  Divyakant Agrawal,et al.  A comparison of DFT and DWT based similarity search in time-series databases , 2000, CIKM '00.

[13]  Sigmund Jenssen,et al.  Treatment and Management of Epilepsy in the Elderly Demented Patient , 2010, American journal of Alzheimer's disease and other dementias.

[14]  Jean Gotman,et al.  High frequency oscillations: The new EEG frontier? , 2010, Epilepsia.

[15]  Gustavo E. A. P. A. Batista,et al.  A study of the behavior of several methods for balancing machine learning training data , 2004, SKDD.

[16]  J. H. Cross,et al.  ILAE Official Report: A practical clinical definition of epilepsy , 2014, Epilepsia.

[17]  Jean-Michel Badier,et al.  Source localization of ictal epileptic activity investigated by high resolution EEG and validated by SEEG , 2010, NeuroImage.

[18]  João Paulo Papa,et al.  EEG signal classification for epilepsy diagnosis via optimum path forest - A systematic assessment , 2014, Neurocomputing.

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

[20]  A M LimaClodoaldo,et al.  Automatic EEG signal classification for epilepsy diagnosis with Relevance Vector Machines , 2009 .

[21]  Stéphane Mallat,et al.  A Theory for Multiresolution Signal Decomposition: The Wavelet Representation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[22]  Clodoaldo Ap. M. Lima,et al.  Kernel machines for epilepsy diagnosis via EEG signal classification: A comparative study , 2011, Artif. Intell. Medicine.

[23]  D. Freitas,et al.  Handbook of Research on Trends in the Diagnosis and Treatment of Chronic Conditions , 2015 .

[24]  C. Koch,et al.  The origin of extracellular fields and currents — EEG, ECoG, LFP and spikes , 2012, Nature Reviews Neuroscience.

[25]  Elif Derya Übeyli.  Combined neural network model employing wavelet coefficients for EEG signals classification , 2009, Digit. Signal Process..

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

[27]  H. Adeli,et al.  Wavelet-based EEG processing for computer-aided seizure detection and epilepsy diagnosis , 2015, Seizure.

[28]  Elif Derya Übeyli.  Analysis of EEG signals by combining eigenvector methods and multiclass support vector machines , 2008, Comput. Biol. Medicine.

[29]  Al Bartolucci,et al.  Effect of epilepsy magnetic source imaging on intracranial electrode placement , 2009, Annals of neurology.

[30]  Daniel Rivero,et al.  Epileptic seizure detection using multiwavelet transform based approximate entropy and artificial neural networks , 2010, Journal of Neuroscience Methods.

[31]  John S Ebersole,et al.  Tonic phase of a generalized convulsive seizure is an independent predictor of postictal generalized EEG suppression , 2013, Epilepsia.

[32]  U. Rajendra Acharya,et al.  Use of principal component analysis for automatic classification of epileptic EEG activities in wavelet framework , 2012, Expert Syst. Appl..

[33]  J. Morlet,et al.  [16] Mallat, S. (1989) \A Theory for Multiresolution Signal Decomposition: The Wavelet Representation, " IEEE Transactions on Pattern Analysis and Machine Intelligence, , 1995 .

[34]  Stéphane Mallat,et al.  Characterization of Signals from Multiscale Edges , 2011, IEEE Trans. Pattern Anal. Mach. Intell..

[35]  Mostefa Mesbah,et al.  A matching pursuit-based signal complexity measure for the analysis of newborn EEG , 2007, Medical & Biological Engineering & Computing.

[36]  Mathieu S. Capcarrère,et al.  Necessary conditions for density classification by cellular automata. , 2001, Physical review. E, Statistical, nonlinear, and soft matter physics.

[37]  Reza Tafreshi,et al.  Automated Real-Time Epileptic Seizure Detection in Scalp EEG Recordings Using an Algorithm Based on Wavelet Packet Transform , 2010, IEEE Transactions on Biomedical Engineering.

[38]  Ingrid Daubechies,et al.  Ten Lectures on Wavelets , 1992 .

[39]  Ali H. Shoeb,et al.  Application of Machine Learning To Epileptic Seizure Detection , 2010, ICML.