The Effect of Multiscale PCA De-noising in Epileptic Seizure Detection

In this paper we describe the effect of Multiscale Principal Component Analysis (MSPCA) de-noising method in terms of epileptic seizure detection. In addition, we developed a patient-independent seizure detection algorithm using Freiburg EEG database. Each patient contains datasets called “ictal” and “interictal”. Window length of 16 s was applied to extract EEG segments from datasets of each patient. Furthermore, Power Spectral Density (PSD) of each EEG segment was estimated using different spectral analysis methods. Afterwards, these values were fed as input to different machine learning methods that were responsible for seizure detection. We also applied MSPCA de-noising method to EEG segments prior to PSD estimation to determine if MSPCA can further enhance the classifiers’ performance. The MSPCA drastically improved both the sensitivity and the specificity, increasing the overall accuracy of all three classifiers up to 20 %. The best overall detection accuracy (99.59 %) was achieved when Eigenvector analysis was used for frequency estimation, and C4.5 as a classifier. The experiment results show that MSPCA is an effective de-noising method for improving the classification performance in epileptic seizure detection.

[1]  OcakHasan.  Automatic detection of epileptic seizures in EEG using discrete wavelet transform and approximate entropy , 2009 .

[2]  Marvin Minsky,et al.  Perceptrons: An Introduction to Computational Geometry , 1969 .

[3]  Abdulhamit Subasi,et al.  EEG signal classification using PCA, ICA, LDA and support vector machines , 2010, Expert Syst. Appl..

[4]  Hlaing Minn,et al.  A Patient-Adaptive Profiling Scheme for ECG Beat Classification , 2010, IEEE Transactions on Information Technology in Biomedicine.

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

[6]  Lalit M. Patnaik,et al.  Epileptic EEG detection using neural networks and post-classification , 2008, Comput. Methods Programs Biomed..

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

[8]  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.

[9]  Hasan Ocak,et al.  Automatic detection of epileptic seizures in EEG using discrete wavelet transform and approximate entropy , 2009, Expert Syst. Appl..

[10]  Tzyy-Ping Jung,et al.  Extended ICA Removes Artifacts from Electroencephalographic Recordings , 1997, NIPS.

[11]  E. C. Chua,et al.  Improved patient specific seizure detection during pre-surgical evaluation , 2011, Clinical Neurophysiology.

[12]  Didier Maquin,et al.  Ocular artifacts removal in scalp EEG: combining ICA and wavelett denoising , 2007 .

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

[14]  Weidong Zhou,et al.  Epileptic seizure detection with linear and nonlinear features , 2012, Epilepsy & Behavior.

[15]  Ahmet Alkan,et al.  Comparison of AR and Welch Methods in Epileptic Seizure Detection , 2006, Journal of Medical Systems.

[16]  Abdulhamit Subasi,et al.  Analysis of EEG Signals Under Flash Stimulation for Migraine and Epileptic Patients , 2011, Journal of Medical Systems.

[17]  Ben H. Jansen,et al.  Autoregressive Estimation of Short Segment Spectra for Computerized EEG Analysis , 1981, IEEE Transactions on Biomedical Engineering.

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

[19]  Brian Litt,et al.  Epileptic seizure prediction using hybrid feature selection over multiple intracranial EEG electrode contacts: a report of four patients , 2003, IEEE Transactions on Biomedical Engineering.

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

[21]  C.W. Anderson,et al.  Multivariate autoregressive models for classification of spontaneous electroencephalographic signals during mental tasks , 1998, IEEE Transactions on Biomedical Engineering.

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

[23]  Hojjat Adeli,et al.  Principal Component Analysis-Enhanced Cosine Radial Basis Function Neural Network for Robust Epilepsy and Seizure Detection , 2008, IEEE Transactions on Biomedical Engineering.

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

[25]  W. M. Carey,et al.  Digital spectral analysis: with applications , 1986 .

[26]  Lotfi Senhadji,et al.  ICA-based EEG denoising: a comparative analysis of fifteen methods , 2012 .

[27]  Marimuthu Palaniswami,et al.  Computational Intelligence in Biomedical Engineering , 2007 .

[28]  Hakan Isik,et al.  Employment and Comparison of Different Artificial Neural Networks for Epilepsy Diagnosis from EEG Signals , 2012, Journal of Medical Systems.

[29]  Rangaraj M. Rangayyan,et al.  Biomedical Signal Analysis: A Case-Study Approach , 2001 .

[30]  S. M. Shafiul Alam,et al.  Detection of epileptic seizures using chaotic and statistical features in the EMD domain , 2011, 2011 Annual IEEE India Conference.

[31]  Sally I. McClean,et al.  Combining Wavelet Analysis and Bayesian Networks for the Classification of Auditory Brainstem Response , 2006, IEEE Transactions on Information Technology in Biomedicine.

[32]  Dimitrios I. Fotiadis,et al.  Epileptic Seizure Detection in EEGs Using Time–Frequency Analysis , 2009, IEEE Transactions on Information Technology in Biomedicine.

[33]  D. Narayana Dutt,et al.  SVD based technique for noise reduction in electroencephalographic signals , 1996, Signal Process..

[34]  Marvin Minsky,et al.  Perceptrons: An Introduction to Computational Geometry, Expanded Edition , 1987 .

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

[36]  Abdulhamit Subasi,et al.  Neural Networks with Periodogram and Autoregressive Spectral Analysis Methods in Detection of Epileptic Seizure , 2004, Journal of Medical Systems.

[37]  Patrick Berg,et al.  Artifact Correction of the Ongoing EEG Using Spatial Filters Based on Artifact and Brain Signal Topographies , 2002, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[38]  David G. Stork,et al.  Pattern Classification , 1973 .

[39]  Sung C. Choi,et al.  Choice of the smoothing parameter and efficiency of k-nearest neighbor classification , 1986 .

[40]  V. A. Makarov,et al.  Recovering EEG brain signals: Artifact suppression with wavelet enhanced independent component analysis , 2006, Journal of Neuroscience Methods.

[41]  Cenk Sahin,et al.  Neural Network-Based Computer-Aided Diagnosis in Classification of Primary Generalized Epilepsy by EEG Signals , 2009, Journal of Medical Systems.

[42]  John L. Semmlow,et al.  Biosignal and biomedical image processing : MATLAB-based applications , 2004 .

[43]  Pablo Laguna,et al.  Bioelectrical Signal Processing in Cardiac and Neurological Applications , 2005 .

[44]  A. Aarabi,et al.  A fuzzy rule-based system for epileptic seizure detection in intracranial EEG , 2009, Clinical Neurophysiology.

[45]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[46]  Christopher J. James,et al.  Employing spatially constrained ICA and wavelet denoising, for automatic removal of artifacts from multichannel EEG data , 2012, Signal Process..

[47]  David L. Donoho,et al.  De-noising by soft-thresholding , 1995, IEEE Trans. Inf. Theory.

[48]  Leif Sörnmo,et al.  Chapter 7 – ECG Signal Processing , 2005 .

[49]  Joseph D. Bronzino,et al.  The Biomedical Engineering Handbook , 1995 .

[50]  Pedro P. Irazoqui,et al.  Multistage seizure detection techniques optimized for low-power hardware platforms , 2011, Epilepsy & Behavior.

[51]  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.

[52]  M. L. Dewal,et al.  Relative wavelet energy and wavelet entropy based epileptic brain signals classification , 2012 .

[53]  A. M. Torres,et al.  A method for removing noise from continuous brain signal recordings , 2013, Comput. Electr. Eng..

[54]  Jean-Michel Poggi,et al.  Multivariate denoising using wavelets and principal component analysis , 2006, Comput. Stat. Data Anal..

[55]  Sabri Koçer,et al.  Classifying Epilepsy Diseases Using Artificial Neural Networks and Genetic Algorithm , 2011, Journal of Medical Systems.