A methodology for time-frequency image processing applied to the classification of non-stationary multichannel signals using instantaneous frequency descriptors with application to newborn EEG signals

This article presents a general methodology for processing non-stationary signals for the purpose of classification and localization. The methodology combines methods adapted from three complementary areas: time-frequency signal analysis, multichannel signal analysis and image processing. The latter three combine in a new methodology referred to as multichannel time-frequency image processing which is applied to the problem of classifying electroencephalogram (EEG) abnormalities in both adults and newborns. A combination of signal related features and image related features are used by merging key instantaneous frequency descriptors which characterize the signal non-stationarities. The results obtained show that, firstly, the features based on time-frequency image processing techniques such as image segmentation, improve the performance of EEG abnormalities detection in the classification systems based on multi-SVM and neural network classifiers. Secondly, these discriminating features are able to better detect the correlation between newborn EEG signals in a multichannel-based newborn EEG seizure detection for the purpose of localizing EEG abnormalities on the scalp.

[1]  Nadine Martin,et al.  Extraction of pertinent subsets from time-frequency representations for detection and recognition purposes , 2002, Signal Process..

[2]  Mohammad B. Shamsollahi,et al.  Seizure Detection in EEG signals: A Comparison of Different approaches , 2006, 2006 International Conference of the IEEE Engineering in Medicine and Biology Society.

[3]  U. Rajendra Acharya,et al.  Erratum to "Entropies for detection of epilepsy in EEG" [Comput. Methods Prog. Biomed. 80 (2005) 187-194] , 2006, Comput. Methods Programs Biomed..

[4]  Tom E. Bishop,et al.  Blind Image Restoration Using a Block-Stationary Signal Model , 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

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

[6]  Antonia Papandreou-Suppappola,et al.  Applications in Time-Frequency Signal Processing , 2002 .

[7]  Robert Oostenveld,et al.  The five percent electrode system for high-resolution EEG and ERP measurements , 2001, Clinical Neurophysiology.

[8]  J. Gotman.  Automatic seizure detection: improvements and evaluation. , 1990, Electroencephalography and clinical neurophysiology.

[9]  Boualem Boashash,et al.  A methodology for detection and classification of some underwater acoustic signals using time-frequency analysis techniques , 1990, IEEE Trans. Acoust. Speech Signal Process..

[10]  D. Massart,et al.  The Mahalanobis distance , 2000 .

[11]  Harald Haas,et al.  Asilomar Conference on Signals, Systems, and Computers , 2006 .

[12]  N. Kehtarnavaz,et al.  Neural network classification of EEG signals using time-frequency representation , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[13]  Boualem Boashash,et al.  Time-Frequency Signal Analysis: Methods and Applications. , 1993 .

[14]  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.

[15]  S. J. Roberts,et al.  Temporal and spatial complexity measures for electroencephalogram based brain-computer interfacing , 2006, Medical & Biological Engineering & Computing.

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

[17]  B. Boashash,et al.  Neonatal Seizure Detection and Localization using Time-Frequency Analysis of Multichannel EEG , 2007, 2007 IEEE International Conference on Signal Processing and Communications.

[18]  Boualem Boashash,et al.  Improving the classification of newborn EEG time-frequency representations using a combined time-frequency signal and image approach , 2012, 2012 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA).

[19]  Osman Erogul,et al.  Epileptic EEG detection using the linear prediction error energy , 2010, Expert Syst. Appl..

[20]  Mostefa Mesbah,et al.  IF estimation for multicomponent signals using image processing techniques in the time-frequency domain , 2007, Signal Process..

[21]  V. Srinivasan,et al.  Artificial Neural Network Based Epileptic Detection Using Time-Domain and Frequency-Domain Features , 2005, Journal of Medical Systems.

[22]  Gernot Kubin,et al.  Joint Time–Frequency Segmentation Algorithm for Transient Speech Decomposition and Speech Enhancement , 2010, IEEE Transactions on Audio, Speech, and Language Processing.

[23]  Srdjan Stankovic.  Time-Frequency Analysis and Its Application in Digital Watermarking , 2010, EURASIP J. Adv. Signal Process..

[24]  G. Lightbody,et al.  A comparison of quantitative EEG features for neonatal seizure detection , 2008, Clinical Neurophysiology.

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

[26]  Elif Derya Übeyli,et al.  Multiclass Support Vector Machines for EEG-Signals Classification , 2007, IEEE Transactions on Information Technology in Biomedicine.

[27]  Ewa Swiercz.  Classification in the Gabor time-frequency domain of non-stationary signals embedded in heavy noise with unknown statistical distribution , 2010, Int. J. Appl. Math. Comput. Sci..

[28]  Boualem Boashash,et al.  Estimating and interpreting the instantaneous frequency of a signal. II. A/lgorithms and applications , 1992, Proc. IEEE.

[29]  Aydin Akan,et al.  A Robust Image Watermarking in the Joint Time-Frequency Domain , 2010, EURASIP J. Adv. Signal Process..

[30]  Mandyam D. Srinath,et al.  Multichannel fusion models for the parametric classification of differential brain activity , 2005, IEEE Transactions on Biomedical Engineering.

[31]  Dimitrios I. Fotiadis,et al.  Automatic Seizure Detection Based on Time-Frequency Analysis and Artificial Neural Networks , 2007, Comput. Intell. Neurosci..

[32]  Michael J. Aminoff,et al.  Electrodiagnosis in Clinical Neurology , 1980 .

[33]  Boualem Boashash,et al.  Time-Frequency Analysis And Pattern Recognition Using Singular Value Decomposition Of The Wigner-Ville Distribution , 1988, Optics & Photonics.

[34]  Fabien Millioz,et al.  Short Time Fourier Transform Probability Distribution for Time-Frequency Segmentation , 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

[35]  Bijan G. Mobasseri,et al.  Digital watermarking in joint time-frequency domain , 2002, Proceedings. International Conference on Image Processing.

[36]  Li Tao,et al.  Improvement on joint time-frequency representation with application of image processing technique , 2003, Proceedings Fifth International Conference on Computational Intelligence and Multimedia Applications. ICCIMA 2003.

[37]  Huaying Li,et al.  Neonatal seizure detection using blind multichannel information fusion , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[38]  Boualem Boashash,et al.  Time-Frequency Distributions Based on Compact Support Kernels: Properties and Performance Evaluation , 2012, IEEE Transactions on Signal Processing.

[39]  Boualem Boashash,et al.  Mobile unit velocity estimation based on the instantaneous frequency of the received signal , 2004, IEEE Transactions on Vehicular Technology.

[40]  Stéphane Mallat,et al.  Audio Denoising by Time-Frequency Block Thresholding , 2008, IEEE Transactions on Signal Processing.

[41]  Irena Orovic,et al.  Robust Speech Watermarking Procedure in the Time-Frequency Domain , 2008, EURASIP J. Adv. Signal Process..

[42]  Boualem Boashash,et al.  Wavelet Denoising Based on the MAP Estimation Using the BKF Prior With Application to Images and EEG Signals , 2013, IEEE Transactions on Signal Processing.

[43]  Nishan Canagarajah,et al.  Region feature-based segmentation of time-frequency images , 2004 .

[44]  Jin Jiang,et al.  Time-frequency feature representation using energy concentration: An overview of recent advances , 2009, Digit. Signal Process..

[45]  W. Hauser,et al.  Comment on Epileptic Seizures and Epilepsy: Definitions Proposed by the International League Against Epilepsy (ILAE) and the International Bureau for Epilepsy (IBE) , 2005, Epilepsia.

[46]  Mohamed-Jalal Fadili,et al.  Bayesian denoising based on the MAP estimation in wavelet-domain using Bessel K form prior , 2005, IEEE International Conference on Image Processing 2005.

[47]  Boualem Boashash,et al.  Algorithms for Time-Frequency Signal Analysis , 1992 .

[48]  C. Elger,et al.  Response: Definitions Proposed by the International League Against Epilepsy (ILAE) and the International Bureau for Epilepsy (IBE) , 2005 .

[49]  Dimitrios I. Fotiadis,et al.  Epileptic Seizure Detection in EEGs Using , 2009 .

[50]  Andrew D. Sterian,et al.  Model-based segmentation of time-frequency images for musical transcription. , 1999 .

[51]  Fabien Millioz,et al.  REASSIGNMENT VECTOR FIELD FOR TIME-FREQUENCY SEGMENTATION , 2007 .

[52]  Douglas D. O'Shaughnessy,et al.  Segmentation of a speech spectrogram using mathematical morphology , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[53]  R R Clancy,et al.  The Contribution of EEG to the Understanding of Neonatal Seizures , 1996, Epilepsia.

[54]  Valery Naranjo,et al.  Removing interference components in time-frequency representations using morphological operators , 2011, J. Vis. Commun. Image Represent..

[55]  Jin S. Hahn,et al.  Chapter 4 – Neonatal and Pediatric Electroencephalography , 2005 .

[56]  Boualem Boashash,et al.  Time-Frequency Methodology for Newborn Electroencephalographic Seizure Detection , 2002 .

[57]  Cheung,et al.  A time-frequency image coding technique , 1999 .

[58]  George S. Tombras,et al.  Description of a 2-Bit Adaptive Sigma-Delta Modulation System with Minimized Idle Tones , 2008, EURASIP J. Adv. Signal Process..

[59]  Boualem Boashash,et al.  Using DSP to detect seizures in newborns , 2003 .

[60]  A. Aarabi,et al.  A multistage knowledge-based system for EEG seizure detection in newborn infants , 2007, Clinical Neurophysiology.

[61]  Mostefa Mesbah,et al.  A Nonstationary Model of Newborn EEG , 2007, IEEE Transactions on Biomedical Engineering.

[62]  A.V. Shekhirev,et al.  Music files compression based on time-frequency representation of audio signal , 2008, 2008 Third International Forum on Strategic Technologies.

[63]  Boualem Boashash,et al.  Use of the cross Wigner-Ville distribution for estimation of instantaneous frequency , 1993, IEEE Trans. Signal Process..

[64]  C. Elger,et al.  Epileptic Seizures and Epilepsy: Definitions Proposed by the International League Against Epilepsy (ILAE) and the International Bureau for Epilepsy (IBE) , 2005, Epilepsia.

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

[66]  E. M. Speiser,et al.  Advanced Algorithms and Architectures for Signal Processing , 1986 .

[67]  LJubisa Stankovic,et al.  A measure of some time-frequency distributions concentration , 2001, Signal Process..

[68]  M. Al-khassaweneh,et al.  A time-frequency inspired robust image watermarking , 2004, Conference Record of the Thirty-Eighth Asilomar Conference on Signals, Systems and Computers, 2004..

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

[70]  K. Abed-Meraim,et al.  An image processing approach for underdetermined blind separation of nonstationary sources , 2003, 3rd International Symposium on Image and Signal Processing and Analysis, 2003. ISPA 2003. Proceedings of the.

[71]  B. Boashash,et al.  Detection of neonatal EEG seizure using multichannel matching pursuit , 2008, 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[72]  A. Zoubir,et al.  EURASIP Journal on Advances in Signal Processing , 2011 .

[73]  Markku Renfors,et al.  Pilot-Based Synchronization and Equalization in Filter Bank Multicarrier Communications , 2010, EURASIP J. Adv. Signal Process..

[74]  Schreiber,et al.  Quantification of depth of anesthesia by nonlinear time series analysis of brain electrical activity , 2000, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[75]  Stefano Parolai,et al.  Denoising of Seismograms Using the S Transform , 2009 .

[76]  Mostefa Mesbah,et al.  Time-Frequency Feature Extraction of Newborn EEG Seizure Using SVD-Based Techniques , 2004, EURASIP J. Adv. Signal Process..

[77]  Boualem Boashash,et al.  Estimating and interpreting the instantaneous frequency of a signal. I. Fundamentals , 1992, Proc. IEEE.

[78]  B Boashash,et al.  A time-frequency approach for newborn seizure detection. , 2001, IEEE engineering in medicine and biology magazine : the quarterly magazine of the Engineering in Medicine & Biology Society.

[79]  Boualem Boashash,et al.  Note on the use of the Wigner distribution for time-frequency signal analysis , 1988, IEEE Trans. Acoust. Speech Signal Process..

[80]  Ervin Sejdic,et al.  Pattern Recognition in Time-Frequency Domain: Selective Regional Correlation and Its Applications , 2008 .

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

[82]  Elif Derya.  Multiclass Support Vector Machines for EEG-Signals Classification , 2007 .

[83]  Boualem Boashash,et al.  Methods of signal classification using the images produced by the Wigner-Ville distribution , 1991, Pattern Recognit. Lett..

[84]  Mingui Sun,et al.  Elimination of cross-components of the discrete pseudo Wigner distribution via image processing , 1989, International Conference on Acoustics, Speech, and Signal Processing,.

[85]  Tzu-Hsien Sang,et al.  Renyi information and signal-dependent optimal kernel design , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[86]  B Boashash.  Digital Signal Processing in the Time-frequency Domain using the Wigner-Ville Distribution , 1985 .

[87]  Jean-Jacques E. Slotine,et al.  Audio classification from time-frequency texture , 2008, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

[88]  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..

[89]  Victor Barroso,et al.  Uncertainty in the time-frequency plane , 2000, Proceedings of the Tenth IEEE Workshop on Statistical Signal and Array Processing (Cat. No.00TH8496).

[90]  Olivier BERDER,et al.  Identification of Frequency Hopping Communications , 2002 .

[91]  Boualem Boashash,et al.  EEG-based automatic epilepsy diagnosis using the instantaneous frequency with sub-band energies , 2011, International Workshop on Systems, Signal Processing and their Applications, WOSSPA.

[92]  Boualem Boashash,et al.  Time-frequency signal and image processing of non-stationary signals with application to the classification of newborn EEG abnormalities , 2011, 2011 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT).

[93]  G. Lightbody,et al.  EEG-based neonatal seizure detection with Support Vector Machines , 2011, Clinical Neurophysiology.

[94]  Boualem Boashash,et al.  Resolution measure criteria for the objective assessment of the performance of quadratic time-frequency distributions , 2003, IEEE Trans. Signal Process..

[95]  John G. Proakis,et al.  Digital Communications , 1983 .

[96]  B. Boashash,et al.  Multichannel-Based Newborn EEG Seizure Detection using Time-Frequency Matched Filter , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[97]  Boualem Boashash,et al.  Compact support kernels based time-frequency distributions: Performance evaluation , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[98]  Jean-Francois Mangin,et al.  Detection of linear features in SAR images: application to road network extraction , 1998, IEEE Trans. Geosci. Remote. Sens..

[99]  Manoranjan Paul,et al.  Video coding using arbitrarily shaped block partitions in globally optimal perspective , 2011, EURASIP J. Adv. Signal Process..

[100]  Patrick J. Loughlin,et al.  Denoising using time-frequency and image processing methods , 1999, Optics & Photonics.

[101]  Mostefa Mesbah,et al.  Newborn seizure detection based on fusion of multichannel EEG , 2008 .

[102]  M. Spiertz,et al.  Audio Segmentation Using Di erent Time-Frequency Representations , 2008 .

[103]  Boualem Boashash,et al.  An Efficient Algorithm for Instantaneous Frequency Estimation of Nonstationary Multicomponent Signals in Low SNR , 2011, EURASIP J. Adv. Signal Process..

[104]  Pierre Soille,et al.  Morphological Image Analysis , 1999 .

[105]  Friedrich Jondral,et al.  Classification of modulation modes using time-frequency methods , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).