Trends in biomedical signal feature extraction

Abstract Signal analysis involves identifying signal behaviour, extracting linear and non-linear properties, compression or expansion into higher or lower dimensions, and recognizing patterns. Over the last few decades, signal processing has taken notable evolutionary leaps in terms of measurement – from being simple techniques for analysing analog or digital signals in time, frequency or joint time–frequency (TF) domain, to being complex techniques for analysis and interpretation in a higher dimensional domain. The intention behind this is simple – robust and efficient feature extraction; i.e. to identify specific signal markers or properties exhibited in one event, and use them to distinguish from characteristics exhibited in another event. The objective of our study is to give the reader a bird's eye view of the biomedical signal processing world with a zoomed-in perspective of feature extraction methodologies which form the basis of machine learning and hence, artificial intelligence. We delve into the vast world of feature extraction going across the evolutionary chain starting with basic A-to-D conversion, to domain transformations, to sparse signal representations and compressive sensing. It should be noted that in this manuscript we have attempted to explain key biomedical signal feature extraction methods in simpler fashion without detailing over mathematical representations. Additionally we have briefly touched upon the aspects of curse and blessings of signal dimensionality which would finally help us in determining the best combination of signal processing methods which could yield an efficient feature extractor. In other words, similar to how the laws of science behind some common engineering techniques are explained, in this review study we have attempted to postulate an approach towards a meaningful explanation behind those methods in developing a convincing and explainable reason as to which feature extraction method is suitable for a given biomedical signal.

[1]  Sridhar Krishnan,et al.  T wave alternans evaluation using adaptive time-frequency signal analysis and non-negative matrix factorization. , 2011, Medical engineering & physics.

[2]  Sridhar Krishnan,et al.  Time-Frequency Signal Synthesis and Its Application in Multimedia Watermark Detection , 2006, EURASIP J. Adv. Signal Process..

[3]  E.J. Candes,et al.  An Introduction To Compressive Sampling , 2008, IEEE Signal Processing Magazine.

[4]  Sridhar Krishnan,et al.  Sleep EMG analysis using sparse signal representation and classification , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[5]  Rangaraj M. Rangayyan,et al.  Adaptive time-frequency analysis of knee joint vibroarthrographic signals for noninvasive screening of articular cartilage pathology , 2000, IEEE Transactions on Biomedical Engineering.

[6]  Sridhar Krishnan,et al.  Time–Frequency Matrix Feature Extraction and Classification of Environmental Audio Signals , 2011, IEEE Transactions on Audio, Speech, and Language Processing.

[7]  Jie Zhu,et al.  Shearlet-based texture feature extraction for classification of breast tumor in ultrasound image , 2013, Biomed. Signal Process. Control..

[8]  April Khademi,et al.  Shift-Invariant DWT for Medical Image Classification , 2011 .

[9]  Dejan Markovic,et al.  Technology-Aware Algorithm Design for Neural Spike Detection, Feature Extraction, and Dimensionality Reduction , 2010, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[10]  Sridhar Krishnan,et al.  EEG seizure detection and epilepsy diagnosis using a novel variation of Empirical Mode Decomposition , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[11]  Liang He,et al.  Speaker verification using Fisher vector , 2014, The 9th International Symposium on Chinese Spoken Language Processing.

[12]  Elif Derya Übeyli,et al.  Wavelet transform feature extraction from human PPG, ECG, and EEG signal responses to ELF PEMF exposures: A pilot study , 2008, Digit. Signal Process..

[13]  Christopher J James,et al.  Independent component analysis for biomedical signals , 2005, Physiological measurement.

[14]  Karthikeyan Umapathy,et al.  Discriminative time-frequency kernels for gait analysis for amyotrophic lateral sclerosis , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[15]  Sridhar Krishnan,et al.  Reconstruction of ECG signals for compressive sensing by promoting sparsity on the gradient , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[16]  Sridhar Krishnan,et al.  Compressive Sensing of Electrocardiogram Signals by Promoting Sparsity on the Second-Order Difference and by Using Dictionary Learning , 2014, IEEE Transactions on Biomedical Circuits and Systems.

[17]  Yoshua Bengio,et al.  Why Does Unsupervised Pre-training Help Deep Learning? , 2010, AISTATS.

[18]  Sridhar Krishnan,et al.  Detection of linear chirp and non-linear chirp interferences in a spread spectrum signal by using Hough-Radon transform , 2002, ICASSP.

[19]  S. Akselrod,et al.  Selective discrete Fourier transform algorithm for time-frequency analysis: method and application on simulated and cardiovascular signals , 1996, IEEE Transactions on Biomedical Engineering.

[20]  Kang-Ping Lin,et al.  QRS feature extraction using linear prediction , 1989, IEEE Transactions on Biomedical Engineering.

[21]  Patrick J. Loughlin,et al.  Modified Cohen-Lee time-frequency distributions and instantaneous bandwidth of multicomponent signals , 2001, IEEE Trans. Signal Process..

[22]  Michael Unser,et al.  An Introduction to Sparse Stochastic Processes , 2014 .

[23]  Sridhar Krishnan,et al.  Time-frequency modeling and classification of pathological voices , 2002, Proceedings of the Second Joint 24th Annual Conference and the Annual Fall Meeting of the Biomedical Engineering Society] [Engineering in Medicine and Biology.

[24]  Kumaraswamy Nanthakumar,et al.  Spatiotemporal Frequency Analysis of Ventricular Fibrillation in Explanted Human Hearts , 2009, IEEE Transactions on Biomedical Engineering.

[25]  Sridhar Krishnan,et al.  Signal feature extraction by multi-scale PCA and its application to respiratory sound classification , 2012, Medical & Biological Engineering & Computing.

[26]  Sridhar Krishnan,et al.  Parametric Time-Frequency Analysis and Its Applications in Music Classification , 2010, EURASIP J. Adv. Signal Process..

[27]  Sridhar Krishnan,et al.  Wavelet packets-based speech enhancement for hearing aids application , 2005 .

[28]  Tara N. Sainath,et al.  FUNDAMENTAL TECHNOLOGIES IN MODERN SPEECH RECOGNITION Digital Object Identifier 10.1109/MSP.2012.2205597 , 2012 .

[29]  J.-J.J. Chen,et al.  Temporal feature extraction and clustering analysis of electromyographic linear envelopes in gait studies , 1990, IEEE Transactions on Biomedical Engineering.

[30]  U. Rajendra Acharya,et al.  Evolutionary algorithm based classifier parameter tuning for automatic diabetic retinopathy grading: A hybrid feature extraction approach , 2013, Knowl. Based Syst..

[31]  Danoush Hosseinzadeh,et al.  On the Use of Complementary Spectral Features for Speaker Recognition , 2008, EURASIP J. Adv. Signal Process..

[32]  Sridhar Krishnan,et al.  Sparse approximation of long-term biomedical signals for classification via dynamic PCA , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[33]  S. Krishnan,et al.  A Robust Audio Watermark Representation Based on Linear Chirps , 2006, IEEE Transactions on Multimedia.

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

[35]  Sridhar Krishnan,et al.  Audio feature clustering for hearing aid systems , 2009, 2009 IEEE Toronto International Conference Science and Technology for Humanity (TIC-STH).

[36]  Danoush Hosseinzadeh,et al.  Gaussian Mixture Modeling of Keystroke Patterns for Biometric Applications , 2008, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[37]  Pascal Frossard,et al.  Dictionary Learning for Stereo Image Representation , 2011, IEEE Transactions on Image Processing.

[38]  Sridhar Krishnan,et al.  A Wavelet-PCA-Based Fingerprinting Scheme for Peer-to-Peer Video File Sharing , 2010, IEEE Transactions on Information Forensics and Security.

[39]  Sridhar Krishnan,et al.  Foot gait time series estimation based on support vector machine , 2014, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[40]  Camille Couprie,et al.  Learning Hierarchical Features for Scene Labeling , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[41]  Sridhar Krishnan,et al.  Analysis of the electromyogram of rapid eye movement sleep using wavelet techniques , 2009, 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[42]  Pascal Frossard,et al.  Dictionary Learning , 2011, IEEE Signal Processing Magazine.

[43]  Sridhar Krishnan,et al.  Adventitious Sounds Identification and Extraction Using Temporal–Spectral Dominance-Based Features , 2011, IEEE Transactions on Biomedical Engineering.

[44]  A. B. Geva.  Feature extraction and state identification in biomedical signals using hierarchical fuzzy clustering , 2006, Medical and Biological Engineering and Computing.

[45]  Pascal Frossard,et al.  Dictionary learning: What is the right representation for my signal? , 2011 .

[46]  Karthikeyan Umapathy,et al.  Exploiting the ambiguity domain for non-stationary biomedical signal classification , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[47]  Alan S. Willsky,et al.  A Wavelet Packet Approach to Transient Signal Classification , 1995 .

[48]  Danoush Hosseinzadeh,et al.  Combining Vocal Source and MFCC Features for Enhanced Speaker Recognition Performance Using GMMs , 2007, 2007 IEEE 9th Workshop on Multimedia Signal Processing.

[49]  Kumaraswamy Nanthakumar,et al.  Transfer Function Estimation of the Right Ventricle of Canine Heart , 2009 .

[50]  Sridhar Krishnan,et al.  Non-negative matrix factorization and sparse representation for sleep signal classification , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[51]  Jonathan Tompson,et al.  Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation , 2014, NIPS.

[52]  Sridhar Krishnan,et al.  Identifying the potential for failure of businesses in the technology, pharmaceutical and banking sectors using kernel-based machine learning methods , 2009, 2009 IEEE International Conference on Systems, Man and Cybernetics.

[53]  Karthikeyan Umapathy,et al.  Discrimination of pathological voices using a time-frequency approach , 2005, IEEE Transactions on Biomedical Engineering.

[54]  N.R. Farnoud,et al.  Ultrasound backscatter signal characterization and classification using autoregressive modeling and machine learning algorithms , 2003, Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE Cat. No.03CH37439).

[55]  S. Krishnan,et al.  Chin EMG analysis for REM sleep behavior disorders , 2012, 2012 ISSNIP Biosignals and Biorobotics Conference: Biosignals and Robotics for Better and Safer Living (BRC).

[56]  Sridhar Krishnan,et al.  Telephone-quality pathological speech classification using empirical mode decomposition , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[57]  P. Dorian,et al.  Optimizing cardiac resuscitation outcomes using wavelet analysis , 2009, 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[58]  G. F. Hughes,et al.  On the mean accuracy of statistical pattern recognizers , 1968, IEEE Trans. Inf. Theory.

[59]  Jean Ponce,et al.  Task-Driven Dictionary Learning , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[60]  Sridhar Krishnan,et al.  MODIFIED SPREAD SPECTRUM AUDIO WATERMARKING ALGORITHM , 2004 .

[61]  Brendan J. Frey,et al.  Deep learning of the tissue-regulated splicing code , 2014, Bioinform..

[62]  S. Krishnan,et al.  Medical image texture analysis: A case study with small bowel, retinal and mammogram images , 2008, 2008 Canadian Conference on Electrical and Computer Engineering.

[63]  Sridhar Krishnan,et al.  Wavelet-based sparse functional linear model with applications to EEGs seizure detection and epilepsy diagnosis , 2012, Medical & Biological Engineering & Computing.

[64]  A. E. Cetin,et al.  Using a variation of empirical mode decomposition to remove noise from signals , 2011, 2011 21st International Conference on Noise and Fluctuations.

[65]  Krishnanand Balasundaram,et al.  Wavelet-based features for characterizing ventricular arrhythmias in optimizing treatment options , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[66]  Manuel Emilio Gegúndez-Arias,et al.  Detecting the Optic Disc Boundary in Digital Fundus Images Using Morphological, Edge Detection, and Feature Extraction Techniques , 2010, IEEE Transactions on Medical Imaging.

[67]  Sridhar Krishnan,et al.  Compressive sensing of ECG signals based on mixed pseudonorm of the first- and second-order differences , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[68]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[69]  G. Bodenstein,et al.  Feature extraction from the electroencephalogram by adaptive segmentation , 1977, Proceedings of the IEEE.

[70]  Karthikeyan Umapathy,et al.  Time-frequency signal decompositions for audio and speech processing , 2005 .

[71]  S. Krishnan,et al.  Empirical mode decomposition based sparse dictionary learning with application to signal classification , 2013, 2013 IEEE Digital Signal Processing and Signal Processing Education Meeting (DSP/SPE).

[72]  Andrzej Cichocki,et al.  Tensor Decompositions for Signal Processing Applications: From two-way to multiway component analysis , 2014, IEEE Signal Processing Magazine.

[73]  April Khademi,et al.  Shift-invariant discrete wavelet transform analysis for retinal image classification , 2007, Medical & Biological Engineering & Computing.

[74]  A. Burgess.  Towards a Unified Understanding of Event-Related Changes in the EEG: The Firefly Model of Synchronization through Cross-Frequency Phase Modulation , 2012, PloS one.

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

[76]  Sridhar Krishnan,et al.  Small bowel image classification using dual tree complex wavelet-based cross co-occurrence features and canonical discriminant analysis , 2015, 2015 International Conference on Advances in Computing, Communications and Informatics (ICACCI).

[77]  I. Osorio,et al.  Intrinsic time-scale decomposition: time–frequency–energy analysis and real-time filtering of non-stationary signals , 2007, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[78]  Steve Renals,et al.  Speaker verification using sequence discriminant support vector machines , 2005, IEEE Transactions on Speech and Audio Processing.

[79]  Sridhar Krishnan,et al.  Application of a variation of empirical mode decomposition and teager energy operator to EEG signals for mental task classification , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[80]  Sridhar Krishnan,et al.  Compressive Sensing of Foot Gait Signals and Its Application for the Estimation of Clinically Relevant Time Series , 2016, IEEE Transactions on Biomedical Engineering.

[81]  Kumaraswamy Nanthakumar,et al.  Predicting refibrillation from pre-shock waveforms in optimizing cardiac resuscitation , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[82]  Sridhar Krishnan,et al.  Pattern Classification of Signals Using Fisher Kernels , 2012 .

[83]  Sridhar Krishnan,et al.  Parametric Analysis of Ultrasound Backscatter Signals for Monitoring Cancer Cell Structural Changes During Cancer Treatment , 2007 .

[84]  Kaamran Raahemifar,et al.  Low sampling rate algorithm for wireless ECG systems based on compressed sensing theory , 2015, Signal Image Video Process..

[85]  Yin Zhang,et al.  A Compressive Sensing and Unmixing Scheme for Hyperspectral Data Processing , 2012, IEEE Transactions on Image Processing.

[86]  Sridhar Krishnan,et al.  Knee Joint Vibration Signal Analysis with Matching Pursuit Decomposition and Dynamic Weighted Classifier Fusion , 2013, Comput. Math. Methods Medicine.

[87]  Cornel Ioana,et al.  Small bowel image classification using cross-co-occurrence matrices on wavelet domain , 2009, Biomed. Signal Process. Control..

[88]  S. Krishnan,et al.  Ambiguity domain-based identification of altered gait pattern in ALS disorder , 2012, Journal of neural engineering.

[89]  Sridhar Krishnan,et al.  Dynamic Principal Component Analysis with Nonoverlapping Moving Window and Its Applications to Epileptic EEG Classification , 2014, TheScientificWorldJournal.

[90]  Rangaraj M. Rangayyan,et al.  Feature identification in the time-frequency plane by using the Hough-Radon transform , 2001, Pattern Recognit..

[91]  P. Dorian,et al.  Wavelet-based markers of ventricular fibrillation in optimizing human cardiac resuscitation , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[92]  Ting Sun,et al.  Single-pixel imaging via compressive sampling , 2008, IEEE Signal Process. Mag..

[93]  David Howard,et al.  A Comparison of Feature Extraction Methods for the Classification of Dynamic Activities From Accelerometer Data , 2009, IEEE Transactions on Biomedical Engineering.

[94]  Karthikeyan Umapathy,et al.  Time-Frequency Analysis via Ramanujan Sums , 2012, IEEE Signal Processing Letters.

[95]  Aswin C. Sankaranarayanan,et al.  Toward Compressive Camera Networks , 2014, Computer.

[96]  Karthikeyan Umapathy,et al.  Discriminative kernel learning in ambiguity domain , 2014, 2014 9th International Symposium on Communication Systems, Networks & Digital Sign (CSNDSP).

[97]  Sridhar Krishnan,et al.  Emotion Recognition Using Novel Speech Signal Features , 2007, 2007 IEEE International Symposium on Circuits and Systems.

[98]  Sridhar Krishnan,et al.  Advanced signal analysis for the detection of periodic limb movements from bilateral ankle actigraphy , 2017, Journal of sleep research.

[99]  Karthikeyan Umapathy,et al.  Audio Signal Processing Using Time-Frequency Approaches: Coding, Classification, Fingerprinting, and Watermarking , 2010, EURASIP J. Adv. Signal Process..

[100]  Witold Pedrycz,et al.  Fuzzy wavelet packet based feature extraction method and its application to biomedical signal classification , 2005, IEEE Transactions on Biomedical Engineering.

[101]  Sridhar Krishnan,et al.  Computer-assisted method for quantifying sleep eye movements that reflects medication effects , 2009, 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[102]  Karthikeyan Umapathy,et al.  A signal classification approach using time-width vs frequency band sub-energy distributions , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[103]  Mohammadreza Balouchestani,et al.  Advanced K-means clustering algorithm for large ECG data sets based on K-SVD approach , 2014, 2014 9th International Symposium on Communication Systems, Networks & Digital Sign (CSNDSP).

[104]  Sridhar Krishnan,et al.  Autoregressive and Cepstral Analysis of Electromyogram in Rapid Movement Sleep , 2009 .

[105]  Sridhar Krishnan,et al.  Pathological speech signal analysis and classification using empirical mode decomposition , 2013, Medical & Biological Engineering & Computing.

[106]  R. M. Rangayyan,et al.  Automatic de-noising of knee-joint vibration signals using adaptive time-frequency representations , 2006, Medical and Biological Engineering and Computing.

[107]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[108]  Steve Renals,et al.  Evaluation of kernel methods for speaker verification and identification , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[109]  Sridhar Krishnan,et al.  Audio scene analysis using parametric signal features , 2011, 2011 24th Canadian Conference on Electrical and Computer Engineering(CCECE).

[110]  B. Macq,et al.  Morphological feature extraction for the classification of digital images of cancerous tissues , 1996, IEEE Transactions on Biomedical Engineering.

[111]  Sridhar Krishnan,et al.  Chaotic time series prediction using knowledge based Green’s Kernel and least-squares support vector machines , 2007, 2007 IEEE International Conference on Systems, Man and Cybernetics.

[112]  Sridhar Krishnan,et al.  A variation of empirical mode decomposition with intelligent peak selection in short time windows , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[113]  Karthikeyan Umapathy,et al.  Perceptual Coding of Audio Signals Using Adaptive Time-Frequency Transform , 2006, EURASIP J. Audio Speech Music. Process..