Unsupervised classification of 12-lead ECG signals using wavelet tensor decomposition and two-dimensional Gaussian spectral clustering

Abstract Due to high dimensionality and multiple variables, unsupervised classification of 12-lead ECG signals involves challenges and difficulties. In order to automatically discover unknown physiological features from raw multivariate signals and detect abnormal cardiac activities of a subject, we proposed an unsupervised classification scheme of 12-lead ECG signals using wavelet tensor decomposition and two-dimensional Gaussian spectral clustering. After filtering and segmentation, each ECG sample is converted into a wavelet tensor by the Discrete Wavelet Packet Transform (DWPT). Main features of ECG samples can be clearly investigated in a multiple feature space constructed by the ECG lead, time and frequency sub-band. Then the Multilinear Principal Component Analysis (MPCA) is applied to reduce the dimensionality of ECG tensors as well as preserve the data interior structure. Taking account of both magnitude and orientation of feature vectors, a novel two-dimensional Gaussian spectral clustering (TGSC) is devised to cluster different 12-lead ECG samples. Furthermore, the dataset obtained from practical 12-lead ECG experiment and two datasets from PhysioBank are used to verify the efficiency of the proposed method. Clustering results show that more useful features of ECG signals can be extracted by the wavelet-tensor-based MPCA than by vector-based PCA. With the two-dimensional Gaussian proximity matrix, the clustering accuracy of TGSC is also higher than that of the traditional spectral clustering.

[1]  Saeed Setayeshi,et al.  A noise robust speech features extraction approach in multidimensional cortical representation using multilinear principal component analysis , 2015, Int. J. Speech Technol..

[2]  Anastasios Tefas,et al.  Spectral clustering and semi-supervised learning using evolving similarity graphs , 2015, Appl. Soft Comput..

[3]  Hong Yu,et al.  Local density adaptive similarity measurement for spectral clustering , 2011, Pattern Recognit. Lett..

[4]  U. Rajendra Acharya,et al.  Automated detection and localization of myocardial infarction using electrocardiogram: a comparative study of different leads , 2016, Knowl. Based Syst..

[5]  Sung-Nien Yu,et al.  Integration of independent component analysis and neural networks for ECG beat classification , 2008, Expert Syst. Appl..

[6]  Fan Li,et al.  A novel electrocardiogram parameterization algorithm and its application in myocardial infarction detection , 2015, Comput. Biol. Medicine.

[7]  Samarendra Dandapat,et al.  Automated detection of heart ailments from 12-lead ECG using complex wavelet sub-band bi-spectrum features , 2017, Healthcare technology letters.

[8]  Li Sun,et al.  ECG Analysis Using Multiple Instance Learning for Myocardial Infarction Detection , 2012, IEEE Transactions on Biomedical Engineering.

[9]  Mario Beauchemin A density-based similarity matrix construction for spectral clustering , 2015, Neurocomputing.

[10]  Vinod Kumar,et al.  Detection of myocardial infarction in 12 lead ECG using support vector machine , 2018, Appl. Soft Comput..

[11]  Majid Moavenian,et al.  A qualitative comparison of Artificial Neural Networks and Support Vector Machines in ECG arrhythmias classification , 2010, Expert Syst. Appl..

[12]  André Carlos Ponce de Leon Ferreira de Carvalho,et al.  Spectral methods for graph clustering - A survey , 2011, Eur. J. Oper. Res..

[13]  U. Rajendra Acharya,et al.  Automated characterization of coronary artery disease, myocardial infarction, and congestive heart failure using contourlet and shearlet transforms of electrocardiogram signal , 2017, Knowl. Based Syst..

[14]  Raymond R. Bond,et al.  A computer-human interaction model to improve the diagnostic accuracy and clinical decision-making during 12-lead electrocardiogram interpretation , 2016, J. Biomed. Informatics.

[15]  Mattias Ohlsson,et al.  Detecting acute myocardial infarction in the 12-lead ECG using Hermite expansions and neural networks , 2004, Artif. Intell. Medicine.

[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]  Muhammad Arif,et al.  Detection and Localization of Myocardial Infarction using K-nearest Neighbor Classifier , 2012, Journal of Medical Systems.

[18]  Haiping Lu,et al.  Boosting Discriminant Learners for Gait Recognition Using MPCA Features , 2009, EURASIP J. Image Video Process..

[19]  Elizabeth Ann Maharaj,et al.  Discriminant analysis of multivariate time series: Application to diagnosis based on ECG signals , 2014, Comput. Stat. Data Anal..

[20]  Hong He,et al.  A two-stage genetic algorithm for automatic clustering , 2012, Neurocomputing.

[21]  U. Rajendra Acharya,et al.  Analysis of Myocardial Infarction Using Discrete Wavelet Transform , 2010, Journal of Medical Systems.

[22]  Joos Vandewalle,et al.  A Multilinear Singular Value Decomposition , 2000, SIAM J. Matrix Anal. Appl..

[23]  Paul Rubel,et al.  A Novel Neural-Network Model for Deriving Standard 12-Lead ECGs From Serial Three-Lead ECGs: Application to Self-Care , 2010, IEEE Transactions on Information Technology in Biomedicine.

[24]  U. Rajendra Acharya,et al.  Automated characterization and classification of coronary artery disease and myocardial infarction by decomposition of ECG signals: A comparative study , 2017, Inf. Sci..

[25]  Michael I. Jordan,et al.  On Spectral Clustering: Analysis and an algorithm , 2001, NIPS.

[26]  Jian Yin,et al.  Optimizing Evaluation Metrics for Multitask Learning via the Alternating Direction Method of Multipliers , 2018, IEEE Transactions on Cybernetics.

[27]  U. Rajendra Acharya,et al.  Application of deep convolutional neural network for automated detection of myocardial infarction using ECG signals , 2017, Inf. Sci..

[28]  Lu Wang,et al.  Multilinear principal component analysis for face recognition with fewer features , 2010, Neurocomputing.

[29]  Samarendra Dandapat,et al.  Third-order tensor based analysis of multilead ECG for classification of myocardial infarction , 2017, Biomed. Signal Process. Control..

[30]  Madhuri S. Joshi,et al.  Analysis of Multi-Lead ECG Signals using Decision Tree Algorithms , 2016 .

[31]  Hong He,et al.  Automatic pattern recognition of ECG signals using entropy-based adaptive dimensionality reduction and clustering , 2017, Appl. Soft Comput..

[32]  U. Rajendra Acharya,et al.  Automated Diagnosis of Myocardial Infarction ECG Signals Using Sample Entropy in Flexible Analytic Wavelet Transform Framework , 2017, Entropy.

[33]  Constantine Kotropoulos,et al.  Non-Negative Multilinear Principal Component Analysis of Auditory Temporal Modulations for Music Genre Classification , 2010, IEEE Transactions on Audio, Speech, and Language Processing.

[34]  Enrique Romero,et al.  ECG assessment based on neural networks with pretraining , 2016, Appl. Soft Comput..

[35]  Tülin Inkaya,et al.  A parameter-free similarity graph for spectral clustering , 2015, Expert Syst. Appl..

[36]  Pei-Chann Chang,et al.  Myocardial infarction classification with multi-lead ECG using hidden Markov models and Gaussian mixture models , 2012, Appl. Soft Comput..

[37]  Liqing Zhang,et al.  Cardiology knowledge free ECG feature extraction using generalized tensor rank one discriminant analysis , 2014, EURASIP J. Adv. Signal Process..

[38]  Haiping Lu,et al.  MPCA: Multilinear Principal Component Analysis of Tensor Objects , 2008, IEEE Transactions on Neural Networks.

[39]  U. Rajendra Acharya,et al.  Automated characterization of cardiovascular diseases using relative wavelet nonlinear features extracted from ECG signals , 2018, Comput. Methods Programs Biomed..

[40]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .

[41]  Juan Pablo Martínez,et al.  Cross-Database Evaluation of a Multilead Heartbeat Classifier , 2012, IEEE Transactions on Information Technology in Biomedicine.

[42]  Pietro Perona,et al.  Self-Tuning Spectral Clustering , 2004, NIPS.