Max-plus and min-plus projection autoassociative morphological memories and their compositions for pattern classification

Cardiac characteristics underlying the time/frequency domain features are limited and not comprehensive enough to reflect the temporal/dynamical nature of ECG patterns. This paper proposes a dynamical ECG recognition framework for human identification and cardiovascular diseases classification via a dynamical neural learning mechanism. The proposed method consists of two phases: a training phase and a test phase. In the training phase, cardiac dynamics within ECG signals is extracted (approximated) accurately by using radial basis function (RBF) neural networks through deterministic learning mechanism. The obtained cardiac system dynamics is represented and stored in constant RBF networks. An ECG signature is then derived from the extracted cardiac dynamics along the periodic ECG state trajectories. A bank of estimators is constructed using the extracted cardiac dynamics to represent the trained gait patterns. In the test phase, recognition errors are generated and taken as the similarity measure by comparing the cardiac dynamics of the trained ECG patterns and the dynamics of the test ECG pattern. Rapid recognition of a test ECG pattern begins with measuring the state of test pattern, and automatically proceeds with the evolution of the recognition error system. According to the smallest error principle, the test ECG pattern can be rapidly recognized. This kind of cardiac dynamics information represents the beat-to-beat temporal change of ECG modifications and the temporal/dynamical nature of ECG patterns. Therefore, the amount of discriminability provided by the cardiac dynamics is larger than the original signals. This paper further discusses the extension of the proposed method for cardiovascular diseases classification. The constructed recognition system can distinguish and assign dynamical ECG patterns to predefined classes according to the similarity of cardiac dynamics. Experiments are carried out on the FuWai and PTB ECG databases to demonstrate the effectiveness of the proposed method.

[1]  Giacomo Boracchi,et al.  ECG Monitoring in Wearable Devices by Sparse Models , 2016, ECML/PKDD.

[2]  Cong Wang,et al.  Relationship Between Persistent Excitation Levels and RBF Network Structures, With Application to Performance Analysis of Deterministic Learning , 2017, IEEE Transactions on Cybernetics.

[3]  S Suave Lobodzinski,et al.  Integrated heart failure telemonitoring system for homecare. , 2010, Cardiology journal.

[4]  José Luís Oliveira,et al.  Telecardiology through ubiquitous Internet services , 2012, Int. J. Medical Informatics.

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

[6]  Cong Wang,et al.  Human gait recognition based on deterministic learning through multiple views fusion , 2016, Pattern Recognit. Lett..

[7]  Wei Zeng,et al.  Fusion of spatial-temporal and kinematic features for gait recognition with deterministic learning , 2017, Pattern Recognit..

[8]  G. Dower,et al.  On Deriving the Electrocardiogram from Vectorcardiographic Leads , 1980, Clinical cardiology.

[9]  F. J. Narcowich,et al.  Persistency of Excitation in Identification Using Radial Basis Function Approximants , 1995 .

[10]  Dimitrios Hatzinakos,et al.  Analysis of Human Electrocardiogram for Biometric Recognition , 2008, EURASIP J. Adv. Signal Process..

[11]  Paolo Crippa,et al.  Multi-Class ECG Beat Classification Based on a Gaussian Mixture Model of Karhunen-Loève Transform , 2020 .

[12]  Kholkhal Mourad,et al.  Efficient automatic detection of QRS complexes in ECG signal based on reverse biorthogonal wavelet decomposition and nonlinear filtering , 2016 .

[13]  Meng-Wei Hsu,et al.  A cloud computing based 12-lead ECG telemedicine service , 2012, BMC Medical Informatics and Decision Making.

[14]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[15]  Ola Pettersson,et al.  ECG analysis: a new approach in human identification , 2001, IEEE Trans. Instrum. Meas..

[16]  P. C. Cortez,et al.  New approach for T-wave peak detection and T-wave end location in 12-lead paced ECG signals based on a mathematical model. , 2013, Medical engineering & physics.

[17]  Brenda K. Wiederhold,et al.  ECG to identify individuals , 2005, Pattern Recognit..

[18]  Fahim Sufi,et al.  Faster person identification using compressed ECG in time critical wireless telecardiology applications , 2011, J. Netw. Comput. Appl..

[19]  G E Dower,et al.  XYZ data interpreted by a 12-lead computer program using the derived electrocardiogram. , 1979, Journal of electrocardiology.

[20]  Steven A. Israel,et al.  A Sequential Procedure for Individual Identity Verification Using ECG , 2009, EURASIP J. Adv. Signal Process..

[21]  Danilo Costarelli,et al.  Neural network operators: Constructive interpolation of multivariate functions , 2015, Neural Networks.

[22]  Gianluca Vinti,et al.  Convergence for a family of neural network operators in Orlicz spaces , 2017 .

[23]  Phalguni Gupta,et al.  Correlation-based classification of heartbeats for individual identification , 2011, Soft Comput..

[24]  W. Todd Scruggs,et al.  eigenPulse: Robust human identification from cardiovascular function , 2008, Pattern Recognit..

[25]  Adrian D. C. Chan,et al.  Wavelet Distance Measure for Person Identification Using Electrocardiograms , 2008, IEEE Transactions on Instrumentation and Measurement.

[26]  Cong Wang,et al.  Rapid Detection of Small Oscillation Faults via Deterministic Learning , 2011, IEEE Transactions on Neural Networks.

[27]  G E Dower,et al.  Deriving the 12-lead electrocardiogram from four (EASI) electrodes. , 1988, Journal of electrocardiology.

[28]  Giacomo Capizzi,et al.  Automatic heart activity diagnosis based on Gram polynomials and probabilistic neural networks , 2018, Biomedical engineering letters.

[29]  Pierre Baldi,et al.  A theory of local learning, the learning channel, and the optimality of backpropagation , 2015, Neural Networks.

[30]  Mauro Forti,et al.  Necessary and sufficient condition for multistability of neural networks evolving on a closed hypercube , 2014, Neural Networks.

[31]  Joseph A. O'Sullivan,et al.  ECG Biometric Recognition: A Comparative Analysis , 2012, IEEE Transactions on Information Forensics and Security.

[32]  Gianluca Vinti,et al.  Max-product neural network and quasi-interpolation operators activated by sigmoidal functions , 2016, J. Approx. Theory.

[33]  DeLiang Wang,et al.  Temporal pattern processing , 1998 .

[34]  Cong Wang,et al.  Learning from neural control , 2006, IEEE Transactions on Neural Networks.

[35]  Cong Wang,et al.  Deterministic Learning and Rapid Dynamical Pattern Recognition , 2007, IEEE Transactions on Neural Networks.

[36]  David J. Hill,et al.  Deterministic Learning Theory , 2009 .

[37]  Cong Wang,et al.  Rapid Oscillation Fault Detection and Isolation for Distributed Systems via Deterministic Learning , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[38]  Clemens Elster,et al.  Verification of humans using the electrocardiogram , 2007, Pattern Recognit. Lett..

[39]  L. Billeci,et al.  An efficient unsupervised fetal QRS complex detection from abdominal maternal ECG , 2014, Physiological measurement.

[40]  Dimitry M. Gorinevsky,et al.  On the persistency of excitation in radial basis function network identification of nonlinear systems , 1995, IEEE Trans. Neural Networks.

[41]  Gianluca Vinti,et al.  Pointwise and uniform approximation by multivariate neural network operators of the max-product type , 2016, Neural Networks.

[42]  Wei Zeng,et al.  Human gait recognition via deterministic learning , 2012, Neural Networks.

[43]  Manas Rakshit,et al.  An efficient wavelet-based automated R-peaks detection method using Hilbert transform , 2017 .

[44]  Carmen C. Y. Poon,et al.  Using the Timing Information of Heartbeats as an Entity Identifier to Secure Body Sensor Network , 2008, IEEE Transactions on Information Technology in Biomedicine.

[45]  Gianluca Vinti,et al.  Approximation by Max-Product Neural Network Operators of Kantorovich Type , 2016 .

[46]  K. Egiazarian,et al.  Comparative study of morphological and time-frequency ECG descriptors for heartbeat classification. , 2006, Medical engineering & physics.

[47]  Carlo Sansone,et al.  Electrocardiogram pattern recognition and analysis based on artificial neural networks and support vector machines: a review. , 2013, Journal of healthcare engineering.

[48]  Moncef Gabbouj,et al.  Real-Time Patient-Specific ECG Classification by 1-D Convolutional Neural Networks , 2016, IEEE Transactions on Biomedical Engineering.