Shared Weighted Continuous Wavelet Capsule Network for Electrocardiogram Biometric Identification

Background:Recently, a marginalized particle-extended Kalman filter (MP-EKF) has been proposed for electrocardiogram (ECG) signal denoising. Similar to particle filters, the performance of MP-EKF relies heavily on the definition of proper particle weighting strategy. In this paper, we aim to investigate the performance of MP-EKF under different particle weighting strategies in both stationary and nonstationary noises. Some of these particle weighting strategies are introduced for the first time for ECG denoising.Methods:In this paper, the proposed particle weighting strategies use different mathematical functions to regulate the behaviors of particles based on noisy measurements and a synthetic ECG signal built using feature parameters of ECG dynamic model. One of these strategies is a fuzzy-based particle weighting method that is defined to adapt its function based on different input signal-to-noise ratios (SNRs). To evaluate the proposed particle weighting strategies, the denoising performance of MP-EKF was evaluated on MIT-BIH normal sinus rhythm database at 11 different input SNRs and in four different types of artificial and real noises. For quantitative comparison, the SNR improvement measure was used, and for qualitative comparison, the multi-scale entropy-based weighted distortion measure was used.Results:The experimental results revealed that the fuzzy-based particle weighting strategy exhibited a very well and reliable performance in both stationary and nonstationary noisy environments.Conclusion:We concluded that the fuzzy-based particle weighting strategy is the best-suited strategy for MP-EKF framework because it adaptively and automatically regulates the behaviors of particles in different noisy environments.

Cardiovascular Diseases (CVD) requires precise and efficient diagnostic tools. The manual analysis of Electrocardiograms (ECGs) is labor-intensive, necessitating the development of automated methods to enhance diagnostic accuracy and efficiency. This research aimed to develop an automated ECG classification using Continuous Wavelet Transform (CWT) and Deep Convolutional Neural Network (DCNN), and transform 1D ECG signals into 2D spectrograms using CWT and train a DCNN to accurately detect abnormalities associated with CVD. The DCNN is trained on datasets from PhysioNet and the MIT-BIH and the MIT-BIH arrhythmia dataset. The integrated CWT and DCNN enable simultaneous classification of multiple ECG abnormalities alongside normal signals. This analytical observational research employed CWT to generate spectrograms from 1D ECG signals, as input to a DCNN trained on diverse datasets. The model is evaluated using performance metrics, such as precision, specificity, recall, overall accuracy, and F1-score. The proposed algorithm demonstrates remarkable performance metrics with a precision of 100% for normal signals, an average specificity of 100%, an average recall of 97.65%, an average overall accuracy of 98.67%, and an average F1-score of 98.81%. This model achieves an approximate average overall accuracy of 98.67%, highlighting its effectiveness in detecting CVD. The integration of CWT and DCNN in ECG classification improves accuracy and classification capabilities, addressing the challenges with manual analysis. This algorithm can reduce misdiagnoses in primary care and enhance efficiency in larger medical institutions. By contributing to automated diagnostic tools for cardiovascular disorders, it can significantly improve healthcare practices in the field of CVD detection.

Automatic detection and classification of electrocardiogram (ECG) signals is of great importance for diagnosis of cardiac abnormalities. A method is proposed here to classify different cardiac abnormalities like Cardiomyopathy, Myocardial infarction, Dysrhythmia, Myocardial hypertrophy and Valvular heart disease. Support Vector Machine (SVM) has been used to classify the patterns inherent in the features extracted through Continuous Wavelet Transform (CWT) of different ECG signals. CWT allows a time domain signal to be transformed into time-frequency domain such that frequency characteristics and the location of particular features in a time series may be highlighted simultaneously. Thus it allows accurate extraction of feature from non-stationary signals like ECG. SVM transforms the multi-dimensional feature space into a linearly separable feature space with the help of Kernel function. In the present work, SVM in regression mode has been successfully applied for the classification of cardiac abnormalities with good diagnostic accuracy.

A system for heartbeat classification is provided a solution against the mortality due to cardiac arrest. Here, an automated real-time system proposed to identify and classify the abnormalities in the electrocardiogram (ECG) signal or its variability. In healthcare services, multiple monitoring systems are available to monitor cardiac health conditions. Although, efficient monitoring and the alert system needed for prevention from any health loss or mortality. In this work, a public database is utilized named MIT-BIH Arrhythmia (MITA) ECG Database and Normal Sinus Rhythm Database (NSRDB). In the classification process features play a key role to identify the class of the signal that may indicate the particular health condition. Here, a statistical technique is used for the analysis of HRV data of ECG signal and decision tree for classification of parameters extracted from HRV signals. In this paper, a method developed for arrhythmia detection using time and time-frequency domain statistical features. Therefore, five statistical parameters of HRV signals were computed and considered as features of normal and arrhythmia HRV signals, used in training and test data in the decision tree classifiers. The use of multiple sizes of training dataset gives accuracy variation as well as the classification rate. As per the comparison of both feature sets and training dataset, Time-frequency feature is efficiently employable for identification of signal class that represents the cardiac health condition, its accuracy in classification reached up to 99.2% with 20:80 data distribution as a training and testing dataset.

We present an innovative and robust solution to both biometric and emotion identification using the electrocardiogram (ECG). The ECG represents the electrical signal that comes from the contraction of the heart muscles, indirectly representing the flow of blood inside the heart, it is known to convey a key that allows biometric identification. Moreover, due to its relationship with the nervous system, it also varies as a function of the emotional state. The use of information-theoretic data models, associated with data compression algorithms, allowed to effectively compare ECG records and infer the person identity, as well as emotional state at the time of data collection. The proposed method does not require ECG wave delineation or alignment, which reduces preprocessing error. The method is divided into three steps: (1) conversion of the real-valued ECG record into a symbolic time-series, using a quantization process; (2) conditional compression of the symbolic representation of the ECG, using the symbolic ECG records stored in the database as reference; (3) identification of the ECG record class, using a 1-NN (nearest neighbor) classifier. We obtained over 98% of accuracy in biometric identification, whereas in emotion recognition we attained over 90%. Therefore, the method adequately identify the person, and his/her emotion. Also, the proposed method is flexible and may be adapted to different problems, by the alteration of the templates for training the model.

This paper investigates the application of the newly proposed Kronecker-based method for the reconstruction of compressively sensed electrocardiogram (ECG) signals. By applying the Kronecker-based method, ECG signal acquisition is done in smaller lengths. Collection of smaller length of ECG signals leads to fewer arithmetic operations during the compression phase. Instead of recovering individually in smaller lengths, recovery is done over several concatenated segments. This newly proposed recovery method improves the quality of the reconstructed signal when compared to the traditional recovery done without concatenation. Two random measurement matrices, namely the Gaussian and the Bernoulli matrices, are considered as sensing matrices in this study and the methodology is evaluated using 10 ECG signals acquired from the MIT arrhythmia database. The random Bernoulli matrix is found to provide better quality of recovered compressed ECG signal even with the traditional compressive recovery techniques. Recovery by the newly proposed Kroneckerbased method results in higher SNR in all the ECG signals when the compression ratio (CR) is 25% or 50% and when the CR is 75%, improvement is observed in majority of the ECG signals. Lower CRs provide better reconstruction than higher CRs. The Kronecker-based recovery method may be useful for wearable ECG devices.

The developments in computer-aided diagnostic technology have promoted the advancement of the Medical Internet of Things. Because electrocardiogram (ECG) signals can reflect the health of the human heart, their classification is conducive to diagnosing heart disease. In this study, a novel classification method for ECG signals based on the continuous wavelet transform (CWT) and a convolutional neural network (CNN) is proposed. The proposed method can construct the time-frequency image of an ECG signal using CWT. Subsequently, the image is input to a CNN model. By leveraging the GoogLeNet network model for image recognition, the model establishes an accurate mapping for recognizing different ECG signals. Multiple public datasets are used to validate the effectiveness of the proposed algorithm. In addition, this method exhibits a higher recognition accuracy than other methods.

The Electrocardiogram (ECG) is a significant tool to investigate the electrical activity of the heart. Even though P and T waves reveal very useful information, their accurate detection is a difficult and challenging task on account of noise, baseline drift and odd morphologies. The need for a rapid and effective detection algorithm motivated us to propose two automated methods: the percentile based Automatic Detection (pAD) and the Graphical based Automatic Detection (gAD). Both algorithms use statistical and probabilistic concepts to achieve adequate delineation and detection of the waves. The former uses the percentile as an adaptive threshold to define the location of these waves. The latter uses a feature wave-bank to train a graphical probabilistic model named as Hidden Conditional Random Field (HCRF). The gAD algorithm takes advantage of the monotonicity and the slope of an ECG to detect and collect waves, which imports to the graphical model and classifies them to P or T waves. The efficiency of our proposed algorithms has been evaluated on 10 long-term (24-hour) ECG recordings of MIT-BIH Normal Sinus Rhythm Database. The training set we used for gAD was very small, only the 0.2% of the total number of the available waves. The results show a significant and promising detection accuracy rate.

In this paper, the robust and efficient filtering framework based on the cubature Kalman filter (CKF) is proposed for electrocardiogram (ECG) denoising. The CKF preserves the second-order content in corrupted measurements and provides the best-known approximation under the Gaussian conjecture. The proposed methodology considers angular velocity in two cases. The performance of CKF is evaluated on numerous ECGs arbitrarily taken from MIT-BIH normal sinus rhythm database. Furthermore, the accuracy and robustness of the CKF have tested on muscle artifacts and white Gaussian noises in the range of -5 to 10 dB input signal-to-noise ratio (SNR). The proposed methodology is compared with extended Kalman filter (EKF) structures and simulation results show that the CKF framework provides better SNR improvement under both noise cases.

This paper proposes a new method to identify people using Electrocardiogram (ECG), particularly the QRS complex which has been proven to be stable against heart rate variability and convenient to be used alone as a biometric feature. 324 QRS complexes are extracted from ECGs of 18 subjects in Physionet's MIT-BIH Normal Sinus Rhythm Database (NSRDB). Multilayer Perceptron (MLP) and Radial Basis Function (RBF) neural networks are used to classify those QRS complexes. If the training data are chosen carefully to cover a wide range of input values (i.e. QRS complexes), then the classification accuracy rates can reach above 98% using MLP and 97% using RBF.

Electrocardiogram (ECG) signal processing aims basically 1) at artifact reduction to make the ECG signals cleaner and better interpretable by human or machine observers, 2) at revealing aspects not immediately observable in plain measured ECG signals even after artifact reduction, or 3) at diagnostics decision support and automated ECG signal interpretation, including classification of ECG signals into different classes associated with normal or pathological heart function. Thus, sports related applications aside, body surface ECG signal processing aims at enhancing ECG based diagnostics. In this Chapter, we review and demonstrate a statistical signal processing approach, independent component analysis (ICA), which is inherently very suitable for ECG signal processing regarding the aims 1) and 2) above, and also equally applicable as a component in systems aimed at accomplishing the aim 3). For more on general ECG signal processing, the reader is directed to the textbook written by Sornmo & Laguna (2005), and for a thorough treatment of ICA to the Hyvarinen’s book (Hyvarinen et al., 2001). A concise review on ICA in ECG signal processing has been presented by Castells et al. (2007a). In this Chapter, we describe and illustrate several widely adopted applications of ICA in ECG signal processing, and discuss associated practical aspects, some of which are not generally found in the literature. The treatment of the matter is aimed at conceptual and practical understanding, leaving the mathematical derivations and proofs far mostly for the interested reader to find in the references. ICA (Castells et al., 2007a; Comon, 1994; Hyvarinen et al., 2001; Hyvarinen & Oja, 2000; Naik & Kumar, 2011) is a statistical signal processing method for decomposing a set of signals into a set of mutually independent component signals. In general, in the applications of ICA, including in ECG signal processing, the objective is that the resulting independent component signals are the original source signals. Since ICA operates purely based on the input signals and a few assumptions, ICA belongs to the class of methods called blind source separation methods. For ICA, a source signal is called an independent component (IC). The terms ‘IC’ and ‘source signal’ are here used interchangeably. For ECG, the source signals are the bioelectrical signals generated by the heart, and all the possible artifact signals. Generally, ICA input signals are the observed signals, which may be measurement time series, such as sampled voltage values in time as in the case of ECGs, image pixel values, or basically any sets of values fulfilling the assumptions of ICA. In the sequel, the term

Present paper deals with design and development of digital FIR filters. Heart diseases, which are one of the death reasons, are among the several serious problems in this century and as per the latest survey, 60% of the patients die due to Heart diseases. Electrocardiogram (ECG) signal plays a vital role in the monitoring and diagnosis of the health conditions of human heart. The basic ECG signal has the frequency range from .5Hz to 100Hz. The most significant noises that corrupt ECG signal are power line interference and baseline wanders. It becomes difficult for the Specialist to diagnose the diseases if artifacts are present in the ECG signal. Designing digital filters to reduce these noises is very important in ECG signal processing. In this work a digital FIR filter for reducing 50Hz power line noise in ECG signal is designed and implemented with different windowing methods as of Hamming, Kaiser, and Chebyshev. The work has been done in MATLAB environment. The result obtained for all FIR filters are compared by comparing the waveforms of the original and filtered ECG signals. The filter which gives the best results is the one using Chebyshev Window.

Electrocardiogram (ECG) signal evaluation is routinely used in clinics as a significant diagnostic method for detecting arrhythmia. However, it is very labor intensive to externally evaluate ECG signals, due to their small amplitude. Using automated detection and classification methods in the clinic can assist doctors in making accurate and expeditious diagnoses of diseases. In this study, we developed a classification method for arrhythmia based on the combination of a convolutional neural network and long short-term memory, which was then used to diagnose eight ECG signals, including a normal sinus rhythm. The ECG data of the experiment were derived from the MIT-BIH arrhythmia database. The experimental method mainly consisted of two parts. The input data of the model were two-dimensional grayscale images converted from one-dimensional signals, and detection and classification of the input data was carried out using the combined model. The advantage of this method is that it does not require performing feature extraction or noise filtering on the ECG signal. The experimental results showed that the implemented method demonstrated high classification performance in terms of accuracy, specificity, and sensitivity equal to 99.01%, 99.57%, and 97.67%, respectively. Our proposed model can assist doctors in accurately detecting arrhythmia during routine ECG screening.

A multi-layer convolutional neural network (MCNN) with hyperparameter optimization (HyperMCNN) is proposed for classifying human electrocardiograms (ECGs). For performance tests of the HyperMCNN, ECG recordings for patients with cardiac arrhythmia (ARR), congestive heart failure (CHF), and normal sinus rhythm (NSR) were obtained from three PhysioNet databases: MIT-BIH Arrhythmia Database, BIDMC Congestive Heart Failure Database, and MIT-BIH Normal Sinus Rhythm Database, respectively. The MCNN hyperparameters in convolutional layers included number of filters, filter size, padding, and filter stride. The hyperparameters in max-pooling layers were pooling size and pooling stride. Gradient method was also a hyperparameter used to train the MCNN model. Uniform experimental design approach was used to optimize the hyperparameter combination for the MCNN. In performance tests, the resulting 16-layer CNN with an appropriate hyperparameter combination (16-layer HyperMCNN) was used to distinguish among ARR, CHF, and NSR. The experimental results showed that the average correct rate and standard deviation obtained by the 16-layer HyperMCNN were superior to those obtained by a 16-layer CNN with a hyperparameter combination given by Matlab examples. Furthermore, in terms of performance in distinguishing among ARR, CHF, and NSR, the 16-layer HyperMCNN was superior to the 25-layer AlexNet, which was the neural network that had the best image identification performance in the ImageNet Large Scale Visual Recognition Challenge in 2012.

The R-R interval (RRI) fluctuation in electrocardiogram (ECG) is called heart rate variability (HRV), which reflects activities of the autonomic nervous system (ANS) and has been used for various health monitoring services. Accurate R wave detection is crucial for success in HRV-based health monitoring services; however, ECG artifacts often cause missing R waves and deteriorate the accuracy of HRV analysis. The present work proposes a new missing RRI interpolation technique based on Just-In-Time (JIT) modeling. In the JIT modeling framework, a local regression model is built by weighing samples stored in the database according to the distance from a query and output is estimated only when an estimate is requested. The proposed method builds a local model and estimates missing RRI only when an RRI detection error is detected. Locally weighted partial least squares (LWPLS) is adopted for local model construction. The proposed method is referred to as LWPLS-based RRI interpolation (LWPLS-RI). The performance of the proposed LWPLS-RI was evaluated through its application to RRI data with artificial missing RRIs. We used the MIT-BIH Normal Sinus Rhythm Database for nominal RRI dataset construction. Missing RRIs were artificially introduced and they were interpolated by the proposed LWPLS-RI. In addition, MEAN that replaces the missing RRI by a mean of the past RRI data was compared as a conventional method. The result showed that the proposed LWPLS-RI improved root mean squared error (RMSE) of RRI by about 70% in comparison with MEAN. In addition, the proposed method realized precise HRV analysis. The proposed method will contribute to the realization of precise HRV-based health monitoring services.