ECG Beat Classification Research Articles

Automated ECG beat classification using DWT and Hilbert transform-based PCA-SVM classifier

Automated ECG beat classification using DWT and Hilbert transform-based PCA-SVM classifier

Proposing feature engineering method based on deep learning and K-NNs for ECG beat classification and arrhythmia detection.

Arrhythmia is slow, fast or irregular heartbeat. Manual ECG assessment and disease classification is an error-prone task because of vast differences in ECG morphology and difficulty in accurate identifying ECG components. Moreover, proposing a computer-aided diagnosis system for heartbeat classification can be useful when access to medical care centers is difficult or impossible. Therefore, the main aim of this study is classifying ECG beats for arrhythmia detection (four beat classes are considered). Previous studies have proposed different methods based on traditional machine learning and/or deep learning. In this paper, a novel feature engineering method is proposed based on deep learning and K-NNs. The features extracted by our proposed method are classified with different classifiers such as decision trees, SVMs with different kernels and random forests. Our proposed method has reasonably good performance for beat classification and achieves the average Accuracy of 99.77%, AUC of 99.99%, Precision of 99.75% and Recall of 99.30% using fivefold Cross Validation strategy. The main advantage of the proposed method is its low computational time compared to training deep learning models from scratch and its high accuracy compared to the traditional machine learning models. The strength and suitability of the proposed method for feature extraction is shown by the high balance between sensitivity and specificity.

GABC based neuro-fuzzy classifier with hybrid features for ECG Beat classification

The main objective of the proposed methodology is to classify an ECG signal as normal or abnormal using the optimal neuro-fuzzy classifier. The proposed work consists of two phases namely, feature extraction and neuro-fuzzy classifier based classification. The beat signals are initially taken from the physio-bank ATM. Then, three types of features are extracted from each signal namely, Morphological-based features, Haar wavelet-based features, and Tri-spectrum based features. After feature extraction, the optimal neuro-fuzzy classifier is classifying the beat signal as normal or abnormal. Here, Artificial Bee Colony (ABC) algorithm is combined with Genetic Algorithm (GA) for training the neuro-fuzzy classifier. For experimental evaluation, the MIT-BIH Arrhythmia Database is utilized and the performances are analyzed in terms of accuracy, sensitivity, and specificity. The experimental results clearly demonstrated that the proposed technique outperformed by having better accuracy of 93% when compared existing technique achieved 84% only.

An Automated ECG Beat Classification System Using Deep Neural Networks with an Unsupervised Feature Extraction Technique

An automated classification system based on a Deep Learning (DL) technique for Cardiac Disease (CD) monitoring and detection is proposed in this paper. The proposed DL architecture is divided into Deep Auto-Encoders (DAEs) as an unsupervised form of feature learning and Deep Neural Networks (DNNs) as a classifier. The objective of this study is to improve on the previous machine learning technique that consists of several data processing steps such as feature extraction and feature selection or feature reduction. It is also noticed that the previously used machine learning technique required human interference and expertise in determining robust features, yet was time-consuming in the labeling and data processing steps. In contrast, DL enables an embedded feature extraction and feature selection in DAEs pre-training and DNNs fine-tuning process directly from raw data. Hence, DAEs is able to extract high-level of features not only from the training data but also from unseen data. The proposed model uses 10 classes of imbalanced data from ECG signals. Since it is related to the cardiac region, abnormality is usually considered for an early diagnosis of CD. In order to validate the result, the proposed model is compared with the shallow models and DL approaches. Results found that the proposed method achieved a promising performance with 99.73% accuracy, 91.20% sensitivity, 93.60% precision, 99.80% specificity, and a 91.80% F1-Score. Moreover, both the Receiver Operating Characteristic (ROC) curve and the Precision-Recall (PR) curve from the confusion matrix showed that the developed model is a good classifier. The developed model based on unsupervised feature extraction and deep neural network is ready to be used on a large population before its installation for clinical usage.

A cascaded classifier for multi-lead ECG based on feature fusion

Background and ObjectiveElectrocardiogram (ECG) is an important diagnostic tool for the diagnosis of heart disorders. Useful features and well-designed classification method are crucial for automatic diagnosis. However, most of the contributions were in single lead or two-lead ECG signal and only features from single lead were used to classify the ECG beats. In this paper, a cascaded classification system is proposed to extract features and classify heartbeats in order to improve the performance of ECG beat classification via multi-lead ECG. MethodsIn contrast with most of the literatures, ten signal features were chosen and run on each of the 12 leads separately. Based on these features, we developed a novel feature fusion method combining information from all available leads, and then implemented a cascaded classifier utilizing random forest (RF) and multilayer perceptron (MLP). Besides, in order to reduce the feature space dimension, principal component analysis (PCA) was applied in the method. MaterialsFour open source databases including MIT-BIH Arrythmia Database, QT Database, MIT-BIH Supraventricular Arrhythmia Database and St. Petersburg Institute of Cardiological Technics 12-lead Arrhythmia Database (INCART Database) were used in this work. These four databases are different in classes of beats, volume of dataset, number of individual volunteers. Except INCART database, in which the recording format is 12−lead, the other three databases consist of 2−lead recordings. Above all, they all have annotations for every single beat including the type of each beat. ConclusionsExtensive experimental results shown that the average accuracy achieved 99.3%, 99.8%, 97.6% and 99.6% on four databases respectively. Compared with most state-of-the-art methods, our work has better performance and strong generalization capability.

A deep learning approach for ECG-based heartbeat classification for arrhythmia detection

Classification is one of the most popular topics in healthcare and bioinformatics, especially in relation to arrhythmia detection. Arrhythmias are irregularities in the rate or rhythm of the heartbeat which, in some cases, may occur sporadically in a subject’s daily life. To capture these infrequent events, a Holter device is usually employed to record long-term ECG data. Therefore, the automatic recognition of abnormal heartbeats from a large amount of ECG data is an important and essential task. In the last two decades, a huge number of methods have been proposed to address the problem of ECG beat classification. At the same time, deep learning has advanced rapidly since the early 2000s and now demonstrates a state-of-the-art performance in various fields. In this paper, we propose a novel deep learning approach for ECG beat classification. We have conducted the experiments on the well-known MIT–BIH Arrhythmia Database, and compared our results with the scientific literature. The final results show that our model is not only more efficient than the state of the art in terms of accuracy, but also competitive in terms of sensitivity and specificity.

ECG beat classification using machine learning techniques

An arrhythmia is an abnormality in the heart rhythm, or heartbeat pattern. ECG beats can be classified into six different arrhythmia beat types (left bundle branch block, right bundle branch block, paced beats, premature ventricular contradiction, atrial premature beats, and normal rhythm). Early and accurate detection of arrhythmia types is important in detecting heart diseases and choosing appropriate treatment for a patient. This paper proposes a combination of Particle Swarm Optimisation (PSO) and Feed Forward Neural Network (FFNN) for ECG beat classification. We have used MIT-BIH arrhythmia database for data collection and prepared three different datasets. Features, such as R peak sample number and QRS complex, are extracted using Pan-Tompkins algorithm. The extracted features are used as inputs to three different classifiers: Multi-Layer Perceptron Neural Network (MLPNN), Support Vector Machine (SVM), and PSO-FFNN. Results show high classification accuracy of over 97% with either of these three classifiers. The performance comparison of these classifiers is carried out using three measures: sensitivity, specificity, and accuracy. The results suggest that PSO-FFNN shows slightly better performance than MLPNN and SVM in terms of accuracy on all datasets.

ECG beat classification using machine learning techniques

ECG beat classification using machine learning techniques

ECG beat classification using empirical mode decomposition and mixture of features

Computer-aided analysis is useful in predicting arrhythmia conditions of the heart by analysing the recorded ECG signals. In this work, we proposed a method to detect, extract informative features to classify six types of heartbeat of ECG signals obtained from the MIT-BIH Arrhythmia database. The powerful discrete wavelet transform (DWT) is used to eliminate different sources of noises. Empirical mode decomposition (EMD) with adaptive thresholding has been used to detect precise R-peaks and QRS complex. The significant features consists of temporal, morphological and statistical were extracted from the processed ECG signals and combined to form a set of features. This feature set is classified with probabilistic neural network (PNN) and radial basis function neural network (RBF-NN) to recognise the arrhythmia beats. The process achieved better result with sensitivity of 99.96%, and positive predictivity of 99.81 with error rate of 0.23% in detecting the QRS complex. In class-oriented scheme, the arrhythmia conditions are classified with accuracy of 99.54%, 99.89% using PNN and RBF-NN classifier respectively. The obtained result confirms the superiority of the proposed scheme compared to other published results cited in literature.

Classification of Heart Rate Data Using BFO-KFCM Clustering and Improved Extreme Learning Machine Classifier

An Electrocardiogram or ECG is an electrical recording of the heart and is used in the investigation of heart disease. The heart rate varies not only in relation to the cardiac demand but is also affected by the presence of cardiac disease and diabetes. Furthermore, it has been shown that Heart Rate Variability (HRV) may be used as an early indicator of cardiac disease susceptibility and the presence of diabetes. Therefore, the heart rate variability may be used for early clinical screening of these diseases. The generalization performance of the SVM classifier is not sufficient for the correct classification of heart rate data. To overcome this problem the Improved Extreme Learning Machine (IELM) classifier is used which works by searching for the best value of the parameters, and upstream by looking for the best subset of features using Bacterial Foraging Optimization (BFO) that feed the classifier. In this work, nine linear and nonlinear features are extracted from the HRV signals. After the preprocessing, feature extraction is done along with feature selection using BFO for data reduction. Then, proposed a scheme to integrate Kernel Fuzzy C-Means (KFCM) clustering and Classifier to improve the accuracy result for ECG beat classification. The results show that the proposed method is effective for classification of heart rate data, with an acceptable high accuracy.

A knowledge-based real time embedded platform for arrhythmia beat classification

This paper aims for accurate classification of ECG beats in real-time. The design, implementation and results of FPGA oriented SOC based embedded platform in laboratory experimental setup is presented. The platform is designed using high-level systematic approach having the capability of real-time classification of ECG beats at the place of patients with high accuracy which will be helpful to enhance the healthcare for cardiovascular diseases. The algorithm involves the integration of the R-peak detection algorithm and Rulebased approach to classify four generic heartbeat classes namely Normal, PVC, Ventricular Fibrillation/Ventricular Flutter, 2° heart block beat. The aforesaid algorithms are performed in software on an integrated TSK3000A processor core (IP cores used) and implemented in hardware targeting FPGA (Xilinx Spartan 3AN). The developed platform is validated by generating real-time ECG beats using MIT-BIH arrhythmia database. The performance of the proposed implementation is evaluated in terms of sensitivity, specificity, positive predictivity and accuracy which is 97.72%, 99.09%, 96.46% and 97.96% respectively. The proposed hardware/software implementation has yielded improved results in comparison to the existing methodologies implemented on the FPGA platforms.

An Effective Classification of Heart Rate Data using PSO-FCM Clustering and Enhanced Support Vector Machine

Background/Objectives: Heart Rate Variability is an essential feature which decides the condition of human heart. ECG is used as diagnostic tool to access the electrical function of the heart. Methods/Statistical Analysis: The nine linear and nonlinear features are derived from the HRV signals. The feature extraction is carried out with the help of Particle Swarm Optimization (PSO) for data reduction. In proposed scheme Fuzzy C-Means (FCM) clustering and classifier integrated to enhance the accuracy result for ECG beat classification. Findings: The Enhanced SVM classifier classifies the heart rate data. Enhanced SVM classifier groups the linear and non-linear parameters as inputs, which are derived from the HRV signal. The denoise signals are classified and identifies the pattern for better classification of ECG signal. Application/Improvements: The proposed scheme is experimented with the assistance of the most commonly used MIT-BIH arrhythmia database and adequate results were obtained with an accuracy level of 98.38% than the other well-known approaches.

ECG beat classification using particle swarm optimization and support vector machine

In this paper, we propose a novel ECG arrhythmia classification method using power spectral-based features and support vector machine (SVM) classifier. The method extracts electrocardiogram’s spectral and three timing interval features. Non-parametric power spectral density (PSD) estimation methods are used to extract spectral features. The proposed approach optimizes the relevant parameters of SVM classifier through an intelligent algorithm using particle swarm optimization (PSO). These parameters are: Gaussian radial basis function (GRBF) kernel parameter σ and C penalty parameter of SVM classifier. ECG records from the MIT-BIH arrhythmia database are selected as test data. It is observed that the proposed power spectral-based hybrid particle swarm optimization-support vector machine (SVMPSO) classification method offers significantly improved performance over the SVM which has constant and manually extracted parameter.

ECG beat classification using a cost sensitive classifier

In this paper, we introduce a new system for ECG beat classification using Support Vector Machines (SVMs) classifier with rejection. After ECG preprocessing, the QRS complexes are detected and segmented. A set of features including frequency information, RR intervals, QRS morphology and AC power of QRS detail coefficients is exploited to characterize each beat.An SVM follows to classify the feature vectors. Our decision rule uses dynamic reject thresholds following the cost of misclassifying a sample and the cost of rejecting a sample. Significant performance enhancement is observed when the proposed approach is tested with the MIT-BIH arrhythmia database. The achieved results are represented by the average accuracy of 97.2% with no rejection and 98.8% for the minimal classification cost.

HEARTBEAT CLASSIFICATION USING SUPPORT VECTOR MACHINES (SVMs) WITH AN EMBEDDED REJECT OPTION

In this paper, we introduce a new system for ECG beat classification using support vector machines classifier with a double hinge loss. The proposed classifier rejects samples that cannot be classified with enough confidence. Specifically in medical diagnoses, the consequence of a wrong classification can be so harmful that it is convenient to reject such sample. After ECG preprocessing, feature selection and extraction, our decision rule uses dynamic reject thresholds according to the cost of rejecting or misclassifying a sample. Significant performance enhancement is observed when the proposed approach is tested with the MIT-BIH arrythmia database. The achieved results are represented by the error reject tradeoff. We obtained 98.2% of sensitivity with no rejection and more than 99% of sensitivity for the optimal classification cost being competitive to other published studies.

Classification of ECG Signals Using Extreme Learning Machine

An Electrocardiogram or ECG is an electrical recording of the heart and is used in the investigation of heart disease. This ECG can be classified as normal and abnormal signals. The classification of the ECG signals is presently performed with the support vector machine. The generalization performance of the SVM classifier is not sufficient for the correct classification of ECG signals. To overcome this problem the ELM classifier is used which works by searching for the best value of the parameters that tune its discriminant function, and upstream by looking for the best subset of features that feed the classifier. The experiments were conducted on the ECG data from the Physionet arrhythmia database to classify five kinds of abnormal waveforms and normal beats. In this paper a thorough experimental study was done to show the superiority of the generalization capability of the Extreme Learning Machine (ELM) is presented and compared with support vector machine (SVM) approach in the automatic classification of ECG beats. In particular, the sensitivity of the ELM classifier is tested and that is compared with SVM combined with two classifiers, they are the k-nearest neighbor classifier (kNN) and the radial basis function neural network classifier (RBF), with respect to the curse of dimensionality and the number of available training beats. The obtained results clearly confirm the superiority of the ELM approach as compared to traditional classifiers.

Feature extraction for ECG heartbeats using higher order statistics of WPD coefficients

This paper describes feature extraction methods using higher order statistics (HOS) of wavelet packet decomposition (WPD) coefficients for the purpose of automatic heartbeat recognition. The method consists of three stages. First, the wavelet package coefficients (WPC) are calculated for each different type of ECG beat. Then, higher order statistics of WPC are derived. Finally, the obtained feature set is used as input to a classifier, which is based on k-NN algorithm. The MIT-BIH arrhythmia database is used to obtain the ECG records used in this study. All heartbeats in the arrhythmia database are grouped into five main heartbeat classes. The classification accuracy of the proposed system is measured by average sensitivity of 90%, average selectivity of 92% and average specificity of 98%. The results show that HOS of WPC as features are highly discriminative for the classification of different arrhythmic ECG beats.

Selection of effective features for ECG beat recognition based on nonlinear correlations

The objective of this study is to develop feature selectors based on nonlinear correlations in order to select the most effective and least redundant features from an ECG beat classification system based on higher order statistics of subband components and a feed-forward back-propagation neural network, denoted as HOS-DWT-FFBNN. Three correlation-based filters (NCBFs) are proposed. Two of them, NCBF1 and NCBF2, apply feature-feature correlation to remove redundant features prior to the feature selection process based on feature-class correlation. The other, SUFCO, skips the redundancy reduction process and selects features based only on feature-class correlation. The performance of these filters is compared to another commonly used nonlinear feature selection method, Relief-F. The discriminality and redundancy of the retained features are evaluated quantitatively. The performance of the most effective NCBF is compared with that of the linear correlation-based filter (LCBF) and other representative heartbeat classifiers in the literature. The results demonstrate that the two NCBFs based on both feature-feature and feature-class correlation methods, i.e. NCBF1 and NCBF2, outperform the other two methods, i.e. SUFCO and Relief-F. An accuracy of as high as 96.34% can be attained with as few as eight features. When tested with statistical methods, the retained features selected by the NCBF1/NCBF2 approach are demonstrated to be more discriminative and less redundant when compared with those features selected by other methods. When compared with LCBF and other heartbeat classifiers in the literature, the proposed NCBF1/NCBF2 approach in conjunction with the HOS-DWT-FFBNN structure outperform them with improved performance that allows discrimination of more beat types and fewer feature dimensions. This study demonstrates the effectiveness and superiority of the proposed approach for ECG beat recognition.

Classification of electrocardiogram signals with support vector machines and extreme learning machine

An Electrocardiogram or ECG is an electrical recording of the heart and is used in the investigation of heart disease. This ECG can be classified as normal and abnormal signals. The classification of the ECG signals is presently performed with the support vector machine. The generalization performance of the SVM classifier is not sufficient for the correct classification of ECG signals. To overcome this problem, the ELM classifier is used which works by searching for the best value of the parameters that tune its discriminant function and upstream by looking for the best subset of features that feed the classifier. The experiments were conducted on the ECG data from the Physionet arrhythmia database to classify five kinds of abnormal waveforms and normal beats. In this paper, a thorough experimental study was done to show the superiority of the generalization capability of the Extreme Learning Machine (ELM) that is presented and compared with support vector machine (SVM) approach in the automatic classification of ECG beats. In particular, the sensitivity of the ELM classifier is tested and that is compared with SVM combined with two classifiers, and they are the k-nearest Neighbor Classifier and the radial basis function neural network classifier, with respect to the curse of dimensionality and the number of available training beats. The obtained results clearly confirm the superiority of the ELM approach as compared with traditional classifiers.

ECG beat classification using features extracted from Teager energy functions in time and frequency domains

It is hypothesised that a key characteristic of ECG signal is its non-linear dynamic behaviour and that the non-linear component changes more significantly between normal and arrhythmia conditions than the linear component. This study makes an attempt to analyse ECG beats from an energy point of view by accounting for the features derived from non-linear component in time and frequency domains using Teager energy operator (TEO). The key feature of TEO is that it models the energy of the source that generated the signal rather than the energy of the signal itself. Hence any deviations in the regular rhythmic activity of the heart get reflected in the Teager energy function. To show the validity of appropriate choice of features, t-tests and scatter plot are used. The t-tests show significant statistical differences and scatter plot of mean of Teager energy in time domain against mean of Teager energy in frequency domain for the ECG beats evaluated on selected Manipal Institute of Technology–Beth Israel Hospital (MIT–BIH) database, which reveals an excellent separation of the features into five different classes: normal, left bundle branch block, right bundle branch block, premature ventricular contraction and paced beats. The neural network results achieved through only two non-linear features exhibit an average accuracy that exceeds 95%, average sensitivity of about 80% and average specificity of almost 100%.