ECG beat classification using particle swarm optimization and radial basis function neural network

In this paper, we present a new system for the classification of electrocardiogram (ECG) beats by using a fast least square support vector machine (LSSVM). Five feature extraction methods are comparatively examined in the 15-dimensional feature space. The dimension of the each feature set is reduced by using dynamic programming based on divergence analysis. After the preprocessing of ECG data, six types of ECG beats obtained from the MIT-BIH database are classified with an accuracy of 95.2% by the proposed fast LSSVM algorithm together with discrete cosine transform. Experimental results show that not only the fast LSSVM is faster than the standard LSSVM algorithm, but also it gives better classification performance than the standard backpropagation multilayer perceptron network.

Convolutional Neural Networks (CNNs) have become a dominant solution for Electrocardiogram (ECG) beat classification, owing to their superior feature extraction capabilities. However, traditional CNN-based accelerators often encounter limitations such as large parameter counts, limited configurability, and inefficient hardware utilization. In this work, we propose a lightweight one-dimensional CNN (1D-CNN) inspired by the InceptionNet architecture, specifically designed for efficient and accurate ECG beat classification. The model integrates customized Inception blocks with parallel convolutional layers of varying kernel sizes to capture multi-scale temporal features. To reduce model complexity and enhance efficiency, <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$1 \times 1$</tex> convolutions are used for dimensionality reduction, resulting in a compact network with only 7,740 parameters. Additionally, we present a hardware accelerator that exploits spatial data reuse across multiple processing units and employs dual-port RAM for concurrent data access, improving throughput and memory efficiency. When implemented on hardware with parallel and pipelined execution at 100 MHz, the system achieves a classification accuracy of 99.32%, sensitivity of 98.50%, specificity of 99.58%, and a positive predictive value (PPV) of 98.30% across five ECG classes with the MIT-BIH database, demonstrating its suitability for real-time deployment in resource-constrained environments.

Early detection and prediction of fatal heart diseases can be useful for medical diagnosis and rehabilitation. In this study, a hybridized Particle Swarm Optimization (PSO) and Radial Basis Function Neural network (RBFN) model has been proposed to improve cardiac arrhythmia prediction accuracy. The performance of RBFN is very sensitive to parameter such as spread. In RBFN training process, the spread is optimized using PSO. In the proposed method a set of linear and non-linear features are extracted from the RR interval time series datasets, which are derived from the MIT-BIH arrhythmia database. Experiments are carried out on the heart rate (RR Interval) time series to predict the eight types of cardiac signals that contain normal and abnormal rhythms. The obtained results suggest that PSO-RBFN model may be an efficient tool to achieve enhancements in terms of prediction accuracy for diagnosis of cardiac disorders. The hybrid PSO-RBFN model yielded an overall prediction accuracy of 96.3%.

An automated patient-specific ECG beat classification using LSTM-based recurrent neural networks

Automatic ECG beat classification plays an important role in detecting cardiac disease. In this paper, we propose an automatic recognition model for ECG signals based on discrete wavelet transform (DWT), principal component analysis (PCA), kernel principal component analysis (KPCA), and adaptive kernel principal component analysis (AKPCA). We extracted different ECG features using DWT, PCA, KPCA, and AKPCA, respectively. These features were combined and used as support vector machine (SVM) input to classify the ECG. ECG records taken from the MIT-BIH arrhythmia database are selected to test the proposed method. The following five heartbeat types were classified using this method: normal beats (N), premature ventricular beats (V), right bundle branch block beats (R), left bundle branch block beats (L), and premature atrial beats (A). The sensitivity, accuracy, precision, and specificity reached 99.95%, 99.86%, 99.53%, and 99.70%, respectively. These results indicate the proposed method is reliable and efficient for ECG beat classification.

Detection and treatment of arrhythmias has become one of the main goals in cardiac care diagnosis provided by general practitioners. Electrocardiogram (ECG) analysis is one of the most commonly used tools to test and diagnose heart problems. Classification of ECG heartbeats enables the identification of specific arrhythmia or other heart conditions. This paper presents and contrasts the results from two effective ECG arrhythmia classification schemes. The first scheme consists of a principal component analysis (PCA) step for feature reduction at the input vector to the classifier, combined with soft independent modelling of class analogy (SIMCA). The second method uses a multi-class support vector machine (MSVM) classifier to differentiate between four different types of arrhythmia from ECG beats. The four types of beats include Normal (N), Premature Ventricular Contraction (PVC), and Atrial premature contraction (APC) and Right Bundle Branch Block Beat (RBBB). The time domain features were obtained from the St Petersburg INCART 12-lead Arrhythmia Database (incartdb). Between 10 and 30 Principal Components (PCs) were selected for reconstructing individual ECG beats and create the input vector to the classifier. The average classification accuracy of the proposed scheme is 76.83% and 98.33% using MSVM and SIMCA classifier respectively. The SIMCA classification algorithm provided better performance than the MSVM classifiers.

The aim of this paper is twofold. First, we present a thorough experimental study to show the superiority of the generalization capability of the support vector machine (SVM) approach in the automatic classification of electrocardiogram (ECG) beats. Second, we propose a novel classification system based on particle swarm optimization (PSO) to improve the generalization performance of the SVM classifier. For this purpose, we have optimized the SVM classifier design 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 basis of ECG data from the Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) arrhythmia database to classify five kinds of abnormal waveforms and normal beats. In particular, they were organized so as to test the sensitivity of the SVM classifier and that of two reference classifiers used for comparison, i.e., the k-nearest neighbor (kNN) classifier and the radial basis function (RBF) 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 SVM approach as compared to traditional classifiers, and suggest that further substantial improvements in terms of classification accuracy can be achieved by the proposed PSO-SVM classification system. On an average, over three experiments making use of a different total number of training beats (250, 500, and 750, respectively), the PSO-SVM yielded an overall accuracy of 89.72% on 40438 test beats selected from 20 patient records against 85.98%, 83.70%, and 82.34% for the SVM, the kNN, and the RBF classifiers, respectively.

An offline optimization approach based on energy storage management response in a microgrid was not fast and not reliable enough to control and adjust the system efficiently after the loss of the utility grid. Thus, it causes system inefficiency and collapse in the presence of violent changes of loads or outage of distributed generations. To solve such a problem, more real-time management is needed. Any changes in loads/generations should be compensated successfully by a battery energy storage system (BESS) in a short period of time. This paper presents a new method for the intelligent online management of both active and reactive power of a BESS based on a radial basis function neural network (RBFNN) incorporating particle swarm optimization (PSO) to prevent the stand-alone microgrid from instability and system collapse. BESS is centrally controlled by a controller developed by the proposed RBFNN. PSO is used to determine the optimized active and reactive power at every load/generation changing situation to monitor the effect of system frequency, voltage, and reference power regulation. These optimized power data are then employed as target data for the RBFNN generalization and training process. To enable the online updating of the operating parameters, the proposed RBFNN is implemented in the management process. With an appropriate RBFNN training, the optimum active and reactive power can directly be obtained without the necessity of performing the PSO optimization process at any change of load/generation. The results show that the predictive results of the proposed RBFNN model only slightly differed from the target results based on PSO and have a minimum statistical error compared to the predictive results based on the multilayer perceptron neural network (MLPNN) model. The proposed RBFNN is suitable for the online estimation of the active and reactive power of BESS and can be used for real-time energy storage management as an online controller.

The identification of nonlinear systems with artificial neural networks models has been successfully used in many applications. Most processes in industry are characterized by nonlinear and time-varying behavior. In this context, the identification of mathematical models for nonlinear systems is vital in many fields of engineering. The Radial Basis Function Neural Network (RBF-NN) is a powerful approach for nonlinear identification and can be improved using Particle Swarm Optimization (PSO) approaches. This paper presents a multivariable nonlinear system identification using RBF-NN combined with standard PSO and Constriction Factor PSO (CFPSO) approaches in order to determine the RBF-NN parameters. RBF-NN is considered to be a good choice for black-box modeling problems due to its rapid learning capacity and, therefore, has been applied successfully to nonlinear time series modeling and nonlinear identification. On the other hand, PSO was inspired by the choreography of bird flocks and fish schools and can be seen as a distributed behavior algorithm that performs multidimensional search. Furthermore, promising simulation results from performance analysis of the proposed RBF-NN with PSO training approaches are presented and discussed in this paper showing promising results.

The detection of ventricular ectopic beats (VEB) in Electrocardiogram (ECG) plays a vital role in the diagnosis of cardiovascular diseases like ventricular tachycardia and ventricular fibrillation, which causes sudden death. This paper discusses the beat interval based features for the automated detection of ventricular ectopic beats. Five-time domain features, pre RR interval, post RR interval, QRS width, QR slope and RS slope are considered and a KNN classifier is employed to classify normal and ventricular ectopic beats. The proposed study make use of ECG signals derived from MIT-BIH arrhythmia database. The quantitative results are compared with qualitative assessment recorded already in the database. The overall classification accuracy achieved is 98.67% and the accuracy for normal & ventricular ectopic beats is 98.81% & 95.12% respectively with the Sensitivity of 95.12%, Specificity of 99.11% and Positive Predictivity of 92.85%.

Classification of electrocardiogram (ECG) signals is obligatory for the automatic diagnosis of cardiovascular disease. With the recent advancement of low‐cost wearable ECG device, it becomes more feasible to utilize ECG for cardiac arrhythmia classification in daily life. In this paper, we propose a lightweight approach to classify five types of cardiac arrhythmia, namely, normal beat (N), atrial premature contraction (A), premature ventricular contraction (V), left bundle branch block beat (L), and right bundle branch block beat (R). The combined method of frequency analysis and Shannon entropy is applied to extract appropriate statistical features. Information gain criterion is employed to select features that the results show that 10 highly effective features can obtain performance measures comparable to those obtained by using the complete features. The selected features are then fed to the input of Random Forest, K‐Nearest Neighbour, and J48 for classification. To evaluate classification performance, tenfold cross validation is used to verify the effectiveness of our method. Experimental results show that Random Forest classifier demonstrates significant performance with the highest sensitivity of 98.1%, the specificity of 99.5%, the precision of 98.1%, and the accuracy of 98.08%, outperforming other representative approaches for automated cardiac arrhythmia classification.

The increasing use of computer numerical control (CNC) machines requires better prediction of the reliability of their servo control systems. A novel reliability prediction model based on radial basis function (RBF) neural network optimized by improved particle swarm optimization (IPSO) was proposed. It can overcome the disadvantages of conventional methods, which are time consuming and resource intensive. The major influences on the reliability of servo system include torque, temperature, current, and complexity. An improved algorithm for predicting the mean time between failure (MTBF) of servo systems based on a particle swarm optimization (PSO) and an RBF neural network algorithm is proposed. Two common problem of the PSO: local minimization and slow convergence were solved by the IPSO. “Zero failure” data preprocessing, data normalization, and small-sample data enhancement were performed on the original data. A homogenized sampling method is proposed to extract training and testing samples. Experimental results show that the improved PSO-based RBF neural network is superior to back propagation (BP) and RBF networks in terms of accuracy in servo system reliability prediction.

Abstract: Mixture of experts (ME) is a modular neural network architecture for supervised learning. This paper illustrates the use of the ME network structure to guide model selection for classification of electrocardiogram (ECG) beats. The expectation maximization algorithm is used for training the ME so that the learning process is decoupled in a manner that fits well with the modular structure. The ECG signals were decomposed into time–frequency representations using discrete wavelet transforms and statistical features were calculated to depict their distribution. The ME network structure was implemented for ECG beats classification using the statistical features as inputs. To improve classification accuracy, the outputs of expert networks were combined by a gating network simultaneously trained in order to stochastically select the expert that is performing the best at solving the problem. Five types of ECG beats (normal beat, congestive heart failure beat, ventricular tachyarrhythmia beat, atrial fibrillation beat, partial epilepsy beat) obtained from the Physiobank database were classified with an accuracy of 96.89% by the ME network structure. The ME network structure achieved accuracy rates which were higher than those of the stand‐alone neural network models.

Scene classification is one of the most significant and challenging tasks in computer vision. This paper presents a new method for scene classification using bag of visual words and a particle swarm optimization (PSO)-based artificial neural network classifier. Contributions of this paper are introducing a novel feature integration method using scale invariant feature transform (SIFT) and local binary pattern (LBP) and a new framework for training radial basis function neural network, combining optimum steepest decent method with a specially designed PSO-based optimizer for center adjustment of radial basis function neural network. Our study shows that using LBP increases the performance of classification task compared to using SIFT only. In addition, our experiments on Proben1 dataset demonstrate improvements in classification performance (averagely about 6.04%) and convergence speed of the proposed radial basis function neural network. The proposed radial basis function neural network is then employed in scene classification task. Results are reported for classification of the Oliva and Torralba, Fei–Fei and Perona and Lazebnik et al. datasets. We compare the performance of the proposed classifier with a multi-way SVM classifier. Experimental results show the superiority of the proposed classifier over the state-of-the-art on the three datasets.

Electrocardiogram (ECG) beat behaves as a non-linear and non-stationary signal. Since most of the existing data processing tools are poor alternatives for processing such signals, Hilbert–Huang transform (HHT) proves to be an efficient method as it deals with a time-varying frequency spectrum. In this study, a new and efficient methodology is proposed using HHT for feature selection which includes a set of essential features such as weighted mean frequency, Kolmogorov complexity and other statistical features (median, standard deviation, kurtosis, skewness and central moment) computed from the intrinsic mode functions extracted using the empirical mode decomposition (EMD) algorithm. Further, one-against-one multi-class support vector machine is employed for the classification of six generic ECG beats, namely: normal, left bundle branch block, right bundle branch block, premature ventricular contraction, paced beat and atrial premature beat. The classification process in this study yields better results than existing methodologies in terms of classification accuracy equal to 99.51% along with sensitivity, specificity and positive predictivity of 98.64, 99.77 and 98.17%, respectively.