MIT-BIH Arrhythmia Database Research Articles

A homologous and heterogeneous multi-view inter-patient adaptive network for arrhythmia detection

Background and ObjectiveElectrocardiogram (ECG) is a widely used diagnostic tool for arrhythmia assessment in clinical practice. However, current arrhythmia detection algorithms rely heavily on signal-based data, while cardiologists often use image-based data. This discrepancy, combined with individual differences in physiological signals, poses challenges for accurate arrhythmia detection. To address these challenges and improve arrhythmia detection performance, we propose a homologous and heterogeneous multi-view inter-patient adaptive network. MethodsWe designed a multi-view representation learning module to capture dynamic and morphological characteristics from ECG signals and electrocardiographic images. Expert knowledge was also elicited to gain internally-invariant characteristics of each category. Finally, we designed a new loss function that aligns the embedding of the source and target domains in the feature space to minimize the negative effects of individual differences. ResultsExperiments on the MIT-BIH arrhythmia database demonstrate that our proposed method outperforms state-of-the-art baselines in terms of accuracy, positive predictive value, sensitivity and F1-score. These results indicate the effectiveness of our method in accurately detecting arrhythmias. ConclusionsOur homologous and heterogeneous multi-view inter-patient adaptive network successfully addresses the challenges of utilizing both ECG signal and electrocardiographic image data for arrhythmia detection and overcoming individual differences in physiological signals. Our proposed method has the potential to improve early diagnosis and treatment outcomes of arrhythmias in clinical practice.

Interpretable Rule Mining for Real-Time ECG Anomaly Detection in IoT Edge Sensors

Electrocardiogram (ECG) analysis is widely used in the diagnosis of cardiovascular diseases. This paper proposes an explainable rule-mining strategy for prioritizing abnormal class detection in ECG data. The proposed method utilizes a biased-trained Artificial Neural Network (ANN) with input features derived from an ECG beat sequence and formulates a set of rules at each node of an on-demand tree-like search algorithm. The rule base at each node is derived from a linear combination of the most impactful features identified using gradient analysis in an ANN. The final derived model is an explainable rule-based system that detects abnormal heartbeats based on statistical and morphological features from ECG. The model achieves the target sensitivity, and accuracy with a low run-time complexity through a comprehensive offline rule mining process and is trained using the MIT-BIH Arrhythmia Database. The system achieves an accuracy of 93% with only nine nodes and a test sensitivity of 90% and 80% respectively for VEB and SVEB beat types, when tested on previously unseen ECG data from the INCART database. The model performance and complexity can be easily adjusted based on the real-time resource constraints of a wearable sensor. The model was deployed on an ARM Cortex M4-based embedded device and is shown to achieve a >50% reduction in sensor power consumption when only abnormal beats are wirelessly transmitted. i.e RF transmission is gated using the model output and transmission is disabled when the subject’s ECG is normal. The proposed technique is highly suited for healthcare applications because of its explainability, lower complexity, and real-time flexibility when deployed in the Internet of Things (IoT) enabled wearable edge sensors.

Electrocardiogram signal compression using adaptive tunable-Q wavelet transform and modified dead-zone quantizer

The electrocardiogram (ECG) signals are commonly used to identify heart complications. These recordings generate large data that needed to be stored or transferred in telemedicine applications, which require more storage space and bandwidth. Therefore, a strong motivation is present to develop efficient compression algorithms for ECG signals. In the above context, this work proposes a novel compression algorithm using adaptive tunable-Q wavelet transform (TQWT) and modified dead-zone quantizer (DZQ). The parameters of TQWT and threshold values of DZQ are selected using the proposed Sparse-grey wolf optimization (Sparse-GWO) algorithm. The Sparse-GWO is proposed in this work to reduce the computation time of the original GWO. Moreover, it is also compared with some popular algorithms such as original GWO, particle swarm optimization (PSO), Hybrid PSOGWO, and Sparse-PSO. The DZQ has been utilized to perform thresholding and quantization. Then, run-length encoding (RLE) has been used to encode the quantized coefficients. The proposed work has been performed on the MIT-BIH arrhythmia database. Quality assessment performed on reconstructed signals ensure the minimal impact of compression on the morphology of reconstructed ECG signals. The compression performance of proposed algorithm is measured in terms of the following evaluation matrices: percent root-mean-square difference (PRD1), compression ratio (CR), signal-to-noise ratio (SNR), and quality score (QS1). The obtained average values are 3.21%, 20.56, 30.62 dB, and 7.79, respectively.

A novel transformer-based ECG dimensionality reduction stacked auto-encoders for arrhythmia beat detection.

Electrocardiogram (ECG) is a powerful tool for studying cardiac activity and diagnosing various cardiovascular diseases, including arrhythmia. While machine learning and deep learning algorithms have been applied to ECG interpretation, there is still room for improvement. For instance, the commonly used Recurrent Neural Networks (RNNs), reply on its previous state to update and is therefore ineffective for parallel computing. RNN also struggles to efficiently address the issue of long-distancereliance. To reduce computational complexity by dimensionality reduction of ECG signals we constructed a Stacked Auto-encoders model using Transformer for ECG-based arrhythmia detection. And overcome the challenges of long-term dependencies and limited parallelizability in traditional RNNs when applied to ECG signalprocessing. In this paper, a Transformer-Based ECG Dimensionality Reduction Stacked Auto-encoders model is proposed for ECG-based arrhythmia detection. The transformer is used to encode ECG signals into a feature matrix, which is then dimensionally reduced using unsupervised greedy training through the four linear layers. This resulted in a low-dimensional representation of ECG features, which are subsequently classified using support vector machines (SVM) to minimizeoverfitting. The proposed method is benchmarked on the MIT-BIH Arrhythmia database. In the 10-fold cross validation of beat-based arrhythmia detection, the average accuracy, sensitivity, specificity and F1 score of the proposed method are 99.83%, 98.84%, 99.84% and 99.13%, respectively, for the record-based arrhythmia detection which refers to the approach where the training and testing sets use ECG data from independent recorded patients are 88.10%, 49.79%, 91.56% and 39.95%, respectively. Compared to other existing ECG-based arrhythmia detection methods, our proposed approach exhibits improved detection accuracy and stronger generalization for arrhythmia beats. Additionally, the use of the record-based data division method makes our approach more suitable for clinicalpractice.

Monitoring and Recognition of Heart Health using Heartbeat Classification with Deep Learning and IoT

The advancement and innovations in the field of science and technology paved way for various advanced treatments in the field of medicine. They are implemented using sensors, and computer-aided designs with artificial intelligence techniques. This helps in the detection of serious health constraints at an earlier stage with appropriate treatments using decision-making techniques. One of the important health concerns that are increasing rapidly is cardiovascular disorders. This includes Arrhythmia and Myocardial Infarction. Earlier prediction and classification can protect them from serious constraints. They are diagnosed using the Electrocardiogram (ECG). To obtain accurate results, artificial intelligence techniques are implemented to extract the optimum output. The proposed system includes the detection and classification using deep learning techniques with the Internet of Things (IoT). The existing heartbeat detection system is overcome using a deep convolutional neural network. This helps in the implementation of automatic heartbeat detection and identification of abnormalities. The ECG signals are pre-processed with segmentation and feature extraction techniques. The classification and identification of constraints in the functioning of the heart are identified using optimization algorithms. The proposed system is trained, tested, and evaluated using the MIT-BIH arrhythmia database. The accuracy and efficiency of the proposed system are 99.98% using the MIT-BIH dataset.

ECG Arrhythmia Classification Using Recurrence Plot and ResNet-18

Cardiovascular diseases are the leading cause of death worldwide, claiming approximately
 17.9 million lives each year. In this study, a novel CAD system to detect and classify electrocardiogram (ECG) signals is presented. Designed system employs the recurrence plot (RP) approach that transforms a ECG signal into a 2D representative colour image, finally performing their classifications via employment of Deep Learning architecture (ResNet-18). Novel system includes two steps, where the first step is the preprocessing one, which performs segmentation of the data into two-second intervals, finally forming images via the RP approach; following, in the second step, the RP images are classified by the ResNet- 18 network. The proposed method is evaluated on the MIT-BIH arrhythmia database where 5 principal types of arrhythmias that have medical relevance should be classified. Novel system can classify the before-mentioned quantity of diseases according to the AAMI Standard and appears to demonstrate good performance in terms of criteria: overall accuracy of 97.62%, precision of 95.42%, recall of 95.42%, F1-Score of 95.06%, and AUC of 95.7% that are competitive with better state-of-the-art systems. Additionally. the method demonstrated the ability in mitigating the problem of imbalanced samples.

Heart Diseases Classification Using Machine Learning Techniques

Abstract: Heart is the most vital organ in the human body, generating a systematic time-varying signal due to its electrical activity is called as an electrocardiogram (ECG). An electrocardiogram records the electrical signals in the heart. It's a common and painless test used to quickly detect heart problems and monitor the heart's health. It is a well-established diagnostic tool for cardiac diseases. ECG signal is monitored by placing sensors as positions on chest and limb. Each heart beat is caused by a section of the heart generating an electrical signal. Nowadays, heart diseases classification is one of the vital problems in health care sector. Therefore, this work aims to classify different heart diseases using machine learning techniques (such as linear discriminant analysis, support vector machine (SVM), multilayer perceptron, random forest, k-nearest neighbour). In order to classify the signal, it consists of major two steps: first step is to pre-process or extract the features and second stage is to apply machine learning algorithms. The performance of these methods can be assessed by popular MIT-BIH Arrhythmia database and quantitative metrics such as accuracy, sensitivity, precision.

An image classification method for arrhythmias based on Gramian angular summation field and improved Inception-ResNet-v2

Arrhythmia is a significant cardiovascular disease that poses a threat to human health, and its primary diagnosis relies on electrocardiogram (ECG). Implementing computer technology to achieve automatic classification of arrhythmia can effectively avoid human error, improve diagnostic efficiency, and reduce costs. However, most automatic arrhythmia classification algorithms focus on one-dimensional temporal signals, which lack robustness. Therefore, this study proposed an arrhythmia image classification method based on Gramian angular summation field (GASF) and an improved Inception-ResNet-v2 network. Firstly, the data was preprocessed using variational mode decomposition, and data augmentation was performed using a deep convolutional generative adversarial network. Then, GASF was used to transform one-dimensional ECG signals into two-dimensional images, and an improved Inception-ResNet-v2 network was utilized to implement the five arrhythmia classifications recommended by the AAMI (N, V, S, F, and Q). The experimental results on the MIT-BIH Arrhythmia Database showed that the proposed method achieved an overall classification accuracy of 99.52% and 95.48% under the intra-patient and inter-patient paradigms, respectively. The arrhythmia classification performance of the improved Inception-ResNet-v2 network in this study outperforms other methods, providing a new approach for deep learning-based automatic arrhythmia classification.

Efficient Key Generation Techniques for Wireless Body Area Network

In wireless body area network health care applications, energy-constraint wearable devices are used to monitor patient physiological parameters. The security of the private health information of a person plays a significant role because if it is captured and read by an unauthorized person, the confidentiality of the patient data is lost. Therefore, there is a requirement to secure the data by performing encryption to transfer it into an unreadable form. Since the resources used for encryption should be kept to a minimum as the devices are attached to the human body, a lightweight encryption algorithm has to be used. Therefore, the generation of a unique key used for encryption plays a significant role. In work, generating a unique key uses the ECG values taken from MIT-BIH Arrhythmia database. Four unique keys are generated, which can be used for encryption. The uniqueness and randomness of the keys generated are proved using the runs test and frequency test within the block. Also, the average hamming distance calculated between the ECG keys generated from two different ECG signals is 62.5% (approx 80 bits), which proves the distinctiveness of the keys generated. Implementation of the work is performed using Matlab.

SRT: Improved transformer-based model for classification of 2D heartbeat images

Electrocardiography (ECG) is a crucial tool for diagnosing cardiovascular diseases. In particular, combining clinical ECG with computer technology for automatic ECG analysis can improve ECG discrimination accuracy. In this study, to tackle the existing problems of 2D classification models (CNN and Transformer) of ECG heartbeat images, we proposed a 2D deep learning classification network SRT comprising a CNN and Transformer-encoder modules to improve the model structure. Furthermore, to identify the global and local differences between different types of ECG heartbeats, we propose a novel attention module (SC-RGA module) to assist the multi-headed attention mechanism in improving the feature extraction of ECG images and the Dilated Stem structure to expand the receptive field at the input of the network. We also applied a series of strategies to deal with data imbalances in public ECG datasets. Finally, we evaluated the performance of SRT using the MIT-BIH arrhythmia database, with a classification accuracy of 0.957, a sensitivity of 0.881, and an average F1 index of 0.826. Comparative experiments demonstrate that the proposed model outperforms several advanced methods.

A Novel Method for Automatic Detection of Arrhythmias Using the Unsupervised Convolutional Neural Network

Abstract In recent years, various models based on convolutional neural networks (CNN) have been proposed to solve the cardiac arrhythmia detection problem and achieved saturated accuracy. However, these models are often viewed as “blackbox” and lack of interpretability, which hinders the understanding of cardiologists, and ultimately hinders the clinical use of intelligent terminals. At the same time, most of these approaches are supervised learning and require label data. It is a time-consuming and expensive process to obtain label data. Furthermore, in human visual cortex, the importance of lateral connection is same as feed-forward connection. Until now, CNN based on lateral connection have not been studied thus far. Consequently, in this paper, we combines CNNs, lateral connection and autoencoder (AE) to propose the building blocks of lateral connection convolutional autoencoder neural networks (LCAN) for cardiac arrhythmia detection, which learn representations in an unsupervised manner. Concretely, the LCAN contains a convolution layer, a lateral connection layer, an AE layer, and a pooling layer. The LCAN detects salient wave features through the lateral connection layer. The AE layer and competitive learning is used to update the filters of the convolution network—an unsupervised process that ensures similar weight distribution for all adjacent filters in each convolution layer and realizes the neurons’ semantic arrangement in the LCAN. To evaluate the performances of the proposed model, we have implemented the experiments on the well-known MIT–BIH Arrhythmia Database. The proposed model yields total accuracies and kappa coefficients of 98% and 0.95, respectively. The experiment results show that the LCAN is not only effective, but also a useful tool for arrhythmia detection.

Premature Ventricular Contraction (PVC) Recognition Using DCT-CWT Based Discriminant and Optimized RBF Neural Network

A new method for premature ventricular contraction (PVC) detection and classification is presented. The proposed algorithm is constituted of two principal phases: the features extraction and reduction phase and the optimized classification phase. In the first phase, the discrete cosine transform (DCT) and the continuous wavelet transform (CWT) are applied on each ECG beat to generate an augmented features vector. For the optimized classification phase, the radial basis function (RBF) neural network classifier is trained and optimized by the bat algorithm. For the aim of performances evaluation of the proposed method, the MIT-BIH arrhythmia database has been used. Consequently, the BAT-RBF classifier yielded an overall sensitivity of 95,2% and an accuracy of 98,2%, confirming clearly the competitiveness of the proposed method compared to some recent and powerful algorithms.

Lightweight electrocardiogram signal compression

Cardiovascular diseases are the primary cause of death around the world. Cardiovascular ailments can be monitored continuously using wearable devices, which are resource-constrained and battery-operated. Efficient data compression is a promising method to reduce transmission energy cost and extend battery lifetime. In this paper, we first propose two novel pruning methods with pruning matrix’s entries taken from the set {−1, 0, 1}, which achieve similar reconstruction quality as compared to DCT pruning but with far less computational cost due to multiplierless operation. Reconstruction for these pruning methods is proposed using Gaussian elimination. Then we design two lightweight compression algorithms based on the pruning methods, i.e., sign compression algorithm and binary compression algorithm. The proposed compression algorithms and pruning methods are evaluated using performance metrics such as compression ratio, percentage root mean square difference, quality score, etc. Furthermore, The pruning methods are implemented in TelosB mote and execution time is evaluated. The experiments are conducted on the MIT-BIH arrhythmia database. The experimental results show that the proposed compression algorithms outperform the state-of-the-art methods.

Classification of arrhythmias using an LSTM- and GAN-based approach to ECG signal augmentation

Abstract Funding Acknowledgements Type of funding sources: Private grant(s) and/or Sponsorship. Main funding source(s): British Heart Foundation Introduction Automated classification of arrhythmias in ECGs is becoming increasingly important. Publicly available ECG datasets have been widely used by the research community to create novel artificial intelligence models that improve these detection rates. The development of these models requires access to large volume of labelled data. However, access to such databases is becoming increasingly limited. In addition, the datasets are often unbalanced because abnormal rhythms are far outweighed by normal samples. The unbalanced nature of the datasets can lead to less accurate models. Therefore, generating realistic synthetic signals can augment the real signals found in such databases and provide data that allows sophisticated model development. Purpose In this study, we propose a deep learning-based approach for synthetic ECG signal generation that uses long short-term memory (LSTM) autoencoder and generative adversarial networks (GAN) to generate signals that mimic the distribution of arrhythmia signals (Figure 1). Methods The LSTM autoencoder is composed of two parts: an encoder and a decoder (Figure 1b). The encoder takes original ECG signal as its input and uses LSTM layers to compress the signal into a set of features. The decoder is formed by reversing the encoding process, which uses the encoded features as its input and converts them back into the original signal. To generate synthetic signals, we inserted GANs between the LSTM encoder and the decoder. GANs are composed of a generator and a discriminator (Figure 1c). The generator produces synthetic ECG features based on noise, whereas the discriminator tries to distinguish between real features and results received from the generator. The pathological beats studies were: left bundle branch block (LBBB), right bundle branch block (RBBB), aberrated atrial premature (AA), and normal beats (N) from the MIT-BIH arrhythmia database, using lead II only. To evaluate the quality of our synthetic signals, we trained an LSTM classifier on a combination of our real and synthetic data and compared the testing results with a model trained on real data alone. Results The LSTM encoder, decoder and GAN were trained individually for each beat type, and examples of generated signals are illustrated in Figure 2. The average accuracy of the classification for the original dataset was 90%, with a recall of 98% for N, 36% for AA, 39% for LBBB and 97% for RBBB. Once synthetic signals were added to the training set, the average testing classification accuracy increased to 98%, with a recall of 99% for N, 83% for AA, 99% for LBBB and 99% for RBBB. For fair comparison, the testing set contained only real data and remained unchanged for both groups. Conclusion In this work, we proved the capability of GANs to generate realistic synthetic signals that helped to improve the detection rates of arrhythmias as measured by both increased overall accuracy and recall.

Time Series Classification for Portable Medical Devices

INTRODUCTION: With the continuous progress of the medical Internet of Things, intelligent medical wearable devices are also gradually mature. Among them, medical wearable devices for arrhythmia detection have broad application prospects. Arrhythmia is a common cardiovascular disease. Arrhythmia causes millions of deaths every year and is one of the most noteworthy diseases. Medical mobile information systems (MMIS) provide many ECG signals, which can be used to train deep models to detect arrhythmia automatically. OBJECTIVES: Using deep models to detect arrhythmia is a research hot spot. However, the current algorithms for arrhythmia detection lack of attention to the unsupervised depth model. And they usually build a large comprehensive model for all users for arrhythmia detection, which has low flexibility and cannot extract personalized features from users. Therefore, this paper proposes a personalized arrhythmia detection system based on attention mechanism called personAD. METHODS: The personAD contains four modules: (1) Preprocessing module; (2) Training module; (3) Arrhythmia detection module and (4) User registration module. The personAD trains a separate autoencoder for each user to detect personalized arrhythmia. Using autoencoder to detect arrhythmia can avoid the imbalance of training data. The autoencoder combines a convolutional network and two attention mechanisms. RESULTS: Based on the results on MIT-BIH Arrhythmia Database, we can find that our arrhythmia detection system achieve 98.03% and 99.32% respectively. CONCLUSION: The personAD can effectively detect arrhythmia in ECG signals. The personAD has higher flexibility, and can easily modify the autoencoders for detecting arrhythmia for users.

Detection of Arrhythmia Heartbeats from ECG Signal Using Wavelet Transform-Based CNN Model

In India, over 25,000 people have died from cardiovascular annually over the past 4 years , and over 28,000 in the previous 3 years. Most of the deaths nowadays are mainly due to cardiovascular diseases (CVD). Arrhythmia is the leading cause of cardiovascular mortality. Arrhythmia is a condition in which the heartbeat is abnormally fast or slow. The current detection method for diseases is analyzing by the electrocardiogram (ECG), a medical monitoring technique that records heart activity. Since actuations in ECG signals are so slight that they cannot be seen by the human eye, the identification of cardiac arrhythmias is one of the most difficult undertakings. Unfortunately, it takes a lot of medical time and money to find professionals to examine a large amount of ECG data . As a result, machine learning-based methods have become increasingly prevalent for recognizing ECG features. In this work, we classify five different heartbeats using the MIT-BIH arrhythmia database . Wavelet self-adaptive thresholding methods are used to first denoise the ECG signal. Then, an efficient 12-layer deep 1D Convolutional Neural Network (CNN) is introduced for better features extraction, and finally, SoftMax and machine learning classifiers are applied to classify the heartbeats. The proposed method achieved an average accuracy of 99.40%, precision of 98.78%, recall of 98.78%, and F1 score of 98.74%, which clearly show that it outperforms with the exiting model . Architecture of proposed work is simple but effective in remote cardiac diagnosis paradigm that can be implemented on e-health devices.

Pre-Processing Based ECG Signal Analysis Using Emerging Tools

The objective of the paper is to count the clear beats (R-peaks or QRS complexes) in the Electrocardiogram (ECG) signal after the pre-processing step. Among the three selected techniques, Independent Principal Component Analysis (IPCA), Fractional Fourier Transform (FrFT) and Fractional Wavelet Transform (FrWT) have Sensitivity (Se) of 99.92%, 99.95% and 99.98%, Accuracy (Acc) of 99.88%, 99.93% and 99.96%, Detection Error Rate (DER) of 0.110%, 0.066% and 0.036% along with the disturbance of 2.3%, 2% and 1.7% respectively. The lowest DER in FrWT indicates that it outperforms the IPCA and FrFT. The False Negative plus False Positive (FN + FP) by using the three techniques was 32, 25 and 13 while the output Signal-to-Noise Ratio (SNR) was found to be 24.42, 26.19 and 34.37 dB respectively. These results were figured out on Real Time Database (RT DB). The values of output SNR, Se and Acc were recorded to be 34.37 dB, 99.98% and 99.96% while using FrWT based pre-processing on the data from RT DB. The same technique when used on the data from MIT-BIH arrhythmia Database (MB DB) gave the values of 24.81 dB, 99.96% and 99.93% respectively. It has been observed that all the attributes of the components of ECG signals were preserved when filtered with FrFT. On the other hand, the FrWT segregates the motion artefacts and ECG signal in a better way than FrFT. This is due to the fact that in FrWT decomposition takes place on the signal rotated at a selected angle resulting in less computationally complex decompositions at various levels. It reveals that FrWT retains important biology-related information as the originally recorded ECG signal has.

An ECG denoising method based on adversarial denoising convolutional neural network

The Electrocardiogram (ECG) is widely used to diagnose heart disease. However, ECG recordings are often polluted by different noises in real situations. It is of great significance to propose an effective method for noise rejection of ECG signal. With the development of deep learning, neural networks have been widely utilized in signal processing. Most of the existing models of deep neural networks have millions of parameters, which places higher requirements on medical computing power. Based on this, this paper proposes a new denoising framework named the Adversarial Denoising Convolutional Neural Network (ADnCNN). We adopt the ADnCNN model to learn the residual signals in the noisy signal to obtain clean signal. A discriminator network is used for two-class classification of the denoised and clean signals, which are fed back to the ADnCNN model for parameter adjustment. The proposed method is validated by dividing three different types of datasets on the MIT-BIH arrhythmia database, the MIT-BIH noise stress test database, and the QT database for experiments. The denoising performance of the ADnCNN model is represented by the Signal-to-Noise Ratio (SNR), Root Mean Square Error (RMSE) and Percentage Root Mean Square Difference (PRD). The generality and adaptability of the model are also demonstrated. Simulation results show that the proposed method has advantages compared to recently proposed models.

Convolutional neural network optimized by differential evolution for electrocardiogram classification.

The Coronavirus disease 2019, or COVID-19, has shifted the medical paradigm from face-to-face to telehealth. Telehealth has become a vital resource to contain the virus spread and ensure the continued care of patients. In terms of preventing cardiovascular diseases, automating electrocardiogram (ECG) classification is a promising telehealth intervention. The healthcare service ensures that patient care is appropriate, comfortable, and accessible. Convolutional neural networks (CNNs) have demonstrated promising results in ECG categorization, which require high accuracy and short training time to ensure healthcare quality. This study proposes a one-dimensional-CNN (1D-CNN) arrhythmia classification based on the differential evolution (DE) algorithm to optimize the accuracy of ECG classification and training time. The performance of 1D-CNNs of different activation functions are optimized based on the standard DE algorithm. Finally, based on MIT-BIH and SCDH arrhythmia databases, the performances of optimized and unoptimized 1D-CNN are compared and analysed. Results show that the 1D-CNN optimized by the DE has higher accuracy in heartbeats classification. The optimized 1D-CNN improves from 97.6% to 99.5% on MIT-BIH and from 80.2% to 88.5% on SCDH. Therefore, the optimized 1D-CNN shows improvements of 1.9% and 8.3% in the two datasets, respectively. In addition, compared with the unoptimized 1D-CNN based on the same parameter settings, the optimized 1D-CNN has less training time. Under the conditions of ReLU function and 10 epochs, the training takes 9.22s on MIT-BIH and 10.35s on SCDH, reducing training time by 67.2% and 64.2%, respectively.

ECG classification using 1-D convolutional deep residual neural network.

An electrocardiograph (ECG) is widely used in diagnosis and prediction of cardiovascular diseases (CVDs). The traditional ECG classification methods have complex signal processing phases that leads to expensive designs. This paper provides a deep learning (DL) based system that employs the convolutional neural networks (CNNs) for classification of ECG signals present in PhysioNet MIT-BIH Arrhythmia database. The proposed system implements 1-D convolutional deep residual neural network (ResNet) model that performs feature extraction by directly using the input heartbeats. We have used synthetic minority oversampling technique (SMOTE) that process class-imbalance problem in the training dataset and effectively classifies the five heartbeat types in the test dataset. The classifier's performance is evaluated with ten-fold cross validation (CV) using accuracy, precision, sensitivity, F1-score, and kappa. We have obtained an average accuracy of 98.63%, precision of 92.86%, sensitivity of 92.41%, and specificity of 99.06%. The average F1-score and Kappa obtained were 92.63% and 95.5% respectively. The study shows that proposed ResNet performs well with deep layers compared to other 1-D CNNs.