scholarly journals Deep Convolutional Neural Network Based ECG Classification System Using Information Fusion and One-Hot Encoding Techniques

2018 ◽  
Vol 2018 ◽  
pp. 1-10 ◽  
Author(s):  
Jia Li ◽  
Yujuan Si ◽  
Tao Xu ◽  
Saibiao Jiang
Keyword(s):  
Cardiovascular Disease ◽  
Adaptive Learning ◽  
Portable Devices ◽  
Ecg Signals ◽  
Automatic Feature Extraction ◽  
Average Accuracy ◽  
Proposed Model ◽  
Home Health Monitoring ◽  
Predictive Rate ◽  
Electrocardiogram Ecg

Although convolutional neural networks (CNNs) can be used to classify electrocardiogram (ECG) beats in the diagnosis of cardiovascular disease, ECG signals are typically processed as one-dimensional signals while CNNs are better suited to multidimensional pattern or image recognition applications. In this study, the morphology and rhythm of heartbeats are fused into a two-dimensional information vector for subsequent processing by CNNs that include adaptive learning rate and biased dropout methods. The results demonstrate that the proposed CNN model is effective for detecting irregular heartbeats or arrhythmias via automatic feature extraction. When the proposed model was tested on the MIT-BIH arrhythmia database, the model achieved higher performance than other state-of-the-art methods for five and eight heartbeat categories (the average accuracy was 99.1% and 97%). In particular, the proposed system had better performance in terms of the sensitivity and positive predictive rate for V beats by more than 4.3% and 5.4%, respectively, and also for S beats by more than 22.6% and 25.9%, respectively, when compared to existing algorithms. It is anticipated that the proposed method will be suitable for implementation on portable devices for the e-home health monitoring of cardiovascular disease.

ARRHYTHMIA DIAGNOSIS FROM ECG SIGNAL ANALYSIS USING STATISTICAL FEATURES AND NOVEL CLASSIFICATION METHOD

2021 ◽  
pp. 2150025
Author(s):  
SAURAV MANDAL ◽  
NABANITA SINHA
Keyword(s):  
Cardiac Arrhythmia ◽  
Present Model ◽  
Fluctuation Analysis ◽  
Statistical Features ◽  
Multifractal Detrended Fluctuation Analysis ◽  
Ecg Signals ◽  
Proposed Model ◽  
Electrocardiogram Ecg ◽  
Detrended Fluctuation ◽  
Heart Condition

This study aims to present an efficient model for autodetection of cardiac arrhythmia by the diagnosis of self-affinity and identification of governing processes of a number of Electrocardiogram (ECG) signals taken from MIT-BIH database. In this work, the proposed model includes statistical methods to find the diagnosis pattern for detecting cardiac abnormalities which is useful for the computer aided system for arrhythmia detection. First, the Rescale Range (R/S) analysis has been employed for ECG signals to understand the scaling property of ECG signals. The value of Hurst exponent identifies the presence of abnormality in ECG signals taken for consideration with 92.58% accuracy. In this study, Higuchi method which deals with unifractality or monofractality of signals has been applied and it is found that unifractality is sufficient to detect arrhythmia with 91.61% accuracy. The Multifractal Detrended Fluctuation Analysis (MFDFA) has been used over the present signals to identify and confirm the multifractality. The nature of multifractality is different for arrhythmia patients and normal heart condition. The multifractal analysis is useful to detect abnormalities with 93.75% accuracy. Finally, the autocorrelation analysis has been used to identify the prevalent governing process in the present arrhythmic ECG signals and study confirms that all the signals are governed by stationary autoregressive methods of certain orders. In order to increase the overall efficiency, this present model deals with analyzing all the statistical features extracted from different statistical techniques for a large number of ECG signals of normal and abnormal heart condition. Finally, the result of present analysis altogether possibly indicates that the proposed model is efficient to detect cardiac arrhythmia with 99.3% accuracy.

scholarly journals ECG Heartbeat Classification Based on an Improved ResNet-18 Model

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Enbiao Jing ◽  
Haiyang Zhang ◽  
ZhiGang Li ◽  
Yazhi Liu ◽  
Zhanlin Ji ◽  
...  
Keyword(s):  
State Of The Art ◽  
Classification Performance ◽  
Classification Models ◽  
Heartbeat Classification ◽  
Ecg Signals ◽  
Residual Structure ◽  
Proposed Model ◽  
Model Training ◽  
Electrocardiogram Ecg

Based on a convolutional neural network (CNN) approach, this article proposes an improved ResNet-18 model for heartbeat classification of electrocardiogram (ECG) signals through appropriate model training and parameter adjustment. Due to the unique residual structure of the model, the utilized CNN layered structure can be deepened in order to achieve better classification performance. The results of applying the proposed model to the MIT-BIH arrhythmia database demonstrate that the model achieves higher accuracy (96.50%) compared to other state-of-the-art classification models, while specifically for the ventricular ectopic heartbeat class, its sensitivity is 93.83% and the precision is 97.44%.

scholarly journals An ECG signal model based on a parametric description of the characteristic waves

ACTA IMEKO ◽  
2020 ◽  
Vol 9 (2) ◽  
pp. 3
Author(s):  
Pavol Dolinsky ◽  
Imrich Andras ◽  
Linus Michaeli ◽  
Jan Saliga
Keyword(s):  
Model Parameters ◽  
Ecg Signal ◽  
Elementary Functions ◽  
Signal Model ◽  
Ecg Signals ◽  
Model Based ◽  
Proposed Model ◽  
Base Functions ◽  
Parametric Description ◽  
Electrocardiogram Ecg

This article introduces a new electrocardiogram (ECG) signal model based on geometric signal properties. Instead of the artificial functions used in common ECG models, the proposed model is based on the modelling of real ECG signals divided into time segments. Each segment has been modelled using simple geometrical forms. The final ECG signal model is represented by the sequence of parameters of the base functions. Parameter variations allow for the generation of different waveforms for each subsequent heartbeat without mixing up the PQRST waves order. Two basic models utilize slightly modified elementary functions, which are computationally simple. A combination of both models allows for the modelling of irregularities in the consecutive heartbeats of the specific ECG waveforms. Respiratory, noise, and powerline interference can be added in order to make the generated ECG signal more realistic. The model parameters are estimated by differential evolution optimization and a comparison between the modelled ECG and the acquired signal. The proposed models are tested by the database included in the LabVIEW Biomedical Toolkit and ECG records in the MIT-BIH arrhythmia database.

scholarly journals Automatic Detection of Arrhythmias Using a YOLO-Based Network with Long-Duration ECG Signals

2020 ◽  
Vol 2 (1) ◽  
pp. 84
Author(s):  
Won Hee Hwang ◽  
Chan Hee Jeong ◽  
Dong Hyun Hwang ◽  
Young Chang Jo
Keyword(s):  
Embedded System ◽  
High Performance ◽  
Detection Algorithm ◽  
Wearable Device ◽  
Arrhythmia Detection ◽  
Ecg Signals ◽  
Long Duration ◽  
Proposed Model ◽  
Different Types ◽  
Electrocardiogram Ecg

Early detection of arrhythmias is very important. Recently, wearable devices are being used to monitor the patient’s heartbeat to detect an arrhythmia. However, there are not satisfactory algorithms for real-time monitoring of arrhythmias in a wearable device. In this work, a novel fast and simple arrhythmia detection algorithm based on YOLO is proposed. The algorithm can detect each heartbeat on long-duration electrocardiogram (ECG) signals without R-peak detection and can classify an arrhythmia simultaneously. The model replaces the 2D Convolutional Neural networks (CNN) with a 1D CNN and the bounding box with a bounding window to utilize raw ECG signals. Results demonstrate that the proposed algorithm has high performance in speed and mean average precisionin detecting an arrhythmia. Furthermore, the bounding window can predict different window lengths on different types of arrhythmia. Therefore, the model can choose an optimal heartbeat window length for arrhythmia classification. Since the proposed model is a compact 1D CNN model based on YOLO, it can be used in a wearable device and embedded system.

scholarly journals Arrhythmia Classification Using One Dimensional Conventional Neural Network

2021 ◽  
Vol 13 (3) ◽  
pp. 43-58
Author(s):  
Sarah kamil ◽  
Lamia Muhammed
Keyword(s):  
Neural Network ◽  
Cardiovascular Disease ◽  
Deep Learning ◽  
Disease Classification ◽  
Visual Interpretation ◽  
Deep Convolutional Neural Networks ◽  
Bundle Branch Block ◽  
Ecg Signals ◽  
Short Period ◽  
Electrocardiogram Ecg

Arrhythmia is a heart condition that occurs due to abnormalities in the heartbeat, which means that the heart's electrical signals do not work properly, resulting in an irregular heartbeat or rhythm and thus defeating the pumping of blood. Some cases of arrhythmia are not considered serious, while others are very dangerous, life-threatening, and cause death in a short period of time. In the clinical routine, cardiac arrhythmia detection is performed by electrocardiogram (ECG) signals. The ECG is a significant diagnosis tool that is used to record the electrical activity of the heart, and its signals can reveal abnormal heart activity. However, because of their small amplitude and duration, visual interpretation of ECG signals is difficult. As a result, we present a significant approach for identifying arrhythmias using ECG signals. In this study, we proposed an approach based on Deep Learning (DL) technology that is a framework of nine-layer one-dimension Conventional Neural Network (1D CNN) for classifying automatically ECG signals into four cardiac conditions named: normal (N), Atrial Premature Beat (APB), Left Bundle Branch Block (LBBB), and Right Bundle Branch Block (RBBB). The practical test of this work was executed with the benchmark MIT-BIH database. We achieved an average accuracy of 99%, precision of 98%, recall of 96.5%, specificity of 99.08%, and an F1-score of 95.75%. The obtained results were compared with some relevant models, and they showed that the proposed framework outperformed those models in some measures. The new approach’s performance indicates its success. Also, it has been shown that deep convolutional neural networks can be used efficiently in automated detection and, therefore, cardiovascular disease protection as well as help cardiologists in medical practice by saving time and effort. Keywords: 1-D CNN, Arrhythmia, Cardiovascular Disease, Classification, Deep learning, Electrocardiogram(ECG), MIT-BIH arrhythmia database.

scholarly journals Symbolic Recurrence Analysis of RR Interval to Detect Atrial Fibrillation

2019 ◽  
Vol 8 (11) ◽  
pp. 1840 ◽  
Author(s):  
Jesús Pérez-Valero ◽  
M. Victoria Caballero Pintado ◽  
Francisco Melgarejo ◽  
Antonio-Javier García-Sánchez ◽  
Joan Garcia-Haro ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Ambulatory Monitoring ◽  
Ecg Signals ◽  
Predictive Algorithm ◽  
Predictive Algorithms ◽  
Proposed Model ◽  
Quantification Analysis ◽  
Fitting In ◽  
Electrocardiogram Ecg ◽  
Fold Cross Validation

Atrial fibrillation (AF) is a sustained cardiac arrhythmia associated with stroke, heart failure, and related health conditions. Though easily diagnosed upon presentation in a clinical setting, the transient and/or intermittent emergence of AF episodes present diagnostic and clinical monitoring challenges that would ideally be met with automated ambulatory monitoring and detection. Current approaches to address these needs, commonly available both in smartphone applications and dedicated technologies, combine electrocardiogram (ECG) sensors with predictive algorithms to detect AF. These methods typically require extensive preprocessing, preliminary signal analysis, and the integration of a wide and complex array of features for the detection of AF events, and are consequently vulnerable to over-fitting. In this paper, we introduce the application of symbolic recurrence quantification analysis (SRQA) for the study of ECG signals and detection of AF events, which requires minimal pre-processing and allows the construction of highly accurate predictive algorithms from relatively few features. In addition, this approach is robust against commonly-encountered signal processing challenges that are expected in ambulatory monitoring contexts, including noisy and non-stationary data. We demonstrate the application of this method to yield a highly accurate predictive algorithm, which at optimal threshold values is 97.9% sensitive, 97.6% specific, and 97.7% accurate in classifying AF signals. To confirm the robust generalizability of this approach, we further evaluated its performance in the implementation of a 10-fold cross-validation paradigm, yielding 97.4% accuracy. In sum, these findings emphasize the robust utility of SRQA for the analysis of ECG signals and detection of AF. To the best of our knowledge, the proposed model is the first to incorporate symbolic analysis for AF beat detection.

scholarly journals Computational Diagnostic Techniques for Electrocardiogram Signal Analysis

Sensors ◽  
2020 ◽  
Vol 20 (21) ◽  
pp. 6318
Author(s):  
Liping Xie ◽  
Zilong Li ◽  
Yihan Zhou ◽  
Yiliu He ◽  
Jiaxin Zhu
Keyword(s):  
Health Care Professionals ◽  
Signal Analysis ◽  
Cardiovascular Death ◽  
Diagnostic Techniques ◽  
Portable Devices ◽  
Ecg Signal ◽  
Great Success ◽  
Ecg Signals ◽  
Electrical Impulses ◽  
Electrocardiogram Ecg

Cardiovascular diseases (CVDs), including asymptomatic myocardial ischemia, angina, myocardial infarction, and ischemic heart failure, are the leading cause of death globally. Early detection and treatment of CVDs significantly contribute to the prevention or delay of cardiovascular death. Electrocardiogram (ECG) records the electrical impulses generated by heart muscles, which reflect regular or irregular beating activity. Computer-aided techniques provide fast and accurate tools to identify CVDs using a patient’s ECG signal, which have achieved great success in recent years. Latest computational diagnostic techniques based on ECG signals for estimating CVDs conditions are summarized here. The procedure of ECG signals analysis is discussed in several subsections, including data preprocessing, feature engineering, classification, and application. In particular, the End-to-End models integrate feature extraction and classification into learning algorithms, which not only greatly simplifies the process of data analysis, but also shows excellent accuracy and robustness. Portable devices enable users to monitor their cardiovascular status at any time, bringing new scenarios as well as challenges to the application of ECG algorithms. Computational diagnostic techniques for ECG signal analysis show great potential for helping health care professionals, and their application in daily life benefits both patients and sub-healthy people.

scholarly journals Classification of Heart conditions by Statistical Characterization of ECG Signal

2020 ◽  
Vol 16 (2) ◽  
Author(s):  
Asma Haque ◽  
Abdur Rahman
Keyword(s):  
Ventricular Tachyarrhythmia ◽  
Research Work ◽  
Ecg Signal ◽  
Statistical Characterization ◽  
Ecg Signals ◽  
Detection Algorithms ◽  
Heart Patients ◽  
Proposed Model ◽  
Electrocardiogram Ecg

Electrocardiogram (ECG) signal exhibits important distinctive feature for different cardiac issues. Automatic classification of electrocardiogram (ECG) signal can be used for primary detection of various heart conditions. Information about heart and ischemic changes of heart may be obtained from cleaned ECG signals. ECG signal has an important role in monitoring and diacritic of the heart patients. An accurate ECG classification is challenging problem. The accuracy often depends on proper selection of observing parameters as well as detection algorithms. Heart disorder means abnormal rhythm or abnormalities present in the heart. In this research work, we have developed a decision tree based algorithm to classify heart problems by utilizing the statistical signal characteristic (SSC) of an ECG signal. The proposed model has been tested with real ECG signal to successfully (60-98%) detect normal, apnea and ventricular tachyarrhythmia condition.

scholarly journals Detection of cardiac arrhythmia using deep CNN and optimized SVM

2021 ◽  
Vol 24 (1) ◽  
pp. 217
Author(s):  
Mohebbanaaz Mohebbanaaz ◽  
Y. Padma Sai ◽  
L. V. Rajani Kumari
Keyword(s):  
Deep Learning ◽  
Transfer Learning ◽  
Cardiac Arrhythmia ◽  
Support Vector ◽  
Automated Classification ◽  
Ecg Signals ◽  
Huge Data ◽  
Proposed Model ◽  
Deep Cnn ◽  
Electrocardiogram Ecg

<span>Deep learning (DL) <span>has become a topic of study in various applications, including healthcare. Detection of abnormalities in an electrocardiogram (ECG) plays a significant role in patient monitoring. It is noted that a deep neural network when trained on huge data, can easily detect cardiac arrhythmia. This may help cardiologists to start treatment as early as possible. This paper proposes a new deep learning model adapting the concept of transfer learning to extract deep-CNN features and facilitates automated classification of electrocardiogram (ECG) into sixteen types of ECG beats using an optimized support vector machine (SVM). The proposed strategy begins with gathering ECG datasets, removal of noise from ECG signals, and extracting beats from denoised ECG signals. Feature extraction is done using ResNet18 via concept of transfer learning. These extracted features are classified using optimized SVM. These methods are evaluated and tested on the MIT-BIH arrhythmia database. Our proposed model is effective compared to all State of Art Techniques with an accuracy of 98.70%.</span></span>

scholarly journals MINIATURE MODULES FOR MULTI-LEAD ECG RECORDING

2008 ◽  
Vol 20 (04) ◽  
pp. 219-222 ◽  
Author(s):  
Yi-Li Tseng ◽  
Hung-Wei Chiu ◽  
Tsung-Hsien Lin ◽  
Fu-Shan Jaw
Keyword(s):  
Home Health Care ◽  
Care Service ◽  
Health Care Service ◽  
Pass Band ◽  
Portable Devices ◽  
Biomedical Signals ◽  
Ecg Signals ◽  
Offset Voltage ◽  
Remote Monitoring Systems ◽  
Electrocardiogram Ecg

Remote monitoring systems for home health care service have become one of the hottest topics recently. Biomedical signals recorded by portable devices can be wirelessly transmitted through the Internet. In this paper, a miniature signal-condition module for ambulatory recording of electrocardiogram (ECG) signals was designed with high input impedance, high common-mode rejection ratio (CMRR), low power, appropriate amplification and filtration, and automatic suppression of offset voltage. For early detection of acute myocardial infarction (AMI), this device is extended and 12-lead ECG recording is available. Due to the modular approach, the module is accommodated for other biomedical signals recording as well if the gain and pass-band of the module are modified.

Sign in / Sign up

Export Citation Format

Share Document