scholarly journals A Hybrid Deep CNN Model for Abnormal Arrhythmia Detection Based on Cardiac ECG Signal

Sensors ◽  
2021 ◽  
Vol 21 (3) ◽  
pp. 951
Author(s):  
Amin Ullah ◽  
Sadaqat ur Rehman ◽  
Shanshan Tu ◽  
Raja Majid Mehmood ◽  
Fawad ◽  
...  
Keyword(s):  
Classification Accuracy ◽  
Vital Role ◽  
Massachusetts Institute Of Technology ◽  
One Dimensional ◽  
Ecg Signals ◽  
Electrocardiogram Signal ◽  
Deep Cnn ◽  
Institute Of Technology ◽  
Fully Connected ◽  
Electrocardiogram Ecg

Electrocardiogram (ECG) signals play a vital role in diagnosing and monitoring patients suffering from various cardiovascular diseases (CVDs). This research aims to develop a robust algorithm that can accurately classify the electrocardiogram signal even in the presence of environmental noise. A one-dimensional convolutional neural network (CNN) with two convolutional layers, two down-sampling layers, and a fully connected layer is proposed in this work. The same 1D data was transformed into two-dimensional (2D) images to improve the model’s classification accuracy. Then, we applied the 2D CNN model consisting of input and output layers, three 2D-convolutional layers, three down-sampling layers, and a fully connected layer. The classification accuracy of 97.38% and 99.02% is achieved with the proposed 1D and 2D model when tested on the publicly available Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) arrhythmia database. Both proposed 1D and 2D CNN models outperformed the corresponding state-of-the-art classification algorithms for the same data, which validates the proposed models’ effectiveness.

scholarly journals A Spatial Pyramid Pooling-Based Deep Convolutional Neural Network for the Classification of Electrocardiogram Beats

2018 ◽  
Vol 8 (9) ◽  
pp. 1590 ◽  
Author(s):  
Jia Li ◽  
Yujuan Si ◽  
Liuqi Lang ◽  
Lixun Liu ◽  
Tao Xu
Keyword(s):  
Classification Accuracy ◽  
Massachusetts Institute Of Technology ◽  
Deep Convolutional Neural Networks ◽  
Beat Classification ◽  
Spatial Pyramid Pooling ◽  
Institute Of Technology ◽  
Fixed Input ◽  
Fully Connected ◽  
Spatial Pyramid

An accurate electrocardiogram (ECG) beat classification can benefit the diagnosis of the cardiovascular disease. Deep convolutional neural networks (CNN) can automatically extract valid features from data, which is an effective way for the classification of the ECG beats. However, the fully-connected layer in CNNs requires a fixed input dimension, which limits the CNNs to receive fixed-scale inputs. Signals of different scales are generally processed into the same size by segmentation and downsampling. If information loss occurs during a uniformly-sized process, the classification accuracy will ultimately be affected. To solve this problem, this paper constructs a new CNN framework spatial pyramid pooling (SPP) method, which solves the deficiency caused by the size of input data. The Massachusetts Institute of Technology-Biotechnology (MIT-BIH) arrhythmia database is employed as the training and testing data for the classification of heartbeat signals into six categories. Compared with the traditional method, which may lose a large amount of important information and easy to be over-fitted, the robustness of the proposed method can be guaranteed by extracting data features from different sizes. Experimental results show that the proposed architecture network can extract more high-quality features and exhibits higher classification accuracy (94%) than the traditional deep CNNs (90.4%).

ELECTROCARDIOGRAM BEAT CLASSIFICATION USING S-TRANSFORM BASED FEATURE SET

2014 ◽  
Vol 14 (05) ◽  
pp. 1450066 ◽  
Author(s):  
MANAB KUMAR DAS ◽  
SAMIT ARI
Keyword(s):  
Feature Extraction ◽  
Support Vector ◽  
Svm Classifier ◽  
Massachusetts Institute Of Technology ◽  
Ecg Signals ◽  
Beat Classification ◽  
Temporal Features ◽  
S Transform ◽  
Institute Of Technology ◽  
Stockwell Transform

In this paper, the conventional Stockwell transform is effectively used to classify the ECG arrhythmias. The performance of ECG classification mainly depends on feature extraction based on an efficient formation of morphological and temporal features and the design of the classifier. Feature extraction is the important component of designing the system based on pattern recognition since even the best classifier will not perform better if the good features are not selected properly. Here, the S-transform (ST) is used to extract the morphological features which is appended with temporal features. This feature set is independently classified using artificial neural network (NN) and support vector machine (SVM). In this work, five classes of ECG beats (normal, ventricular, supra ventricular, fusion and unknown beats) from Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) arrhythmia database are classified according to AAMI EC57 1998 standard (Association for the Advancement of Medical Instrumentation). Performance is evaluated on several normal and abnormal ECG signals of MIT-BIH arrhythmias database using two classifier techniques: ST with NN classifier (ST-NN) and other proposed ST with SVM classifier (ST-SVM). The proposed method achieves accuracy of 98.47%. The performance of the proposed technique is compared with ST-NN and earlier reported technique.

FRACTAL ANALYSIS OF THE ELECTROCARDIOGRAM SIGNAL

2014 ◽  
Vol 14 (04) ◽  
pp. 1450055 ◽  
Author(s):  
IBTICEME SEDJELMACI ◽  
F. BEREKSI-REGUIG
Keyword(s):  
Premature Ventricular Contraction ◽  
Multifractal Spectrum ◽  
Bundle Branch Block ◽  
Ecg Signals ◽  
Linear Approach ◽  
Atrial Premature Beat ◽  
The Subject ◽  
Electrocardiogram Signal ◽  
Electrocardiogram Ecg

In this paper, the analysis of the electrocardiogram (ECG) signal is carried out according a non-linear approach. This concerns the eventual fractal behavior of such signal and the correlation of such behavior with normal and pathological ECG signals. The analysis is carried out on different ECG signals taken from the MIT-BIH arrhythmia database. In fact these signals are those of six subjects with different ages and presenting both normal and abnormal arrhythmias situations. The abnormal situations are atrial premature beat (APB), premature ventricular contraction (PVC), right bundle branch block (RBBB) and left bundle branch block (LBBB). The fractal behavior of these signals is analyzed according to the determination of the multifractal spectrum and the fractal dimension variations and looking for eventually a fractal signature of each heart disease and age of the subject. The obtained results show a fractal signature according to the age and the pathologies for the studied cases. However further investigations are required on larger databases to confirm such results.

scholarly journals Electrocardiogram Signal Denoising by Hilbert Transform and Synchronous Detection

2020 ◽  
Vol 24 (4) ◽  
pp. 323-336
Author(s):  
Mohammed Assam Ouali ◽  
◽  
Asma Tinouna ◽  
Mouna Ghanai ◽  
Kheireddine Chafaa
Keyword(s):  
Hilbert Transform ◽  
High Energy ◽  
Signal Denoising ◽  
Ecg Signal ◽  
Synchronous Detection ◽  
Ecg Signals ◽  
Dominant Component ◽  
Electrocardiogram Signal ◽  
Electrocardiogram Ecg ◽  
Ecg Database

An efficient method for Electrocardiogram (ECG) signal denoising based on synchronous detection and Hilbert transform techniques is presented. The goal of the method is to decompose a noisy ECG signal into two components classified according to their energy: (1) component with high energy representing the dominant component which is the clean ECG signal, and (2) component with low energy representing the sub-dominant component which is the contaminant noise. The investigated approach is validated through out some experimentations on MIT-BIH ECG database. Experimental results show that random noises can be effectively suppressed from ECG signals.

scholarly journals Feature Extraction of ECG Signals using NI LabVIEW Biomedical Workbench and Classification with Artificial Neural Network

2019 ◽  
pp. 34-38
Author(s):  
Ebru Sayilgan ◽  
Savas Sahin
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Heart Beat ◽  
Massachusetts Institute Of Technology ◽  
Data Set ◽  
Ecg Signals ◽  
Multiple Classification ◽  
Sensitivity And Selectivity ◽  
Artificial Neural ◽  
Institute Of Technology

In this study, a data set containing normal and different heart beat types recorded by the Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) was used for the detection of cardiac dysfunctions. In this data set, features were extracted using the LabVIEW Biomedical Workbench from the normal heartbeat and six different arrhythmia types. Obtained signals were evaluated by using Artificial Neural Network multiple classification method. Classification performances were compared before extracting the feature on the same data set. Classifier performances were evaluated by accuracy, sensitivity and selectivity performances criteria of classification. In the classifier performances, the "Normal" beat rate was found to be 99% accurate with the highest success compared to other arrhythmia types. As a result, both analysis methods are successful, but when the LabVIEW Biomedical Workbench is used, the classification results have achieved higher success.

Localization of Characteristic Peaks in Cardiac Signal

2015 ◽  
Vol 4 (1) ◽  
pp. 18-31
Author(s):  
Subash Khanal ◽  
N. Sriraam
Keyword(s):  
Segment Length ◽  
Ecg Signal ◽  
Ecg Signals ◽  
Accurate Localization ◽  
Characteristic Points ◽  
Institute Of Technology ◽  
Simplified Procedure ◽  
Electrocardiogram Ecg ◽  
Research Domain ◽  
Selection Of

Cardiovascular system study using Electrocardiogram (ECG) signals have evolved tremendously in the research domain of medical electronics and signal processing community. The extraction of characteristic points of an ECG signal helps in detection of any irregularities if present. This paper attempts to provide the basic understanding of ECG signal, pre-processing and extraction of fiducial points P, Q, R, S, T and their respective amplitude. Continuous Wavelet Transform (CWT) has been used for the localization of R peaks. Finally, other peaks are localized in time plane, using inter-beat interval dependent search windows. The proposed method was tested using ECG signal data obtained from MIT Physionet-ATM database and Signals derived from medical instrumentation lab of M.S. Ramaiah Institute of Technology. The simulation results were quite promising in terms of accurate localization of characteristic peaks, their respective amplitude in time plane and other features like R-R intervals, QRS width, S-T segment length, etc. The simplified procedure proposed in this study shows clear indication for arrhythmias detection which can be extended for automated ECG signal classification by appropriate selection of pattern classifiers.

Automatic Arrhythmia Detection

2010 ◽  
pp. 204-218
Author(s):  
Carlos M. Travieso ◽  
Jesús B. Alonso ◽  
Miguel A. Ferrer ◽  
Jorge Corsino
Keyword(s):  
Support Vector ◽  
Massachusetts Institute Of Technology ◽  
Classification Methods ◽  
Success Rates ◽  
Arrhythmia Detection ◽  
Time Frequency ◽  
Vector Machines ◽  
Institute Of Technology ◽  
Electrocardiogram Ecg ◽  
Frequency Features

In the present chapter, the authors have developed a tool for the automatic arrhythmias detection, based on time-frequency features and using a Support Vector Machines (SVM) as classifier. Arrhythmia Database Massachusetts Institute of Technology (MIT) has been used in the work in order to detect eight different states, seven are pathologies and one is normal. The unions of different blocks and its optimization have found success rates of 99.82% for RR’ interval detection from electrocardiogram (PQRST waves), and 99.23% for pathologic detection. In particular, the authors have used wavelet transform in order to characterize the wave of electrocardiogram (ECG), based on Biorthogonal family, achieving the most discriminative coefficients. A discussion on arrhythmia ECG classification methods is also presented in this paper.

scholarly journals An Automatic System for Atrial Fibrillation by Using a CNN-LSTM Model

2020 ◽  
Vol 2020 ◽  
pp. 1-9
Author(s):  
Fengying Ma ◽  
Jingyao Zhang ◽  
Wei Chen ◽  
Wei Liang ◽  
Wenjia Yang
Keyword(s):  
Atrial Fibrillation ◽  
Classification Accuracy ◽  
Short Term Memory ◽  
Sequence Data ◽  
Detection System ◽  
Heart Rhythm ◽  
Classification Performance ◽  
Ecg Signals ◽  
Electrocardiogram Ecg

Atrial fibrillation (AF) is a common abnormal heart rhythm disease. Therefore, the development of an AF detection system is of great significance to detect critical illnesses. In this paper, we proposed an automatic recognition method named CNN-LSTM to automatically detect the AF heartbeats based on deep learning. The model combines convolutional neural networks (CNN) to extract local correlation features and uses long short-term memory networks (LSTM) to capture the front-to-back dependencies of electrocardiogram (ECG) sequence data. The CNN-LSTM is feeded by processed data to automatically detect AF signals. Our study uses the MIT-BIH Atrial Fibrillation Database to verify the validity of the model. We achieved a high classification accuracy for the heartbeat data of the test set, with an overall classification accuracy rate of 97.21%, sensitivity of 97.34%, and specificity of 97.08%. The experimental results show that our model can robustly detect the onset of AF through ECG signals and achieve stable classification performance, thereby providing a suitable candidate for the automatic classification of AF.

Electrocardiography (ECG) analysis and a new feature extraction method using wavelet transform with scalogram analysis

2020 ◽  
Vol 0 (0) ◽  
Author(s):  
Hüseyin Yanık ◽  
Evren Değirmenci ◽  
Belgin Büyükakıllı ◽  
Derya Karpuz ◽  
Olgu Hallıoğlu Kılınç ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Correct Diagnosis ◽  
Statistical Investigation ◽  
Massachusetts Institute Of Technology ◽  
Ecg Analysis ◽  
Feature Extraction Method ◽  
Ecg Signals ◽  
Detection Analysis ◽  
Institute Of Technology ◽  
New Feature

AbstractElectrocardiography (ECG) signals and the information obtained through the analysis of these signals constitute the main source of diagnosis for many cardiovascular system diseases. Therefore, accurate analyses of ECG signals are very important for correct diagnosis. In this study, an ECG analysis toolbox together with a user-friendly graphical user interface, which contains the all ECG analysis steps between the recording unit and the statistical investigation, is developed. Furthermore, a new feature calculation methodology is proposed for ECG analysis, which carries distinct information than amplitudes and durations of ECG main waves and can be used in artificial intelligence studies. Developed toolbox is tested using both Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) Arrhythmia ECG Database and an experimentally collected dataset for performance evaluation. The results show that ECG analysis toolbox presented in this study increases the accuracy and reliability of the ECG main wave detection analysis, highly fasten the process duration compared to manual ones and the new feature set can be used as a new parameter for decision support systems about ECG based on artificial intelligence.

scholarly journals A Deep-Learning Approach to ECG Classification Based on Adversarial Domain Adaptation

Healthcare ◽  
2020 ◽  
Vol 8 (4) ◽  
pp. 437
Author(s):  
Lisha Niu ◽  
Chao Chen ◽  
Hui Liu ◽  
Shuwang Zhou ◽  
Minglei Shu
Keyword(s):  
Deep Learning ◽  
Classification Accuracy ◽  
Domain Adaptation ◽  
Human Life ◽  
Diagnostic System ◽  
Ecg Signals ◽  
Cross Domain ◽  
Training Samples ◽  
Computer Aided ◽  
Fully Connected

Cardiovascular disease has become one of the main diseases threatening human life and health. This disease is very common and troublesome, and the existing medical resources are scarce, so it is necessary to use a computer-aided automatic diagnosis to overcome these limitations. A computer-aided diagnostic system can automatically diagnose through an electrocardiogram (ECG) signal. This paper proposes a novel deep-learning method for ECG classification based on adversarial domain adaptation, which solves the problem of insufficient-labeled training samples, improves the phenomenon of different data distribution caused by individual differences, and enhances the classification accuracy of cross-domain ECG signals with different data distributions. The proposed method includes three modules: multi-scale feature extraction F, domain discrimination D, and classification C. The module F, constitutive of three different parallel convolution blocks, is constructed to increase the breadth of features extracted from this module. The module D is composed of three convolutional blocks and a fully connected layer, which is to solve the problem of low model layers and low-feature abstraction. In the module C, the time features and the deep-learning extraction features are concatenated on the fully connected layer to enhance feature diversity. The effectiveness of the proposed method is verified by experiments, and the classification accuracy of the experimental electrical signals reaches 92.3%.

Sign in / Sign up

Export Citation Format

Share Document