scholarly journals Data Independent Acquisition Based Bi-Directional Deep Networks for Biometric ECG Authentication

2021 ◽  
Vol 11 (3) ◽  
pp. 1125
Author(s):  
Htet Myet Lynn ◽  
Pankoo Kim ◽  
Sung Bum Pan
Keyword(s):  
Short Term Memory ◽  
Feature Learning ◽  
Biometric Authentication ◽  
Qrs Complex ◽  
Data Types ◽  
Ecg Signals ◽  
Data Independent Acquisition ◽  
Deep Networks ◽  
Classification Tasks ◽  
Electrocardiogram Ecg

In this report, the study of non-fiducial based approaches for Electrocardiogram(ECG) biometric authentication is examined, and several excessive techniques are proposed to perform comparative experiments for evaluating the best possible approach for all the classification tasks. Non-fiducial methods are designed to extract the discriminative information of a signal without annotating fiducial points. However, this process requires peak detection to identify a heartbeat signal. Based on recent studies that usually rely on heartbeat segmentation, QRS detection is required, and the process can be complicated for ECG signals for which the QRS complex is absent. Thus, many studies only conduct biometric authentication tasks on ECG signals with QRS complexes, and are hindered by similar limitations. To overcome this issue, we proposed a data-independent acquisition method to facilitate highly generalizable signal processing and feature learning processes. This is achieved by enhancing random segmentation to avoid complicated fiducial feature extraction, along with auto-correlation to eliminate the phase difference due to random segmentation. Subsequently, a bidirectional recurrent neural network (RNN) with long short-term memory (LSTM) deep networks is utilized to automatically learn the features associated with the signal and to perform an authentication task. The experimental results suggest that the proposed data-independent approach using a BLSTM network achieves a relatively high classification accuracy for every dataset relative to the compared techniques. Moreover, it exhibited a significantly higher accuracy rate in experiments using ECG signals without the QRS complex. The results also revealed that data-dependent methods can only perform well for specified data types and amendments of data variations, whereas the presented approach can also be considered for generalization to other quasi-periodical biometric signal-based classification tasks in future studies.

scholarly journals IMPROVEMENT OF THE CREDIBILITY OF ANALYSIS OF ELECTROCARDIOGRAMS FOR BIOMETRIC PERSONAL IDENTIFICATION

2020 ◽  
pp. 125-130
Author(s):  
Яковенко І.О. ◽  
Рудий О.Д. ◽  
Турчина М.О.
Keyword(s):  
Electrical Activity ◽  
Age Groups ◽  
Personal Identification ◽  
Physical Parameters ◽  
Biometric Authentication ◽  
High Demand ◽  
Biometric Data ◽  
Ecg Signals ◽  
High Level ◽  
Electrocardiogram Ecg

Nowadays there is a high demand for biometric authentication. These systems possess a high level of protection, as they evaluate not only the physical parameters, but also personality characteristics. The paper analyzes a biometric scheme based on the electrical activity of the human heart in the form of electrocardiogram (ECG) signals. The study was performed using standard laboratory measurements KL-720 has all age groups. As a result, an electrical activity signal was obtained. The aim of this work was to filter the captured signal for further use with biometric data.

Semantic Segmentation of QRS Complex in Single Channel ECG with Bidirectional LSTM Networks

2020 ◽  
Vol 10 (3) ◽  
pp. 758-762 ◽  
Author(s):  
Lingfeng Liu ◽  
Baodan Bai ◽  
Xinrong Chen ◽  
Qin Xia
Keyword(s):  
Short Term Memory ◽  
Single Channel ◽  
Semantic Segmentation ◽  
Time Interval ◽  
Qrs Complex ◽  
Short Term ◽  
Attention Model ◽  
Interval Prediction ◽  
Long Short Term Memory ◽  
Electrocardiogram Ecg

In this paper, bidirectional Long Short-Term Memory (BiLSTM) networks are designed to realize the semantic segmentation of QRS complex in single channel electrocardiogram (ECG) for the tasks of R peak detection and heart rate estimation. Three types of seq2seq BiLSTM networks are introduced, including the densely connected BiLSTM with attention model, the BiLSTM U-Net, and the BiLSTM U-Net++. To alleviate the sparse problem of the QRS labels, symmetric label expansion is applied by extending the single R peak into a time interval of fixed length. Linear ensemble method is introduced that averages the outputs of different BiLSTM networks. The cross-validation results show significant increase of the accuracy and decrease of discontinuous gaps in the QRS interval prediction by the ensembling over singular neural networks.

ALGORITHM FOR AUTOMATIC DETECTION OF ECG WAVES

2011 ◽  
Vol 11 (01) ◽  
pp. 15-29 ◽  
Author(s):  
DIB. NABIL ◽  
F. BEREKSI-REGUIG
Keyword(s):  
Detection Accuracy ◽  
Ecg Signal ◽  
Qrs Complex ◽  
Qrs Detection ◽  
Accurate Identification ◽  
Ecg Signals ◽  
Good Ability ◽  
Noisy Conditions ◽  
Electrocardiogram Ecg ◽  
T Waves

An accurate measurement of the different electrocardiogram (ECG) intervals is dependent on the accurate identification of the beginning and the end of the P, QRS, and T waves. Available commercial systems provide a good QRS detection accuracy. However, the detection of the P and T waves remains a serious challenge due to their widely differing morphologies in normal and abnormal beats. In this paper, a new algorithm for the detection of the QRS complex as well as for P and T waves identification is provided. The proposed algorithm is based on different approaches and methods such as derivations, thresholding, and surface indicator. The proposed algorithm is tested and evaluated on ECG signals from the universal MIT-BIH database. It shows a good ability to detect P, QRS, and T waves for different cases of ECG signal even in very noisy conditions. The obtained QRS, sensitivity and positive predictivity are respectively 95.39% and 98.19%. The developed algorithm is also able to separate the overlapping P and T waves.

scholarly journals An Effective LSTM Recurrent Network to Detect Arrhythmia on Imbalanced ECG Dataset

2019 ◽  
Vol 2019 ◽  
pp. 1-10 ◽  
Author(s):  
Junli Gao ◽  
Hongpo Zhang ◽  
Peng Lu ◽  
Zongmin Wang
Keyword(s):  
Short Term Memory ◽  
Recurrent Network ◽  
Short Term ◽  
Ecg Signals ◽  
Beat Classification ◽  
Long Short Term Memory ◽  
Lstm Network ◽  
Reliable Solution ◽  
Electrocardiogram Ecg

To reduce the high mortality rate from cardiovascular disease (CVD), the electrocardiogram (ECG) beat plays a significant role in computer-aided arrhythmia diagnosis systems. However, the complex variations and imbalance of ECG beats make this a challenging issue. Since ECG beat data exist in heavily imbalanced category, an effective long short-term memory (LSTM) recurrence network model with focal loss (FL) is proposed. For this purpose, the LSTM network can disentangle the timing features in complex ECG signals, while the FL is used to resolve the category imbalance by downweighting easily identified normal ECG examples. The advantages of the proposed network have been verified in the MIT-BIH arrhythmia database. Experimental results show that the LSTM network with FL achieved a reliable solution to the problem of imbalanced datasets in ECG beat classification and was not sensitive to quality of ECG signals. The proposed method can be deployed in telemedicine scenarios to assist cardiologists into more accurately and objectively diagnosing ECG signals.

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.

scholarly journals Opening the black box: interpretability of machine learning algorithms in electrocardiography

2021 ◽  
Vol 379 (2212) ◽  
Author(s):  
Matteo Bodini ◽  
Massimo W. Rivolta ◽  
Roberto Sassi
Keyword(s):  
Machine Learning ◽  
Machine Learning Algorithms ◽  
P Wave ◽  
Qrs Complex ◽  
Ecg Signals ◽  
T Wave ◽  
Cardiac Abnormalities ◽  
Challenges And Opportunities ◽  
Clinically Significant ◽  
Electrocardiogram Ecg

Recent studies have suggested that cardiac abnormalities can be detected from the electrocardiogram (ECG) using deep machine learning (DL) models. However, most DL algorithms lack interpretability, since they do not provide any justification for their decisions. In this study, we designed two new frameworks to interpret the classification results of DL algorithms trained for 12-lead ECG classification. The frameworks allow us to highlight not only the ECG samples that contributed most to the classification, but also which between the P-wave, QRS complex and T-wave, hereafter simply called ‘waves’, were the most relevant for the diagnosis. The frameworks were designed to be compatible with any DL model, including the ones already trained. The frameworks were tested on a selected Deep Neural Network, trained on a publicly available dataset, to automatically classify 24 cardiac abnormalities from 12-lead ECG signals. Experimental results showed that the frameworks were able to detect the most relevant ECG waves contributing to the classification. Often the network relied on portions of the ECG which are also considered by cardiologists to detect the same cardiac abnormalities, but this was not always the case. In conclusion, the proposed frameworks may unveil whether the network relies on features which are clinically significant for the detection of cardiac abnormalities from 12-lead ECG signals, thus increasing the trust in the DL models. This article is part of the theme issue ‘Advanced computation in cardiovascular physiology: new challenges and opportunities’.

scholarly journals An Efficient Technique for Compressing ECG Signals Using QRS Detection, Estimation, and 2D DWT Coefficients Thresholding

2012 ◽  
Vol 2012 ◽  
pp. 1-10 ◽  
Author(s):  
Mohammed Abo-Zahhad ◽  
Sabah M. Ahmed ◽  
Ahmed Zakaria
Keyword(s):  
Threshold Level ◽  
Ecg Signal ◽  
Error Signal ◽  
Qrs Complex ◽  
Qrs Detection ◽  
High Compression Ratio ◽  
Compression Technique ◽  
Ecg Signals ◽  
The Difference ◽  
Electrocardiogram Ecg

This paper presents an efficient electrocardiogram (ECG) signals compression technique based on QRS detection, estimation, and 2D DWT coefficients thresholding. Firstly, the original ECG signal is preprocessed by detecting QRS complex, then the difference between the preprocessed ECG signal and the estimated QRS-complex waveform is estimated. 2D approaches utilize the fact that ECG signals generally show redundancy between adjacent beats and between adjacent samples. The error signal is cut and aligned to form a 2-D matrix, then the 2-D matrix is wavelet transformed and the resulting wavelet coefficients are segmented into groups and thresholded. There are two grouping techniques proposed to segment the DWT coefficients. The threshold level of each group of coefficients is calculated based on entropy of coefficients. The resulted thresholded DWT coefficients are coded using the coding technique given in the work by (Abo-Zahhad and Rajoub, 2002). The compression algorithm is tested for 24 different records selected from the MIT-BIH Arrhythmia Database (MIT-BIH Arrhythmia Database). The experimental results show that the proposed method achieves high compression ratio with relatively low distortion and low computational complexity in comparison with other methods.

scholarly journals Bi-level Probabilistic Feature Learning for Deformable Image Registration

2020 ◽  
Author(s):  
Risheng Liu ◽  
Zi Li ◽  
Yuxi Zhang ◽  
Xin Fan ◽  
Zhongxuan Luo
Keyword(s):  
Image Registration ◽  
Optimization Model ◽  
State Of The Art ◽  
Feature Learning ◽  
Deformable Registration ◽  
Deep Networks ◽  
Level Model ◽  
Classification Tasks ◽  
Upper Level ◽  
Traditional Approaches

We address the challenging issue of deformable registration that robustly and efficiently builds dense correspondences between images. Traditional approaches upon iterative energy optimization typically invoke expensive computational load. Recent learning-based methods are able to efficiently predict deformation maps by incorporating learnable deep networks. Unfortunately, these deep networks are designated to learn deterministic features for classification tasks, which are not necessarily optimal for registration. In this paper, we propose a novel bi-level optimization model that enables jointly learning deformation maps and features for image registration. The bi-level model takes the energy for deformation computation as the upper-level optimization while formulates the maximum \emph{a posterior} (MAP) for features as the lower-level optimization. Further, we design learnable deep networks to simultaneously optimize the cooperative bi-level model, yielding robust and efficient registration. These deep networks derived from our bi-level optimization constitute an unsupervised end-to-end framework for learning both features and deformations. Extensive experiments of image-to-atlas and image-to-image deformable registration on 3D brain MR datasets demonstrate that we achieve state-of-the-art performance in terms of accuracy, efficiency, and robustness.

scholarly journals The validity of a person’s authentication using an electrocardiogram with a limited number of channels

2020 ◽  
Vol 2 ◽  
pp. 43-50
Author(s):  
V.V. Vyshnevskyi ◽  
◽  
T.N. Romanenko ◽  
Yu.O. Lugovskyi ◽  
◽  
...  
Keyword(s):  
Phase Space ◽  
Single Channel ◽  
Three Dimensional ◽  
Qrs Complex ◽  
Ecg Signals ◽  
Dimensional Phase Space ◽  
Number Of Patients ◽  
Ecg Leads ◽  
Electrocardiogram Ecg ◽  
Synthetic Phase

The concept of mobile and home telemedicine for screening and early diagnostics of cardiovascular dis-eases is being expanded due to the emergence of mobile diagnostic devices and smartphones. In the course of such telemedicine consultations, the doctor must be sure that the digital electrocardiogram (ECG) be-longs to the patient who was registered. Both multi-channel and single-channel ECG-recording devices are available on the telemedicine consulting market now. Single-channel electrocardiographs are more eco-nomic feasible for home use. Previously, the authors have developed and experimentally tested the algo-rithms for patient authentication by his/her multi-channel ECG. These algorithms are based on the analysis of the shape of QRS complex in three-dimensional phase space of coordinates. Therefore, it is reasonable to adapt these algorithms to single-channel ECG. In case of multi-channel ECG, we can construct a three-dimensional phase space of coordinates by obtaining all the necessary data from the ECG leads. In a case of the single-channel ECG it is necessary to create two additional signals artificially and then it will be possible to form a synthetic phase space. In general, the question of the validity of biometric person au-thentication algorithms by his/her ECG with a limited number of channels is discussed in this paper. Be-sides the algorithms for solving the problem of authentication, the comparison of sensitivity and specificity indicators, calculated on the results of experiments for multi-channel and single-channel ECG, are also given in this paper. The results of experiments with multi-channel and single-channel ECG of a larger number of patients are given in comparison to the previous experiments. The results of the experiments for the case of recording ECG signals by different devices are given as well.

scholarly journals ConvNet: 1D-Convolutional Neural Networks for Cardiac Arrhythmia Recognition Using ECG Signals

2021 ◽  
Vol 38 (6) ◽  
pp. 1737-1745
Author(s):  
Amine Ben Slama ◽  
Hanene Sahli ◽  
Ramzi Maalmi ◽  
Hedi Trabelsi
Keyword(s):  
Cardiac Arrhythmia ◽  
Heart Beat ◽  
Diagnostic Tools ◽  
Qrs Complex ◽  
Complex Signals ◽  
Ecg Signals ◽  
Proposed Model ◽  
Improved Performance ◽  
Electrocardiogram Ecg ◽  
Aided Diagnosis

In healthcare, diagnostic tools of cardiac diseases are commonly known by the electrocardiogram (ECG) analysis. Atypical electrical activity can produce a cardiac arrhythmia. Various difficulties can be imposed to clinicians e.g., myocardial infarction arrhythmia via the non-stationarity and irregularity heart beat signals. Through the assistance of computer-aided diagnosis methods, timely specification of arrhythmia diseases reduces the mortality rate of affected patients. In this study, a 1 Lead QRS complex -layer deep convolutional neural network is proposed for the recognition of arrhythmia datasets. By the use of this CNN model, we planned a complete structure of the classification architecture after a pre-processing stage counting the denoising and QRS complex signals detection procedure. The chief benefit of the new proposed methodology is that the automatically training the QRS complexes without requiring all original extracted ECG signals. The proposed model was trained on the increased ECG database and separated into five classes. Experimental results display that the established CNN method has improved performance when compared to the state-of-the-art studies.

Sign in / Sign up

Export Citation Format

Share Document