scholarly journals Automated Cardiovascular Arrhythmia Classification Based on Through Nonlinear Features and Tunable-Q Wavelet Transform (TQWT) Based Decomposition

2021 ◽  
Vol 8 (2) ◽  
pp. 35-41
Author(s):  
Nazanin Tataei Sarshar ◽  
Mehdi Abdossalehi
Keyword(s):  
Cardiovascular Disease ◽  
Wavelet Transform ◽  
Cardiac Arrhythmias ◽  
Heart Attack ◽  
Ecg Signal ◽  
Q Factor ◽  
Ecg Signals ◽  
Heart Patients ◽  
Normal People ◽  
Nonlinear Features

Today, cardiovascular disease has become an epidemic. Statistics show that one person dies every 33 seconds due to cardiovascular disease. It is estimated that 33% of men and 10% of women have a heart attack before the age of 60. Arrhythmias are abnormal beats that cause the heart to beat too fast or too slow to pump. Automatic electrocardiogram analysis is critical to the diagnosis and treatment of heart patients. There are several learning methods for analyzing ECG signals to diagnose arrhythmias. In the proposed method, the heart rate signals are decomposed into different sub bands using the Tunable Q-Factor Wavelet Transform (TQWT) method, then the features are extracted and modified using classification with the aim of better classifying and separating data in the process of identifying the clinical features of the class. They are classified so that normal people and people with cardiac arrhythmias can be distinguished from their ECG signals. The results showed that the proposed method classifies the ECG signal with 99.25% accuracy. Since accuracy in diagnosing cardiac arrhythmias in medicine is a vital and important factor, so the proposed method can be very effective for the decision of cardiologists.

scholarly journals ECG signal diagnoses using intelligent systems

2018 ◽  
Vol 7 (4) ◽  
pp. 2733
Author(s):  
Raaed Faleh Hassan ◽  
Sally Abdulmunem Shaker
Keyword(s):  
Cardiac Arrhythmias ◽  
Intelligent Systems ◽  
Fuzzy Inference ◽  
Accurate Diagnosis ◽  
Ecg Signal ◽  
Backpropagation Neural Network ◽  
Inference System ◽  
Ecg Signals ◽  
Heart Patients ◽  
Electrocardiogram Ecg

Accurate diagnosis of arrhythmias plays a crucial role in saving the lives of many heart patients. The aim of this research is to find the more efficient method to diagnosis electrocardiogram (ECG) diseases. This work presents the use of Backpropagation neural network (BPNN) and fuzzy logic for automatic detection of cardiac arrhythmias based on analysis of the ECG. These a more valuable tool used to classify ECG signals in cardiac patients. Data collected from physioBank ATM. The analysis of the ECG signal is performed in MATLAB environment. In BPNN the results appear that the only two misclassifications happened to result in an accuracy of 90.4%. while in fuzzy inference system the results appear that the classification accuracy is 100%.   

DISCRETE WAVELET TRANSFORM APPLIED ON PERSONAL IDENTITY VERIFICATION WITH ECG SIGNAL

2009 ◽  
Vol 07 (03) ◽  
pp. 341-355 ◽  
Author(s):  
CHUANG-CHIEN CHIU ◽  
CHOU-MIN CHUANG ◽  
CHIH-YU HSU
Keyword(s):  
Wavelet Transform ◽  
Discrete Wavelet Transform ◽  
Personal Identity ◽  
Rejection Rate ◽  
Normal Subjects ◽  
Discrete Wavelet ◽  
Ecg Signal ◽  
Identity Verification ◽  
Ecg Signals ◽  
Electrocardiogram Ecg

The main purpose of this study is to present a novel personal authentication approach with the electrocardiogram (ECG) signal. The electrocardiogram is a recording of the electrical activity of the heart and the recorded signals can be used for individual verification because ECG signals of one person are never the same as those of others. The discrete wavelet transform was applied for extracting features that are the wavelet coefficients derived from digitized signals sampled from one-lead ECG signal. By the proposed approach applied on 35 normal subjects and 10 arrhythmia patients, the verification rate was 100% for normal subjects and 81% for arrhythmia patients. Furthermore, the performance of the ECG verification system was evaluated by the false acceptance rate (FAR) and false rejection rate (FRR). The FAR was 0.83% and FRR was 0.86% for a database containing only 35 normal subjects. When 10 arrhythmia patients were added into the database, FAR was 12.50% and FRR was 5.11%. The experimental results demonstrated that the proposed approach worked well for normal subjects. For this reason, it can be concluded that ECG used as a biometric measure for personal identity verification is feasible.

scholarly journals SS-SWT and SI-CNN: An Atrial Fibrillation Detection Framework for Time-Frequency ECG Signal

2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Hongpo Zhang ◽  
Renke He ◽  
Honghua Dai ◽  
Mingliang Xu ◽  
Zongmin Wang
Keyword(s):  
Atrial Fibrillation ◽  
Wavelet Transform ◽  
Morbidity And Mortality ◽  
High Morbidity ◽  
Ecg Signal ◽  
Time Frequency ◽  
Ecg Signals ◽  
Convolution Process ◽  
The Time Domain ◽  
Atrial Fibrillation Detection

Atrial fibrillation is the most common arrhythmia and is associated with high morbidity and mortality from stroke, heart failure, myocardial infarction, and cerebral thrombosis. Effective and rapid detection of atrial fibrillation is critical to reducing morbidity and mortality in patients. Screening atrial fibrillation quickly and efficiently remains a challenging task. In this paper, we propose SS-SWT and SI-CNN: an atrial fibrillation detection framework for the time-frequency ECG signal. First, specific-scale stationary wavelet transform (SS-SWT) is used to decompose a 5-s ECG signal into 8 scales. We select specific scales of coefficients as valid time-frequency features and abandon the other coefficients. The selected coefficients are fed to the scale-independent convolutional neural network (SI-CNN) as a two-dimensional (2D) matrix. In SI-CNN, a convolution kernel specifically for the time-frequency characteristics of ECG signals is designed. During the convolution process, the independence between each scale of coefficient is preserved, and the time domain and the frequency domain characteristics of the ECG signal are effectively extracted, and finally the atrial fibrillation signal is quickly and accurately identified. In this study, experiments are performed using the MIT-BIH AFDB data in 5-s data segments. We achieve 99.03% sensitivity, 99.35% specificity, and 99.23% overall accuracy. The SS-SWT and SI-CNN we propose simplify the feature extraction step, effectively extracts the features of ECG, and reduces the feature redundancy that may be caused by wavelet transform. The results shows that the method can effectively detect atrial fibrillation signals and has potential in clinical application.

scholarly journals Classification of Heart Rate Time Series Using Machine Learning Algorithms

2021 ◽  
Vol 2 (1) ◽  
Keyword(s):  
Detection System ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Ecg Signal ◽  
Ecg Signals ◽  
Heart Patients ◽  
Extraction Step ◽  
Ecg Arrhythmia ◽  
Electrocardiogram Ecg ◽  
The Given

An important diagnostic method for diagnosing abnormalities in the human heart is the electrocardiogram (ECG). A large number of heart patients increase the assignment of physicians. To reduce their assignment, an automatic computer detection system is needed. In this study, a computer system for classifying ECG signals is presented. The MIT-BIH, ECG arrhythmia database is used for analysis. After the ECG signal is noisy in the preprocessing stage, the data feature is extracted. In the feature extraction step, the decision tree is used and the support vector machine (SVM) is constructed to classify the ECG signal into two categories. It is normal or abnormal. The results show that the system classifies the given ECG signal with 90% sensitivity.

scholarly journals Analysis and Synthesis of Electrocardiogram (ECG) using Fourier and Wavelet Transform

2020 ◽  
Vol 17 (02) ◽  
Keyword(s):  
Wavelet Transform ◽  
Wavelet Analysis ◽  
Wavelet Transforms ◽  
Great Accuracy ◽  
Ecg Signal ◽  
Ecg Signals ◽  
Analysis And Synthesis ◽  
The Time Domain ◽  
Transformation Methods ◽  
Electrocardiogram Ecg

Electrocardiogram (ECG) is the study of the electrical signals of the human heart that are generated by the pumping action of the heart caused by the polarization and depolarization of the nodes of the heart. These signals must be interpreted with great accuracy and efficiency as they are paramount in prognosis and subsequent diagnosis of the condition of the patient. The goal of this project is to analyze the ECG signals following Fourier and Wavelet transforms, and to highlight and demonstrate the advantages of the Wavelet transform. Firstly, it involves simulating the temporal digital ECG signal and explaining the signal constituents, i.e., P, Q, R, S, T waves while staying in the time domain. Secondly, the ECG signal will be transferred into the frequency domain for quick, fast, and compressed analysis and carry out signal processing using Fourier analysis and highlight the pros and cons of this technique. Thirdly, wavelet analysis will be explored and demonstrated to mitigate the shortcoming of the former tool, i.e., Fourier. At this stage, various ECG signals, mimicking abnormalities, will be analyzed. This work will highlight the effectiveness of wavelet analysis as a tool to examine ECG signals. This work, hence, will entail, comparison of both transformation methods by utilizing the computational power of MATLAB.

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 Adaptive Symlet filter based on ECG baseline wander removal

2020 ◽  
Vol 17 (2) ◽  
pp. 187-197
Author(s):  
Ali Nahar
Keyword(s):  
Wavelet Transform ◽  
Adaptive Filter ◽  
Reference Signal ◽  
Low Frequency ◽  
Noise Removal ◽  
Ecg Signal ◽  
Computing Technique ◽  
Ecg Signals ◽  
Computation Process ◽  
Approximation Coefficients

In this paper, proposed a new approach of combining the hybrid soft computing technique called Adaptive Symlet Wavelet Transform (ASWT) filter. The baseline wanders (BW) noise removal from an ECG signals to minimize distortion of the S-T segment of the ECG signal specially that have high sampling frequencies. Therefore, when using Symlet Wavelet Transform (SWT) to analysis the ECG signal can cause problems to analysis, exclusively when examining the content of the ECG signal at low-frequency such as S-T segment. The corresponding frequency components of the approximation coefficients at level number seven are (0-3.9) Hz. Since the BW frequency is below 0.5 Hz and ST segment frequency between (0.67-4) Hz. The adaptive filter with a unity reference signal used to remove the BW noise below 0.5 Hz from the lowest level of the approximation coefficient of the decomposed ECG signal. The denoising output from adaptive filter and the output from SWT (the other detail coefficients) will use as an input to ISWT for reconstruction ECG signals with the remove BW signal. This method represents a very effective filter for BW noise removal, as it does not need for any computation process of reference point.

CLASSIFICATION OF CARDIAC ARRHYTHMIAS USING ARTERIAL BLOOD PRESSURE BASED ON DISCRETE WAVELET TRANSFORM

2017 ◽  
Vol 29 (05) ◽  
pp. 1750034 ◽  
Author(s):  
Roghayyeh Arvanaghi ◽  
Sabalan Daneshvar ◽  
Hadi Seyedarabi ◽  
Atefeh Goshvarpour
Keyword(s):  
Blood Pressure ◽  
Wavelet Transform ◽  
Discrete Wavelet Transform ◽  
Arterial Blood Pressure ◽  
Cardiac Arrhythmias ◽  
Support Vector ◽  
Discrete Wavelet ◽  
Ecg Signal ◽  
Arterial Blood

Early and correct diagnosis of cardiac arrhythmias is an important step in the treatment of patients. In the recent decades, a wide area of bio-signal processing is allocated to cardiac arrhythmia classification. Unlike other studies, which have employed Electrocardiogram (ECG) signal as a main signal to classify the arrhythmia and sometimes they have used other vital signals as an auxiliary signal to fill missing data and robust detections. In this study, the Arterial Blood Pressure (ABP) is used to classify six types of heart arrhythmias. In other words, in this study for first time, the arrhythmias are classified according ABP signal information. Discrete Wavelet Transform (DWT) is used to de-noise and decompose ABP signal. On feature extraction stage, three types of features including frequency, power, and entropy are extracted. In classification stage, Least Square Support Vector Machine (LS-SVM) is employed as a classifier. The accuracy, sensitivity, and specificity rates of 95.75%, 96.77%, and 96.32% are achieved, respectively. Currently, the classification of cardiac arrhythmias is based on the ABP signal which has some advantages. The recording of ABP signal is done by means of one electrode and therefore it has resulted in lower costs compared with the ECG signal. Finally, it has been shown that ABP has very important and valuable information about the heart performance and can be used in arrhythmia classification.

scholarly journals Adaptive Motion Artifact Reduction Based on Empirical Wavelet Transform and Wavelet Thresholding for the Non-Contact ECG Monitoring Systems

Sensors ◽  
2019 ◽  
Vol 19 (13) ◽  
pp. 2916 ◽  
Author(s):  
Xiaowen Xu ◽  
Ying Liang ◽  
Pei He ◽  
Junliang Yang
Keyword(s):  
Wavelet Transform ◽  
Heart Diseases ◽  
Motion Artifact ◽  
Motion Artifacts ◽  
Monitoring Systems ◽  
Ecg Signal ◽  
Wavelet Thresholding ◽  
Ecg Monitoring ◽  
Ecg Signals ◽  
Empirical Wavelet Transform

Electrocardiogram (ECG) signals are crucial for determining the health status of the human heart. A clean ECG signal is critical in analysis and diagnosis of heart diseases. However, ECG signals are often contaminated by motion artifact noise in the non-contact ECG monitoring systems. In this paper, an ECG motion artifact removal approach based on empirical wavelet transform (EWT) and wavelet thresholding (WT) is proposed. This method consists of five steps, namely, spectrum preprocessing, spectrum segmentation, EWT decomposition, wavelet threshold denoising, and EWT reconstruction. The proposed approach was used to process real ECG signals collected by the non-contact ECG monitoring equipment. The results of quantitative study and analysis indicate that this approach produces a better performance in terms of restorage of QRS complexes of the original ECG with reduced distortion, retaining useful information in ECG signals, and improvement of the signal to noise ratio (SNR) value of the signal. The output results of the practical ECG signal test show that motion artifact in the real recorded ECG is effectively filtered out. The proposed method is feasible for reducing motion artifacts from ECG signals, whether from simulation ECG signals or practical non-contact ECG monitoring systems.

ECG SIGNAL CODING USING BIORTHOGONAL WAVELET-BASED BURROWS–WHEELER CODER

2011 ◽  
Vol 09 (02) ◽  
pp. 269-281 ◽  
Author(s):  
R. SHANTHA SELVA KUMARI ◽  
R. SURIYA PRABHA ◽  
V. SADASIVAM
Keyword(s):  
Signal Processing ◽  
Wavelet Transform ◽  
Ecg Signal ◽  
Biorthogonal Wavelet ◽  
Time Frequency ◽  
Ecg Signals ◽  
Coding Efficiency ◽  
Frequency Representation ◽  
Mean Square Difference ◽  
Signal Coding

Wavelets are the powerful tool for signal processing especially bio-signal processing. Wavelet transform is used to represent the signal to some other time frequency representation better suited for detecting and removing redundancies. In this paper, electrocardiogram (ECG) signal coding using biorthogonal wavelet-based Burrows–Wheeler Coder is discussed. Biorthogonal wavelet transform is used to decompose the ECG signal. Then the Burrows–Wheeler Coder is applied in order to compress the decomposed ECG signal. The Burrows–Wheeler Coder is the combination of Burrows–Wheeler Transformation (BWT), Move-to-Front (MTF) coder and Huffman coder. Compression Ratio (CR) and Percent Root mean square Difference (PRD) are used as performance measures. ECG signals/records from MIT-BIH arrhythmic database are used to evaluate the performance of this coder. This algorithm is tested with 25 different records from MIT-BIH arrhythmia database and obtained the average PRD as 0.0307% to 3.8706% for the average CR of 3.6362 : 1 to 280.48 : 1. For record 117, the CR of 8.1638 : 1 is achieved with PRD 0.1652%. This experimental results show that this coder outperforms other coders such as Djohn, EZW, SPIHT, Novel algorithm etc. that exist in the literature in terms of coding efficiency and computation.

Sign in / Sign up

Export Citation Format

Share Document