A comparative analysis of ECG denoising methods

In recent years, Electrocardiogram (ECG) plays an imperative role in heart disease diagnostics, Human Computer Interface (HCI), stress and emotional states assessment, etc. In general, ECG signals affected by noises such as baseline wandering, power line interference, electromagnetic interference, and high frequency noises during data acquisition. In order to retain the ECG signal morphology, several researches have adopted using different preprocessing methods. In this work, the stroop color word test based mental stress inducement have done and ECG signals are acquired from 10 female subjects in the age range of 20 years to 25 years. We have considered the Discrete Wavelet Transform (DWT) based wavelet denoising have incorporated using different thresholding techniques to remove three major sources of noises from the acquired ECG signals namely, power line interference, baseline wandering, and high frequency noises. Three wavelet functions (db4, coif5 and sym7) and four different thresholding methods are used to denoise the noise in ECG signals. The experimental result shows the significant reduction of above considered noises and it retains the ECG signal morphology effectively. Four different performance measures were considered to select the appropriate wavelet function and thresholding rule for efficient noise removal methods such as, Signal to Interference Ratio (SIR), noise power, Percentage Root Mean Square Difference (PRD) and finally periodogramof Power Spectral Density (PSD). The experimental result shows the coif5 wavelet andrigrsurethresholding rule is optimal for unknown Signal to Noise Ratio (SNR) in the real time ECG signals.

<title>Abstract</title> Electrocardiogram (ECG) signals are critical to identify various cardiac abnormalities. However, the accuracy of ECG-based clinical interpretations can be significantly compromised due to contamination from various artifacts. Traditional ECG denoising methods often struggle to maintain the balance between noise suppression and preservation of essential ECG characteristics. This study presents, for the first time, a deep learning (DL)-based autoencoder (AE) for robust ECG denoising and artifact cancellation and automated ECG diagnosis and classification. Unlike traditional methods, AEs are designed to learn efficient data representations, making them well-suited for distinguishing between clean signals and noise without extensive computational demands. The proposed approach leverages the PTB Diagnostic ECG Database (PTBdb) and introduces various types of noise derived from the MIT-BIH Noise Stress Test Database, including muscle artifacts (MA), electrode motion artifacts (EM), baseline wander (BW), and their combinations. The proposed AE model is trained to eliminate these noise components effectively while preserving the critical morphological features of the ECG signals. To assess the performance of the introduced method, comprehensive experiments are performed to compare clean, noisy, and AE denoised ECG signals. The AE's performance is further benchmarked against classical denoising techniques, assessing key metrics such as signal to noise ratio (SNR), mean square error (MSE), root mean square error (RMSE) and a percent root-mean square difference (PRD). The results elucidate that the introduced AE-based denoising framework not only outperforms conventional techniques in noise suppression but also enhances the reliability of ECG signal interpretation, making it an effective solution for implementation in clinical settings.

Electrocardiogram (ECG) signal recording is a challenging task in the field of biomedical engineering. ECG is the cardiac recording of systematic electrical activity arising from the electro-physiological rhythm of the heart muscle. But, during processing, the ECG signal is contaminated with different types of noise in the medical environment. An immense task is the separation of the preferred signal from noises caused by artifacts like muscle noise, power line interference (PLI), baseline wandering (BW), and motion artifacts (MA). Hence, our paper focuses on 50 Hz PLI which is a major artifact/noise affecting the recorded ECG signal. This paper comprehensively reviews fundamental concepts of different denoising techniques. Some of the pioneers’ works are also concisely explained in the paper. Further, in this work, comparative analysis is carried out using notch filter, adaptive filter, discrete wavelet transform (DWT) and empirical mode decomposition (EMD) for filtering 50 Hz PLI noise. A considerable improvement in signal-to-noise ratio (SNR) can be observed from the results when compared with SNR input and SNR output values. Performance comparisons of all the four techniques are also analyzed based on variations in noise frequency. The simulations were carried out in the environment of MATLAB 2019b®. This work epitomizes the significance of our quantitative evaluation, in which adaptive filters are found to perform better with respect to the SNR, whereas DWT performs better with assessment of mean square error (MSE).

Electrocardiogram (ECG) signal enhancement is necessary in telemedicine. In such ECG monitoring systems, noises like muscle artifacts, electrode motion and baseline wander are often embedded in the ECG signals during acquisition and transmission. In this study, a novel method is proposed for the ECG signal enhancement based on the finding that ECG signals extracted over a big data share significant similarities in the morphology for a particular person. We construct a guided filter and reform it by a Butterworth high-pass filter. The Butterworth high-pass filter is utilized to remove the baseline wander. The advantageous edge-preserving guided filter is then applied to remove the rest noise, of which frequencies are between the ECG signals. Very promising results with high accuracy and the edge-preserving features have been achieved in the comparative experiments. We evaluated the proposed denoising method using ECG signals from the MIT-BIH Arrhythmia database and the Noise Stress Test database. The experimental results demonstrate that the proposed method achieves better signal-to-noise ratio (SNR) and lower root mean square error (RMSE) when compared to the wavelet with subband dependent thresholding (WT-Subband), Back Propagation Neural Network and Stockwell transform methods. Using the proposed method, the average output SNR ranges from 8.57 to 19.28 dB, and the average RMSE is less than 0.41.

In this paper, we propose a novel ECG signal enhancement method based on Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Higher Order Statistics (HOS). In our scheme, the noisy ECG signal is first decomposed adaptively into oscillatory components called intrinsic mode functions (IMFs) by using Empirical Mode Decomposition (EMD) or its variants. Therefore, the obtained modes are separated into two groups of noisy signal modes and one group of useful signal modes, by using a novel criterion derived from the HOS namely the fourth order cumulant or kurtosis. After that, a modified shrinkage scheme based on Interval Thresholding technique is adaptively applied to each selected IMF from the noise-dominant groups in order to reduce the noise and to preserve the QRS complex. The overall filtered ECG signal is then reconstructed by combining the thresholded IMFs and the retained unprocessed lower frequency relevant IMFs. Various tests and simulations are investigated to evaluate the performance of our proposed approach in combination with the EMD, Ensemble EMD (EEMD) and CEEMDAN algorithms. The simulation results carried on MIT-BIH Arrhythmia database, show that CEEMDAN method gives better performance than the two other methods, and outperforms some state-of-the-art methods in terms of Signal to Noise Ratio (SNR) and Root Mean Square Error (RMSE).

Electrocardiogram (ECG) signals are crucial for monitoring cardiac activity and diagnosing various cardiovascular conditions. However, these signals are often contaminated by different types of noise, such as baseline wander, muscle artifacts, and power line interference, which can obscure critical information and hinder accurate diagnosis. This study used a 1-Dimensional Convolutional Neural Network (1D CNN) architecture with seven convolutional layers for denoising ECG signals. The model utilizes a fully convolutional autoencoder approach, comprising an encoder that transforms noisy input signals into compact feature representations and a decoder that reconstructs the cleaned signals. The proposed architecture was tested using the MIT-BIH Noise Stress Test Database, which includes ECG recordings with simulated noise conditions. Performance evaluation metrics such as Mean Squared Error (MSE), Signal-to-Noise Ratio (SNR), and Mean Absolute Deviation (MAD) were used to assess the model's effectiveness. Results showed a low MSE of 0.034, a high SNR of 15.8 dB, and a MAD of 0.754, indicating significant noise reduction and high-quality signal reconstruction. These findings demonstrate that the 1D CNN architecture effectively reduces various types of noise in ECG signals, thereby enhancing signal quality and facilitating more accurate analysis and diagnosis. The model's ability to maintain the integrity of crucial ECG features while removing noise suggests its potential utility in clinical applications for improving cardiovascular disease diagnosis

Many studies have been devoted to the adaptive power-line interference (PLI) filter design for ECG signal processing. However, almost all existing PLI suppression filters are developed for applications in which the presence of PLI noise is assumed a priori. Indiscriminate application of PLI suppression over an ECG signal that is free of PLI noise may deform ECG morphology, and even cause degraded performance of subsequent processing. To date, little work has been done on the possibility of ECG signal degradation by such filtering operation and the impact on further processing. In order to evaluate the difference between the original and the filtered pattern, this study proposes quantitative evaluation measures. The assessments include convergence time, the frequency tracking efficiency, the execution time and the relative statistics in time and frequency domain. Extensive experiments have been done with artificially and practically corrupted ECG signals for four existing PLI adaptive filtering techniques (Ahlstrom and Tompkinspsila, Pei and Tsengpsilas, Sopsilas and Ziarani and Konradpsilas algorithm). The results reveal that ECG signal distortion resulted from these existing adaptive filters. None of the existing algorithms outperform the others in all assessments. The proposed evaluation measures can also be used for the performance evaluation of the other types of artifact suppression, such as the baseline wander and EMG corruption contaminated in ECG, after minor modification. The proposed measures also make the optimal filter design under different constraints possible for ECG signal processing.

In this paper, a new optimization on windowing technique based on finite impulse response (FIR) filters is proposed for revealing and evaluating the Influence of filters position in cascaded filter tested on the ECG signal de-noising. baseline wander (BLW), power line interference (PLI) and electromyography (EMG) noises are getting removed. The performance of the adopted method is evaluated on the PTB diagnostic database. Subsequently, the comparisons are based on signal to noise ratio (SNR) improvement and mean square error (MSE) minimization. Where the Rectangular, and Kaiser windows have been used for the more potent performances. The disparity average (DA) of SNR values is detected; in both Kaiser and Rectangular windows are assessed by ±0.38046dB and ±0.70278dB respectively, while the MSE values were constant. The excellent configuration or filters position (H-B-L) of the filtration system is selected according to high measurements of SNR and low MSE too, to de-noise the ECG signals. First of all, this applied approach has led to 31.30 dB SNR improvement with MSE minimization of 26. 43%. This means that there is a significant contribution to improving the field of filtration.

Baseline wander and power line interference removal from ECG signals using eigenvalue decomposition

Electroencephalogram (EEG) is bioelectric signal, which represents the brain activity and usually contaminated with artifacts due to movements of eye, heart, muscles and power line interference. Among these, artifacts due to Ocular Activity make the analysis difficult. This paper presents a new threshold for the removal of Ocular Artifacts (OA) from single channel EEG based on Empirical Mode Decomposition (EMD) inspired by Wavelet Thresholding that yields a relatively cleaner EEG signals. Unlike the conventional EMD based EEG denoising techniques, that neglects the higher order low frequency Intrinsic Mode Functions (IMFs) EMD Interval Thresholding (EMD-IT) and Iterative EMD Interval Thresholding (EMD-IIT) is opted to correct the artifacts. Computations are carried out using EEG Motor Movement/Imagery (eegmmidb) dataset and compare the performance of Proposed Threshold (PT) with current threshold functions i.e., Universal Threshold (UT) and Statistical Threshold (ST) using several standard performance metrics: Change in SNR (ΔSNR), Artifact Rejection Ratio (ARR), Correlation Coefficient (CC) and Root Mean Square Error (RMSE). Results of these studies reveal that the EMD-IT with PT can effectively remove the OAs from EEG signals and maintaining the background neural activity in non artifact zones intact in contrast with those of existing ones.

Background:Electrocardiogram (ECG) plays a vital role in the analysis of heart activity. It can be used to analyze the different heart diseases and mental stress assessment also. Various noises, such as baseline wandering, muscle artifacts and power line interface disturbs the information within the ECG signal. To acquire correct information from ECG signal, these noises should be removed.Methods:In the proposed work, the improved variational mode decomposition (IVMD) method for the removal of noise in ECG signals is used. In the proposed method, the weighted signal amplitude integrated over the timeframe of the ECG signal varies the window size during decomposition. Raw ECG data are extracted from 10 subjects and ECG data are also taken from the MIT BIH database for the proposed method.Results:The performance comparison of traditional variational mode decomposition (VMD) and the proposed technique is also calculated using mean square error, percentage root mean square difference, signal to noise ratio and correlation coefficient. The extracted highest signal to noise ratio (SNR) value of acquired ECG signals using traditional VMD is 42db whereas highest value of signal to noise ratio (SNR) using improved VMD (IVMD) is 83db.Conclusion:The proposed IVMD technique represented better performance than traditional VMD for denoising of ECG signals.

Filtering of surface EMG using ensemble empirical mode decomposition

High-density surface electromyogram (HD-sEMG) undertakes the task of detecting the activity of motor units (MUs). However, its recordings are often mixed with power line interference and its harmonics (PLI), white Gaussian noise (WGN), baseline wandering (BW), and motion artifact (MA). The poor signal-to-noise ratio (SNR) is an obstacle for clinical applications. The surface electromyogram (sEMG) preprocessing technology rarely considers the diversity and specificity of noise, that is, the algorithm is only for a certain type of noise or only uses one method to deal with all kinds of noise. In this article, we propose a method based on variational mode decomposition (VMD) to specifically remove these four types of noise, which makes full use of the characteristics of noise. A variance-dependent adaptive parameter optimization method was proposed for PLI and WGN removal, and the higher-order statistics (HOS) were further used to adaptively suppress WGN without reference signals. The method was first evaluated using simulated data and then experimentally validated on three different databases involving not only healthy subjects but also amputees, specifically in comparison with previous methods. Both simulated and experimental results showed that the proposed method was significantly superior to the traditional methods (Wilcoxon signed-rank test, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${p} \lt 0.001$ </tex-math></inline-formula>). It resulted in 14.11%, 59.71%, and 5.76%, better than traditional methods on the three experimental databases, respectively. Our proposed method has positive implications for sEMG-based or HD-sEMG-based human-robot interfaces.

Automated detection and classification of electrocardiogram (ECG) noise sources can play a crucial role in reliable measurement of ECG parameters for accurate diagnosis of cardiovascular diseases (CVDs) under unsupervised telehealth monitoring and intensive care unit (ICU) applications. Although the methods had quite acceptable detection rates, most methods are too complicated for real-time implementation for wearable cardiac health monitoring devices. Therefore, in this paper, we present a low-complexity algorithm for automatically detecting and classifying the ECG noises including flat line (FL), time-varying noise (TVN), baseline wander (BW), abrupt change (ABC), muscle artifact (MA) and power line interference (PLI). The proposed method is based on the moving average (MAv) and derivative filters and the five temporal features including turning points, global and local amplitude estimates, zerocrossing and autocorrelation peak values. The proposed method is tested and validated using a wide variety of clean and noisy ECG signals taken from the MIT-BIH arrhythmia database and Physionet Challenge database. The method achieves an average sensitivity (Se) of 98.55%, positive productivity (+P) of 95.27% and overall accuracy (OA) of 94.19% for classifying the noises. Results show that the proposed method outperforms the other existing methods.

In this paper several variable step size adaptive filter structures for extracting high resolution electrocardiographic (ECG) signals are presented which estimates the deterministic components of the ECG signal and removes the artifacts. The noise canceller minimizes the mean square error (MSE) between the input noisy ECG signal and noise reference. Different noise canceller structures are proposed to remove diverse forms of artifacts: power line interference, baseline wander, muscle artifacts and electrode motion artifacts. The proposed implementation is suitable real time applications, where large signal to noise ratios with fast convergence are required. Simulation studies shows that the proposed realization gives better performance compared to existing realizations in terms of signal to noise ratio, convergence rate and MSE.