Robust Design of Nonlinear Adaptive Hammerstein Filter Structure Using Evolutionary Algorithm: Real-Time Application to ECG Signals.

An automated ECG signal quality assessment method for unsupervised diagnostic systems

When we acquiring the Electrocardiogram (ECG) signal from the person, the signal amplitude (PQRST) and timing values are changes due to various artefacts. The different artefacts are Baseline wander, power line interference, muscle artefact, motion artefact and the channel noise also added sometimes during the transmission of the signal for diagnosis purpose. The adaptive filters play vital role for reduction of noise in the desired signals. In this paper we proposed, block based error normalized Recursive Least Square (RLS) adaptive algorithm and sign based RLS adaptive algorithm, which are used for reduction of muscle artifact noise and base line wander noise in the ECG signal. From the simulation result we analyzed that, comparing to Least Mean Square algorithm, the proposed RLS algorithm gives fast convergence rate with high signal to noise ratio and less mean square error. Index Terms—RLS Adaptive algorithms, Signal to noise ratio, artifacts, mean square error, ECG signal.

Automatic electrocardiogram (ECG) signal enhancement has become a crucial pre-processing step in most ECG signal analysis applications. In this Letter, the authors propose an automated noise-aware dictionary learning-based generalised ECG signal enhancement framework which can automatically learn the dictionaries based on the ECG noise type for effective representation of ECG signal and noises, and can reduce the computational load of sparse representation-based ECG enhancement system. The proposed framework consists of noise detection and identification, noise-aware dictionary learning, sparse signal decomposition and reconstruction. The noise detection and identification is performed based on the moving average filter, first-order difference, and temporal features such as number of turning points, maximum absolute amplitude, zerocrossings, and autocorrelation features. The representation dictionary is learned based on the type of noise identified in the previous stage. The proposed framework is evaluated using noise-free and noisy ECG signals. Results demonstrate that the proposed method can significantly reduce computational load as compared with conventional dictionary learning-based ECG denoising approaches. Further, comparative results show that the method outperforms existing methods in automatically removing noises such as baseline wanders, power-line interference, muscle artefacts and their combinations without distorting the morphological content of local waves of ECG signal.

The Electrocardiogram(ECG) signal is one of the bio-signals to check body status. Traditionally, the ECG signal was checked in the hospital. In these days, as the number of people who is interesting with periodic their health check increase, the requirement of self-diagnosis system development is being increased as well. Ubiquitous concept is one of the solutions of the self-diagnosis system. Zigbee wireless sensor network concept is a suitable technology to satisfy the ubiquitous concept. In measuring ECG signal, there are several kinds of methods in attaching electrode on the body called as Lead I, II, III, etc. In addition, several noise components occurred by different measurement situation such as experimenter's respiration, sensor's contact point movement, and the wire movement attached on sensor are included in pure ECG signal. Therefore, this paper is based on the two kinds of development concept. The first is the Zibee wireless communication technology, which can provide convenience and simpleness, and the second is motion artifact remove algorithm, which can detect clear ECG signal from measurement subject. The motion artifact created by measurement subject's movement or even respiration action influences to distort ECG signal, and the frequency distribution of the noises is around from 0.2Hz to even 30Hz. The frequencies are duplicated in actual ECG signal frequency, so it is impossible to remove the artifact without any distortion of ECG signal just by using low-pass filter or high-pass filter. The suggested algorithm in this paper has two kinds of main parts to extract clear ECG signal from measured original signal through an electrode. The first part is to extract motion noise signal from measured signal, and the second part is to extract clear ECG by using extracted motion noise signal and measured original signal. The paper suggests several techniques in order to extract motion noise signal such as predictability estimation theory, low pass filter, a filter including a moving weighted factor, peak to peak detection, and interpolation techniques. In addition, this paper introduces an adaptive filter in order to extract clear ECG signal by using extracted baseline noise signal and measured signal from sensor.

This study presents a simple electrocardiogram (ECG) signal analyzer for homecare system among the elderly. It can transmit ECG signals of patient around his/her house through Bluetooth to computers in house. ECG signals are analyzed by the computer. If abnormal case of heartbeat is found, the emergency call is automatically dialed. Meanwhile, the determined heartbeat case of ECG signals will be forwarded to patient's MD through internet. Therefore, the patient can do whatever he/she wants around his/her house with our proposed simple cardiac arrhythmias signal analyzer. The proposed consists of five major processing stages: (i) preprocessing stage for enlarging ECG signals' amplitude and eliminating noises; (ii) ECG signal transmitter/receiver stage, ECG signals are transmitted through Bluetooth to the signal receiver in patient's house; (iii) QRS extraction stage for detecting QRS waveform using the Difference Operation Method (DOM) method; (iv) qualitative features stage for qualitative feature selection on ECG signals; and (v) classification stage for determining patient's heartbeat cases using the Principal Component Analysis (PCA) method. In the experiment, the total classification accuracy (TCA) was approximately 93.19% in average.

Electrocardiogram (ECG) signals are significantly distorted during recording by muscle artifact (MA), causing signal frequency overlap and making it difficult to interpret ECG data correctly. Deep learning (DL) methods for signal processing have shown promising results. However, there is a significant necessity in building proper DL models with appropriate datasets. We propose an enhanced hybrid deep learning framework called HRGB-Net based on residual neural network (ResNet), global channel attention block (GCAB), and bidirectional-long-short-term memory (Bi-LSTM) blocks for filtering the MA noise from ECG by using three distinctive MIT-BIH real-time datasets from the PhysioNet repository by creating suitable datasets for training. We use both raw ECG data and short-time Fourier-transformed (STFT) ECG data for comparative analysis with three neural network models: a convolutional neural Network (CNN), a fully connected neural network (FCNN), and a regression-based LSTM (Reg-LSTM-DNN) model to assess the proposed model. The signal-to-noise ratio (SNR) of noisy ECG signals is varied from - 7dB to 2dB to analyze the mean square error (MSE) and correlation coefficient (CC) performances after the denoising process. Our proposed method utilizes the regression ability to remove MA noise and generate a clean ECG signal with improved values of these signal parameters. The STFT-trained and tested ECG data shows better results than the raw ECG data for efficiently eliminating the MA with a 98.82% correlation coefficient and optimal MSE value of 0.053068. The results prove our proposed HRGB-Net model's remarkable ability to outperform the neural network models and other standard techniques.

Electrocardiogram (ECG) is a graphical representation and bio-signal recording of cardiac electrical activity.It conveys a great amount of information regarding structural and functional performance of the heart.Hence, ECG plays an essential role in the cardiac assessment, abnormality detection and clinical diagnosis.A clean ECG signal plays an imperative and vital role in the primary clinical analysis and diagnosis of cardiac diseases.Unfortunately, the greatest obstacle in analyzing and interpreting an ECG signal is the presence of unwanted artifacts and noises as they contaminate and degrade the quality of the ECG signals.As a result, removal of unwanted artifacts and noises from an ECG signal becomes an indispensable task to ensure an accurate and reliable ECG analysis could be performed.In this study, many ECG noise reduction and enhancement methods based on various digital filter designs, as well as discrete wavelet transform with various mother wavelets, are modelled to investigate and benchmark their performance in term of Signal-to-Noise Ratio (SNR) and Root Mean Square Error (RMSE).This testing are based on ten randomly selected ECG datasets acquired from ECG-ID Database (ecgiddb) which available in PhysioNet.Based on structured qualitative and quantitative performance analysis, results conclude that the discrete wavelet transform with db8 as mother wavelet outperforms the Finite Impulse Response (FIR) and Infinite Impulse Response (IIR) digital filter designs in de-noising and enhancing a raw ECG signal with highest SNR value of 4.4148, at the same time achieve significant lowest RMSE value of 4.0767.This is due to the reason that discrete wavelet transform method has advantages in analyzing the ECG signal in both time and frequency domain, thus causing less distortion to ECG signal.

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.

Separating an information-bearing signal from the background noise is a general problem in signal processing. In a clinical environment during acquisition of an electrocardiogram (ECG) signal, The ECG signal is corrupted by various noise sources such as powerline interference (PLI), baseline wander and muscle artifacts. This paper presents novel methods for reduction of powerline interference in ECG signals using empirical wavelet transform (EWT) and adaptive filtering. The proposed methods are compared with the empirical mode decomposition (EMD) based PLI cancellation methods. A total of six methods for PLI reduction based on EMD and EWT are analysed and their results are presented in this paper. The EWT-based de-noising methods have less computational complexity and are more efficient as compared with the EMD-based de-noising methods.

Electrocardiogram (ECG) signals are usually contaminated by numerous artefacts during the recording process, and the quality of physiological information related to the heart is compromised. Due to this, artefact cancellation has become necessary for ECG signals. In this paper, swarm intelligence-based optimally tuned adaptive noise cancellers (ANCs) have been proposed and applied to denoise the ECG signal. The results have been analysed both qualitatively and quantitatively for noise cancellation from ECG signals through the ANCs optimized by using the seagull optimization algorithm (SOA), the Neighbourhood-based lineal population size success history-based adaptive differential evolution (NLSHADE) algorithm and the hyperbolic gravitational search algorithm (HGSA). The performance of the proposed methodology has been validated by using the additive white Gaussian noise at a diverse signal-to-noise ratio (SNR) on two publicly available datasets of ECG signal from the arrhythmia database (ADB) and QT ECG database (QTDB). The reference noise for ANC was considered using the noise stress test database (NSTDB). The performance of SOA-assisted ANC has been tested with the help of the Wilcoxon signed-rank test. The proposed technique-based ANCs supplied an enhanced percentage root mean squared deviation (PRD) value of 3.40E-03, mean squared error (MSE) value of 1.35E-11 and mean SNR improvement of 10.986 dB as compared to the reported state-of-the-art methods along with the benchmark competent algorithms, namely NLSHADE and HGSA.

Introduction: The precise interpretation of the Electrocardiogram (ECG) signal can reveal the condition of the heart. Health Monitoring (HM)-ECG signal analysis can assist in identifying any abnormalities or arrhythmias in the heart with the detection of an R peak in the ECG signal. The following issues are not handled by the conventional algorithm for R peak detection: noise from muscle artifacts, power line interference and baseline drift, and variability in ECG waveforms brought on by pathological abnormalities. Methodology: This research proposes a robust approach for detecting R peaks in QRS complexes using a recurrent neural network. Our proposed methodology was applied to the well-known MITBIH Arrhythmia Database (MIT-DB) dataset and the China Physiological Signal Challenge (2020) database, which contains over a million beats. The hybrid linearization technique used an adaptive filter and Discrete Wavelet Transform (DWT) to remove noise from the ECG signal. The next step was to use principal component analysis (PCA) to extract characteristics from the ECG data. Lastly, the R peak signals were classified using Long Short-Term Memory (LSTM) to improve accuracy through optimization techniques like Grey Wolf Optimization (GWO). The algorithm';s performance was also evaluated using the MIT-BIH Arrhythmia database and the China Physiological Signal Challenge (2020). Results: The suggested formal technique yielded the best results for R-peak detection on CPSC- DB, with an F1-score of 95.3%, recall of 96.8%, accuracy of 99.5%, and precision of 95.3%. Conclusion: The F1-score, recall, and precision of the algorithms on MIT-DB are all equivalent to, or better than, those of the competing methods.

Although cascaded multistage adaptive noise cancellers have been employed before by researchers for multiple artifact removal from the ElectroCardioGram (ECG) signal, they all used the same adaptive algorithm in all the cascaded multi-stages for adjusting the adaptive filter weights. In this paper, we propose a cascaded 4-stage adaptive noise canceller for the removal of four artifacts present in the ECG signal, viz. baseline wander, motion artifacts, muscle artifacts, and 60 Hz Power Line Interference (PLI). We have investigated the performance of eight adaptive algorithms, viz. Least Mean Square (LMS), Least Mean Fourth (LMF), Least Mean Mixed-Norm (LMMN), Sign Regressor Least Mean Square (SRLMS), Sign Error Least Mean Square (SELMS), Sign-Sign Least Mean Square (SSLMS), Sign Regressor Least Mean Fourth (SRLMF), and Sign Regressor Least Mean Mixed-Norm (SRLMMN) in terms of Signal-to-Noise Ratio (SNR) improvement for removing the aforementioned four artifacts from the ECG signal. We employed the LMMN, LMF, LMMN, LMF algorithms in the proposed cascaded 4-stage adaptive noise canceller to remove the respective ECG artifacts as mentioned above. We succeeded in achieving an SNR improvement of 12.7319 dBs. The proposed cascaded 4-stage adaptive noise canceller employing the LMMN, LMF, LMMN, LMF algorithms outperforms those that employ the same algorithm in the four stages. One unique and powerful feature of our proposed cascaded 4-stage adaptive noise canceller is that it employs only those adaptive algorithms in the four stages, which are shown to be effective in removing the respective ECG artifacts as mentioned above. Such a scheme has not been investigated before in the literature.

An efficient ECG signals denoising technique based on the combination of particle swarm optimisation and wavelet transform

For wearable electrocardiogram (ECG) acquisition, it was easy to infer motion artifices and other noises. In this paper, a novel end-to-end ECG denoising method was proposed, which was implemented by fusing the Efficient Channel Attention (ECA-Net) and the cycle consistent generative adversarial network (CycleGAN) method. The proposed denoising model was optimized by using the ECA-Net method to highlight the key features and introducing a new loss function to further extract the global and local ECG features. The original ECG signal came from the MIT-BIH Arrhythmia Database. Additionally, the noise signals used in this method consist of a combination of Gaussian white noise and noises sourced from the MIT-BIH Noise Stress Test Database, including EM (Electrode Motion Artifact), BW (Baseline Wander) and MA (Muscle Artifact), as well as mixed noises composed of EM+BW, EM+MA, BW+MA and EM+BW+MA. Moreover, corrupted ECG signals were generated by adding different levels of single and mixed noises to clean ECG signals. The experimental results show that the proposed method has better denoising performance and generalization ability with higher signal-to-noise ratio improvement (SNRimp), as well as lower root-mean-square error (RMSE) and percentage-root-mean-square difference (PRD).

As the basic tool for the diagnosis of cardiac diseases, electrocardiogram (ECG) is often contaminated by muscle artifacts, which can cause unreliable interpretation and measurement for ECG. To adequately remove muscle artifacts which contaminate ECG signals, we propose a novel computation framework combining the convolution auto-encoder (CAE) and average beat subtraction in this paper. Firstly, the framework subtracts from the original ECG signal based on an initial average beat, which preserves the characteristics of a heart beat; the average beat is updated according to the original ECG signal to incorporate inter-beat variations. Then, the framework filters the residual ECG signal by a convolution auto-encoder (CAE), which filters out the contaminated parts and keeps the specific information related to the ECG signal. Finally, we combine the filtered residual ECG signal and updated average beat to obtain an enhanced ECG signal. Our framework is evaluated on ECG records from the MIT-BIH Arrhythmia Database, and results show that our framework outperforms existing methods in muscle artifacts removal.