Search

Electrocardiogram (ECG) paper records are used commonly for diagnosing heart abnormalities. The stored ECG paper records are recorded on thermal paper and may face ink evaporation problem over the time. Generally, to overcome this problem ECG paper record is scanned and stored as an image. However, the addition of noise during scanning such as low resolution scan, blurring, folding of paper, nonuniform lighting, orientation etc. can create difficulty in information retrieval. Current work robustly handles various degradation problems encountered in ECG paper scanning using modified k-fill algorithm. The proposed algorithm is tested with 836 ECG paper recordings with different types of degradations like aging effect, folding effect, ink evaporation effect, blurring effect and low resolution effect. We extracted clinically important parameters such as heart rate etc. with accuracy of 97.33% and abnormalities such as bradycardia, tachycardia, and atrial flutter from the ECG paper records using perceptual spectral centroid method. Overall accuracy of our prediction algorithm was found out to be 98.6%. We assume our work would be low cost, preliminary expert mechanism at rural places in the absence of expert cardiologist. [ABSTRACT FROM AUTHOR]

In this paper, the pre-processing of ECG signal is studied. Firstly, the traditional digital filter is introduced and analyzed. Secondly, the mathematical morphological filter is studied and simulated with MATLAB software. Finally, the simulation results show that the digital morphological filter can remove the baseline drift, myoelectric interference and noise well, and retain the useful information in the ECG waveform. [ABSTRACT FROM AUTHOR]

Stress is a common experience with significant impacts on our health, which has sparked an increase in research aimed at detecting stress. This paper explores the effectiveness of using Electrocardiogram (ECG) signals as a key indicator for stress detection. What distinguishes our research is the carefully constructed architecture of our deep neural network model, coupled with the meticulous optimization strategies employed. We trained and evaluated our model using the comprehensive WESAD[10] dataset, which includes PANAS[10] self-reports. Our proposed model demonstrates remarkable improvements in accuracy and F1 score compared to previous attempts, highlighting the potential of deep learning techniques in understanding and predicting stress levels based on physiological data and harness its power to offer an objective measure of the body's response to stress. The results of the DeepChill demonstrate the effectiveness of the deep learning model in detecting stress from ECG signals, highlighting its potential for health monitoring and intervention. This contributes to the field of affective computing by providing a reliable and efficient method for stress detection. The proposed fully connected neural network model has attained an impressive accuracy of 92% surpassing the 85% accuracy reported on the WESAD dataset. [ABSTRACT FROM AUTHOR]

Cardiac arrhythmias are abnormalities caused by irregularities in the heart's electrical conduction system. Cardiovascular diseases (CVD) have been identified as the leading cause of death worldwide. Premature ventricular contraction (PVC) is one of these diseases. It is an arrhythmia that can be linked to a several heart diseases that affect between 40% and 75% of the population. Ventricular bigeminy occurs when one or two premature beats are detected on an electrocardiogram when there is ventricular contraction between two normal heartbeats or trigeminy. The appearance of ventricular bigeminy or trigeminy rhythms is related to angina. Myocardial infarction, hypertension, and congestive heart failure are also possible conditions. Based on deep learning, this paper proposes creating a robust approach for automatically detecting and classifying cardiovascular arrhythmias in long-term electrocardiogram (ECG) recordings from halters based on deep learning (DL). We present a convolutional neural network (CNN) and long-short-time memory (LSTM) model that identifies cardiovascular arrhythmias. We have designed and implemented the proposed model using Python. The model was trained and validated on a database that includes a total of 17 long-recorded ECG signals (24 h) from 17 subjects, which were obtained from Yfa Hospital. The signals were recorded with seven leads holter. The CNN classifier achieved an accuracy of 91.14% as a final result, validated through a 10-fold cross-validation. Moreover, the proposed model was found to be capable of analyzing ECG recordings to classify multiple cardiovascular arrhythmias in the ECG record signals efficiently. [ABSTRACT FROM AUTHOR]

This paper presents a novel model for arrhythmia detection based on a cascading technique that utilizes a combination of the One-Sided Selection (OSS) method, Support Vector Machine (SVM), and K-Nearest Neighbor (KNN) algorithms, this model denoted by (OWSK) model to classify four types of electrocardiogram (ECG) heartbeats following inter-patient scheme. The OWSK model consists of three stages. The first stage involves resampling using the One-Sided Selection (OSS) method to solve the imbalance problem and reduce data by removing noisy, borderline, and redundant samples. The second stage involves using Wavelet Transformation (WT) and Power Spectral Density (PSD) to extract the most relevant frequency domain features. The third stage involves a cascading process by constructing the classifier from SVM trained on the whole dataset to classify normal and abnormal beats. Then, KNN (K-Nearest Neighbors) is trained on only the three irregular minority classes to classify the three types of arrhythmias for the detection of ventricular ectopic beats, supraventricular ectopic beats, and fusion beats (V, S, and F). The performance of the proposed model is evaluated in terms of different metrics, including accuracy, recall, precision, and F1 score. The results show the superiority of the proposed model in medical diagnosis compared to the latest works, where it achieves 90%, 90%, 93%, and 91% for accuracy, recall, precision, and F1 score under the inter-patient paradigm and 98%, 98%, 98%, and 98% under the intra-patient paradigm. [ABSTRACT FROM AUTHOR]

School-based cardiac screening is useful for identifying children and adolescents with a high risk of sudden cardiac death. However, because of challenges associated with cost, distance, and human resources, cardiac screening is not widely implemented, especially in rural areas with limited medical resources. This study aims to establish a cloud-based system suitable for mass cardiac screening of schoolchildren in rural areas with limited medical resources. Students from three schools were included. They or their guardians completed a simple questionnaire, administered in paper or electronic form. Heart sounds were recorded using an electronic stethoscope. Twelve-lead electrocardiograms (ECGs) were recorded and digitalized. The signals were transmitted through Bluetooth to a tablet computer and then uploaded to a cloud server over Wi-Fi. Crowdsourced pediatric cardiologists reviewed those data from a web-based platform and provided remote consultation. In cases in which abnormal heart sounds or ECGs were noted, the students were referred to the hospital for further evaluation. A total of 1004 students were enrolled in this study. Of the 138 students referred, 62 were diagnosed as having an abnormal heart condition and most had previously been undiagnosed. The interrater agreeability was high. An innovative strategy combining a cloud-based cardiac screening system with remote consultation by crowdsourced experts was established. This system allows pediatric cardiologists to provide consultation and make reliable diagnoses. Combined with crowdsourcing, the system constitutes a viable approach for mass cardiac screening in children and adolescents living in rural areas with insufficient medical resources. [ABSTRACT FROM AUTHOR]

The electrocardiogram (ECG) signal is commonly used to screen and diagnose cardiovascular diseases. In recent years, deep neural networks have been regarded as an effective way for automatic ECG disease diagnosis. The convolutional neural network is widely used for ECG signal extraction because it can obtain different levels of information. However, most previous studies adopt single scale convolution filters to extract ECG signal features, ignoring the complementarity between ECG signal features of different scales. In the paper, we propose a dual-scale network with convolution filters of different sizes for 12-lead ECG classification. Our model can extract and fuse ECG signal features of different scales. In addition, different spatial and time periods of the feature map obtained from the 12-lead ECG may have different contributions to ECG classification. Therefore, we add a spatial-temporal attention to each scale sub-network to emphasize the representative local spatial and temporal features. Our approach is evaluated on PTB-XL dataset and achieves 0.9307, 0.8152, and 89.11 on macroaveraged ROC-AUC score, a maximum F1 score, and mean accuracy, respectively. The experiment results have proven that our approach outperforms the baselines. [ABSTRACT FROM AUTHOR]

One of sleep-disordered breathing (SDB) form is sleep apnea, commonly known as snoring during sleep, based on various complex mechanisms and predisposing factors. Sleep apnea is also related to various medical problems. It impacts morbidity and mortality so that it becomes a burden on public health services. Its detection needs to be done correctly through electrocardiogram signals to detect sleep apnea more quickly and precisely. This study was conducted to detect sleep apnea based on electrocardiogram signals using multi-scale entropy analysis. Multi-scale entropy (MSE) is used in a finite length of time series for measuring the complexity of the signal. MSE can be applied to both physical and physiological data sets and. In this paper we used MSE to detect Sleep Apnea on electrocardiogram (ECG) signals. MSE was applied two classes of ECG data, normal ECG signals, and apnea ECG signals. In this paper, classification and verification were carried out using the Support Vector Machine (SVM) and N-fold cross-validation (N-fold CV). From the experimental results, the highest accuracy was 85.6% using 5-fold CV and MSE scale of 10. The result shows that the system model that can detect sleep using the multi-scale entropy method. [ABSTRACT FROM AUTHOR]

In this paper, as a new application of machine learning, a K- Nearest Neighbor (KNN) classification model is proposed to recognize artifacts in Electrocardiography (ECG) signal using 3-axis accelerometer signals. A fine KNN model using wavelet scattering coefficients as features of 3-axis accelerometer sensor captured training dataset have been proposed as alternative to other machine learning methods to classify artifacts. In wearable health-monitoring devices, artifact noise results signal deformations and it is not possible to employ filtering methods all the time due to data loss. As a result, wearable ECG monitoring devices are not reliable for critical medical usages. Our proposed model classifies accelerometer sensor samples with high probability of having artifact noises in ECG signal with positive predictive value of 94.7%. High accuracy rate of the proposed model in this work gives it an opportunity to be employed in ECG monitoring wearable devices to capture patients ECG history and labeling artifact samples for noise filtration or signal reconstruction systems to cancel the noise without having signal deformations. [ABSTRACT FROM AUTHOR]

Biomedical technologies help countless patients in improving the quality of managing health. The latest trend in biomedical engineering includes tissue bioengineering, biosensors, enhanced bone regeneration; and bioinstrumentation. Electrocardiogram (ECG) a very popular tool in medical science records the electrical activity of the heart. Its interpretations & usefulness have created a revolution in Cardiology. It involves measuring the potential difference between two points or measuring the dipole moment of the heart when it contracts and relaxes. There are various noises present in the signal. In this paper, the authors have designed filters for the elimination of electromyography noise and baseline wander noise present in ECG signal. The filters are designed and simulated using various approaches namely operational amplifier, a two-stage operational amplifier (2SOA), an operational transconductance amplifier (gm amplifier). The theoretical values are evaluated and compared using simulated results. The theoretical and practical values agree with each other. Also, current amplifiers (2SOA and gm amplifier) results in better gain improvement in comparison to operational amplifier [ABSTRACT FROM AUTHOR]

A critical component of dealing with heart disease is real-time identification, which triggers rapid action. The main challenge of real-time identification is illustrated here by the rare occurrence of cardiac arrhythmias. Recent contributions to cardiac arrhythmia prediction using supervised learning approaches generally involve the use of demographic features (electronic health records), signal features (electrocardiogram features as signals), and temporal features. Since the signal of the electrical activity of the heartbeat is very sensitive to differences between high and low heartbeats, it is possible to detect some of the irregularities in the early stages of arrhythmia. This paper describes the training of supervised learning using features obtained from electrocardiogram (ECG) image to correct the limitations of arrhythmia prediction by using demographic and electrocardiographic signal features. An experimental study demonstrates the usefulness of the proposed Arrhythmia Prediction by Supervised Learning (APSL) method, whose features are obtained from the image formats of the electrocardiograms used as input. [ABSTRACT FROM AUTHOR]

The electrocardiogram (ECG) is immensely beneficial for diagnosing the arrhythmias that may lead to serious complications in the heart health. In this paper, the continuous wavelet transform (CWT) was used for electrocardiogram arrhythmias detection. The natural arrhythmias were: Supra-ventricular arrhythmias (SV), atrioventricular (AV) and Normocardia (NC) were chosen for detection as well as for testing the proposed method The Natural signals were taken from MIT-BIH database to be used for testing. The continuous wavelet transform was connected to the standard deviation (SD) and Shannon entropy (SE) for feature extraction stage. For classification a safe threshold has been suggested to discriminate between the different arrhythmias. Several combinations of the CWT application were testing. The wavelet packet transform was used for comparison. All combinations have given reasonable results, but continuous wavelet transform with standard deviation taken for the third sub signal have given the superior results. The results of our study will open the door for choosing the continuous transform for detection that has been neglected by the researchers for this task. [ABSTRACT FROM AUTHOR]

• End-to-end single-lead ECG diagnosis with high accuracy and efficiency. • Multi-scale convolutions and hybrid RNNS for multi-angle ECG insights. • Imbalanced clinical datasets: realistic data distribution. • Segmentation and recombination: for large-scale datasets with varying lengths. Arrhythmia is a prevalent cardiovascular disease that can unveil various heart health issues. In recent times, the rise of wearable devices has garnered attention towards the advantages of portable single-lead ECG devices in heart health monitoring. Achieving end-to-end ECG automatic diagnosis through deep learning is essential due to the time-consuming and labour-intensive characteristics of manual diagnosis of ECG records. This paper presents the design of a hybrid residual recurrent convolutional neural network (HRRCNN) for automatically diagnosing single-lead ECG with multiple labels. Firstly, the convolutional layers and residual networks extract the spatial and short-term temporal features. Subsequently, a hybrid recurrent neural network (RNN) comprised of a double-layer bidirectional gated recurrent unit (GRU) and a bidirectional long short-term memory (LSTM) is employed to capture long and short-term temporal features. Finally, an output layer, comprising an attention layer and a fully connected layer, converts the extracted features into classification results. To evaluate the performance of HRRCNN, a dataset from the Shanghai First People's Hospital Affiliated to Shanghai JiaoTong University(Shanghai General Hospital, SGH) is utilized. The experimental results demonstrate that HRRCNN achieves an accuracy of 95.08 %, F1-macro of 87.22 %, Sensitivity of 88.51 %, and a positive prediction rate of 86.13 %. Comparative analysis with existing methods underscores the superior performance of HRRCNN, thereby establishing its potential as an out-of-hospital heart health monitoring tool and an auxiliary tool in clinical settings. [ABSTRACT FROM AUTHOR]

Heart disease remains the main leading cause of death globally and around 50% of the patients died due to sudden cardiac death (SCD). Early detection and prediction of SCD have become an important topic of research and it is crucial for cardiac patient's survival. Electrocardiography (ECG) has always been the first screening method for patient with cardiac complaints and it is proven as an important predictor of SCD. ECG parameters such as RR interval, QT duration, QRS complex curve, J-point elevation and T-wave alternan are found effective in differentiating normal and SCD subjects. The objectives of this paper are to give an overview of SCD and to analyze multiple important ECG-based SCD detection and prediction models in terms of processing techniques and performance wise. Detail discussions are made in four major stages of the models developed including ECG data, signal pre-processing and processing techniques as well as classification methods. Heart rate variability (HRV) is found as an important SCD predictor as it is widely used in detecting or predicting SCD. Studies showed the possibility of SCD to be detected as early as one hour prior to the event using linear and non-linear features of HRV. Currently, up to 3 hours of analysis has been carried out. However, the best prediction models are only able to detect SCD at 6 minutes before the event with acceptable accuracy of 92.77%. A few arguments and recommendation in terms of data preparation, processing and classification techniques, as well as utilizing photoplethysmography with ECG are pointed out in this paper so that future analysis can be done with better accuracy of SCD detection accuracy. [ABSTRACT FROM AUTHOR]

In the recent years, error recovery circuits in optimized data path units are adopted with approximate computing methodology. In this paper the novel multipliers have effective utilization in the newly proposed two different 4:2 approximate compressors that generate Error free Sum (ES) and Error free Carry (EC). Proposed ES and Proposed EC in 4:2 compressors are used for performing Partial Product (PP) compression. The structural arrangement utilizes Dadda structure based PP. Due to the regularity of PP arrangement Dadda multiplier is chosen for compressor implementation that favors easy standard cell ASIC design. In this, the proposed compression idealogy are more effective in the smallest n columns, and the accurate compressor in the remaining most significant columns. This limits the error in the multiplier output to be not more than 2n for an n X n multiplication. The choice among the proposed compressors is decided based on the significance of the sum and carry signals on the multiplier result. As an enhancement to the proposed multiplier, we introduce two Area Efficient (AE) variants viz., Proposed-AE (P-AE), and P-AE with Error Recovery (P-AEER). The proposed basic P-AE, and P-AEER designs exhibit 46.7%, 52.9%, and 52.7% PDP reduction respectively when compared to an approximate multiplier of minimal error type and are designed with 90nm ASIC technology. The proposed design and their performance validation are done by using Cadence Encounter. The performance evaluations are carried out using cadence encounter with 90nm ASIC technology. The proposed-basic P-AEA and P-AEER designs demonstrate 46.7%, 52.9% and 52.7% PDP reduction compared to the minimal error approximate multiplier. The proposed multiplier is implemented in digital image processing which revealed 0.9810 Structural SIMilarity Index (SSIM), to the least, and less than 3% deviation in ECG signal processing application. [ABSTRACT FROM AUTHOR]

The paper examines the accuracy of classification performed by selected deep learning methods on a large number of ECG data streams. Specifically, it investigates the performance of two types of neural networks: the convolutional neural network (CNN) and residual neural network (ResNet). The results were compared with those obtained by the classic k-nearest neighbors (k-NN) approach. A number of significant signal and method-specific parameters were taken into account, like the duration of the signal examined, the distance between consecutive R waves, the analysis window, the number of learning epochs, etc. The investigation was performed on two data sets: PTB and MIT (Arrhythmia). [ABSTRACT FROM AUTHOR]

Electrocardiogram (ECG) is a diagnostic tool for cardiovascular disease in clinical medicine, but noisy ECG signals can easily lead to misdiagnosis. This paper presents a lightweight U-Net model (LUNet) for denoising and noise localization of ECG signals of varying lengths. The proposed model acts as a denoising autoencoder, which accepts an ECG signal containing noises and outputs the denoised signal. The locations of unacceptable noise are determined by comparing the difference between the input and output signals of the model. The proposed method for ECG signal denoising achieved Root Mean Square Error (RMSE) scores of 0.0116 ± 0.0016, 0.0149 ± 0.0033, 0.0122 ± 0.0015, and 0.0098 ± 0.0012 for baseline wander (BW), muscle artifacts (MA), electrode motion artifacts (EM), and Additive white Gaussian noise (AWGN), respectively. For ECG signal noise localization, the proposed method obtained high Intersection over Union (IoU) scores and Dice scores. Meanwhile, our model showed excellent generalization performance on two public ECG databases. On the 12-lead ECG arrhythmia classification task, the results using the processed dataset with the proposed method were 2.4% higher in F1 score than using the original dataset. The proposed method is highly effective in removing acceptable noise from ECG signals of varying lengths and locating the positions of unacceptable noise. This paper presents a promising solution for denoising and noise localization of ECG signals, which can improve ECG interpretation and potentially lead to better diagnosis and treatment of cardiovascular diseases. [ABSTRACT FROM AUTHOR]

To address the problems of the imbalanced datasets, limited computing power, and memory capability of wearable devices, this paper proposes a new hybrid method for imbalanced dataset mitigation and a novel lightweight Convolutional Neural Network (CNN) framework for electrocardiogram(ECG) signal classification. First, data enhancement method is used by changing the amplitude of a small number of samples and combining with the weighted loss function in the deep learning model. Then, One-Dimensional Convolutional Block Attention Module (1D_CBAM) mechanism autoencoder model is proposed to compress the ECG heartbeat signals and extract the features of the ECG heartbeats. A modified one-dimensional lightweight CNN model based on MobileNet architecture is eventually used to categorize various arrhythmias utilizing the above features. Using the MIT-BIH arrhythmia dataset, the proposed model is tested by dividing the MIT Database(MITDB) into Dataset1 and Dataset2, in conjunction with suggestions from AAMI and other heartbeat signal classification methods. The experimental results show that the proposed imbalanced dataset mitigation method has higher performance than other methods in this paper, the proposed model has the most stable convergence and the lowest reconstruction loss (approximately 0.1) in the feature extraction process under the same conditions. During the classification process, the lightweight CNN model has approximately 4x fewer trainable parameters(Params: 12,788) and its performance [Dataset1: F1-Score: 96.24% ACC: 98.21%; Dataset2: F1-Score: 98.73% ACC: 99.61%] is comparable to the traditional CNN model [Dataset1: F1-Score: 96.98% ACC: 99.17%; Dataset2: F1-Score: 99.18% ACC: 99.72%]. • We develop a new processing method for mitigating the imbalanced dataset. It contains the following two steps, the first step is data augmentation, and the second step is class weight optimization. • We propose a new data compression and coding model based on the autoencoder Algorithm. This method can be used to reconstruct the ECG signal while paying attention to the amplitude characteristic of the signal itself, as well as the correlations between the temporal and spatial position of ECG signals. • We design the lightweight CNN model based on MobileNet architecture to reduce the number of parameters and computations of the traditional CNN model. [ABSTRACT FROM AUTHOR]

• The proposed M aternal E CG- G uided Neural Net work (MEG-Net) integrates maternal ECG as a reference, enhancing fetal ECG extraction by providing spatial and temporal information about maternal ECG components. • This approach is particularly beneficial in challenging scenarios where fetal and maternal QRS complexes coincide. • MEG-Net is rigorously compared against other learning-based approaches and conventional abdominal electrode-sourced (AES) and combined sources (CS) methods, aiming to demonstrate its effectiveness and potential advantages in fetal ECG extraction. Historically, acquiring a reliable and accurate non-invasive fetal electrocardiogram has several significant challenges in both data acquisition and attenuation of maternal signals. These barriers include maternal physical/physiological parameters, hardware sensitivity, and the effectiveness of signal processing algorithms in separating maternal and fetal electrocardiograms. In this paper, we focus on the evaluation of signal-processing algorithms. Here, we propose a learning-based method based on the integration of maternal electrocardiogram acquired as guidance for transabdominal fetal electrocardiogram signal extraction. The results demonstrate that incorporating the maternal electrocardiogram signal as input for training the neural network outperforms the network solely trained using information from the abdominal electrocardiogram. This indicates that leveraging the maternal electrocardiogram serves as a suitable prior for effectively attenuating maternal electrocardiogram from the abdominal electrocardiogram. [ABSTRACT FROM AUTHOR]

• A novel hybrid adaptive framework for the extraction of fetal ECG is proposed. • FastICA extracts the maternal part and enhances the fetal part in abdominal ECG. • AEFLN cancels maternal ECG without any time and amplitude alignment. • Finally, NWT determines the exact fetal R-peak envelopes for FHR calculation. • Proposed framework attains 95.29% of SE, 96.68% of PPV, and 95.92% of F1 score. Continuous monitoring of fetal health requires the accurate calculation of the Fetal Heart Rate (FHR) by efficiently isolating fetal Electrocardiogram (fECG) from non-invasive abdominal Electrocardiogram (aECG). There are numerous solutions proposed for this problem, having its own restrictions. This paper introduces a novel three-stage hybrid adaptive approach for fECG extraction and FHR determination from aECG. The proposed framework is an amalgamation of independent component analysis (ICA), adaptive exponential functional link network (AEFLN), and novel wavelet thresholding (NWT). The proposed work aims to determine the best quality fetal R-peaks for calculating fetal heart rate (FHR). ICA is a blind source separation technique that uses all the information from the multichannel inputs to determine the maternal Electrocardiogram (mECG) and enhanced aECG. In the next stage, a non-linear adaptive filter, AEFLN, is used for the extraction of fECG. This approach requires no additional algorithm for polarity reversal and time alignment before AEFLN. At last, NWT determines the fetal R-peak envelopes from the residual fECG. The R-peak envelopes are used to analyze FHR, and its accuracy was accessed using the FHR trace. So far, FastICA-AEFLN-NWT has not been used as a hybrid method for fECG extraction and fetal R-peak detection. The algorithm's effectiveness was tested on both real databases from Daisy and Physionet and synthetic databases from Physionet. The proposed hybrid method attains 95.29 % of sensitivity (SE), 96.68 % of Positive Predictive Value (PPV), 95.92 % of F1 score, and FHR measurement (FHRmeas) is 29.72 bpm2. The proposed methodology outperforms the state-of-art methods in fECG extraction. [ABSTRACT FROM AUTHOR]

Conventionally, multi-lead Electrocardiogram (ECG) signals are recorded and stored using high sensing rates and high precision, resulting in huge data volumes and placing greater pressure on storage and transmission resources. Compressive sensing (CS) allows efficient encoding and decoding of signals through sparse representation, measurement and reconstruction for compressed storage and transmission of ECG signals. Traditional CS methods generally requires manually selecting the features or dictionaries used in sparse representations, which lacks adaptivity and flexibility, and the complexity of the reconstruction process limits the application of CS in some scenarios with high real-time requirements. In this paper, we propose a deep compressive sensing framework for processing multi-lead ECG signals by combining CS and deep learning, which is based on multi-scale feature fusion to construct a binary tree-shaped autoencoder architecture to achieve efficient compression and reconstruction of ECG signals. Experiments on the PTB diagnostic ECG database show that the proposed method achieves "very good" reconstruction quality at low sensing rates, with PRD and SNR of 1.77 % and 35.67 dB, respectively, when SR = 20 %. In addition, we investigate how the number of quantization bits affects the quality of reconstructed signals. After analysis, we found that 8-bit quantization can be used in practical applications to ensure the quality of reconstructed ECG signals, while decrease the bit rate of the data, improving the transmission efficiency, and reduce energy consumption. [ABSTRACT FROM AUTHOR]

Premature ventricular contractions (PVCs) are a common type of arrhythmia and can be life-threatening if deteriorated. There are several challenges remain to be resolved to the inter-patient paradigm of PVCs detection task by deep learning approaches. This research aims to overcome data imbalance, inaccurate ECG segments labeling and finding a generalized end-to-end model. In this paper, we present a deep learning network, PVCNet, to detect PVCs based on single-lead ECG. All ECG records are firstly split into fixed length segments based on the R-peak locations. To obtain more contextual information and improve the accuracy of segments labeling, we innovatively label the segment with sequence heartbeats label in the single heartbeat classification task, which was widely labeled with single heartbeat label in previous practices. Meanwhile, a loss function of redesigned weights is introduced to encourage the model to focus on detecting the specific heartbeat in the input segment. Additionally, a novel data augmentation method is conducted to alleviate the data imbalance problem. The proposed model is trained and validated on the MIT-BIH Arrhythmia Database (MITDB) with the inter-patient paradigm and tested on the St.Petersburg INCART Database (INCARTDB). It achieves a sensitivity of 89.91%, positive prediction value of 96.72%, F1-score of 93.19% and an overall accuracy of 98.50% on the testing database and outperforms existing approaches. The experimental results validate the effectiveness of the proposed approach and potentially can be applied to long-term ECG monitoring scenarios for the PVC detection task. [Display omitted] • We label the input ECG segment with a sequence of four heartbeats which decreases the possible label noise and provides more contextual information. • A loss function of redesigned weights is introduced to encourage the model to focus on detecting the specific heartbeat in the input segment. • Several comparisons and ablation studies results validate the effectiveness of the proposed PVC detection approach. [ABSTRACT FROM AUTHOR]

Time series analysis is crucial in the field of medical sciences. Recently, it has become crucial to comprehend the intricacies of data to forecast and assess the likelihood of survival in patients with different ailments. The study employs diverse datasets from multiple PTB electrocardiogram (ECG) datasets, which exhibit a high degree of uncorrelation. These datasets include patients with various heart diseases and age groups, ensuring dataset diversity. The paper presents two models that utilize deep learning and residual bias. The primary approach proposed is a hybrid GRU-CNN model. In contrast, the second model incorporates residual bias (RB) to improve upon the first model, referred to as the RB-GRU-CNN model. The hybrid GRU-CNN model has been compared to conventional deep learning models across multiple metrics, achieving the highest average percentage of improvement in RMSE (46.73%), MSE (67.46%), MAPE (43.92%), and MAE (48.52%) compared to LSTM. The RB-GRU-CNN proposed model demonstrated greater efficacy than the GRU-CNN proposed model, as confirmed by non-parametric statistical Friedman ranking and their corresponding Holm's p-values. The comprehensive study of the results proves that the proposed models outperformed the performance of the traditional models. [ABSTRACT FROM AUTHOR]

Numerous studies focus on diagnosing heart diseases using deep learning methods applied to 12-lead electrocardiographic (ECG) records. However, these studies often face limitations due to reliance on specific datasets, which vary in size and parameters such as patient metadata, the number of doctors annotating ECGs, types of devices used for ECG recording, data preprocessing techniques, etc. It is well-known that high-quality deep neural networks trained on one ECG dataset may not necessarily perform well on other datasets or in different clinical settings. In this paper, we propose a methodology designed to enhance the quality of heart disease prediction regardless of the dataset. We achieve this by first training neural networks on a variety of labeled datasets, then fine-tuning for specific datasets, significantly improving prediction accuracy. We demonstrate its applicability by training various neural networks on a large private dataset TIS, which contains a wide range of ECG records from multiple hospitals, and on a relatively smaller public dataset, PTB-XL. Our results show that networks trained on a large dataset improves classification performance. Furthermore, these networks fine-tuned on PTB-XL outperform those trained exclusively on smaller datasets. Additionally, we made the weights of our pre-trained models publicly available, enabling researchers and clinicians to adapt these models to their specific datasets. • Models trained on distinct ECG records may notably differ in quality across datasets. • Pre-training models on various ECG datasets improves the classification performance. • Fine-tuning networks on smaller ECG datasets significantly improves performance. • Researchers can use pre-trained model weights to adapt them for their tasks and data. [ABSTRACT FROM AUTHOR]

Cardiovascular disease (CADs) is considered the primary leading cause of death. Irregular activity of heart, these disease can be detected and classified by Electrocardiogram (ECG), which is constructed from using electrodes placed on human skin to record the electrical activity of the heart. Because QRS complex represents the basic part of the ECG signal, these components should be recognized in order to analysis the other characteristics of the signal. Different methods and algorithms are proposed to analysis and processing the ECG signal. In this paper, a new QRS complex recognition method are proposed based on discrete cosine transform (DCT) with variable adaptive threshold method, which is used to determine threshold based on characteristic of each ECG signal to detect upper and lower levels of threshold to detect the peak of the signal. At first, the DCT is applied to the ECG signal to isolate it into different coefficients and eliminate or reduce the noises of the signal based on processing of high frequency components of DCT coefficients, which have less information, then the ECG is reconstructed by cropping the most important coefficients to be used in threshold determination. The basic idea is that the reconstructed signal have high differences between the components of the signal, and this facilitates the process of calculating the threshold value, which is used later to find peaks of ECG signal. The proposed method is tested and its performance are determined based on three different datasets, which are MITBIH Arrhythmia dataset, (LTSTDB) and (EDB) and the performance are evaluated using different metrics, which are Detection rate, accuracy, specificity and sensitivity. The experimental results show that the proposed method is performed or outperformed other works, therefore it can be used in peak detection applications. [ABSTRACT FROM AUTHOR]

Highlights • The papers suggested by the reviewers are cited / added in the relevant section of the manuscript. • The details of statistical test used to validate the results and the MATLAB command used are added to the manuscript in Section 4, pg. no. 21. • The quality of the figures has been modified. • The time series comparison and corresponding discussion for the proposed method and EEMD based method with reference to the contaminated EEG is shown in fig.10, pg. no. 21. • As suggested by the reviewer, abstract is modified. Abstract The electroencephalogram (EEG) electrodes are susceptible to electrocardiogram (ECG) artifacts, misleading the analysis and diagnosis from the EEG recording. This paper mainly focuses on detection and correction of contaminating ECG artifact of various strengths, from a single channel EEG in the absence of a reference ECG channel. The algorithm involves two stages i.e. detection of ECG artifacts and correction of those artifacts. For detection of ECG artifact, modified S-transform (MST) is used on the bandpass filtered contaminated EEG to localize the higher energy QRS segments in time scale. For improved energy concentration of MST around the instantaneous frequency, artifact detection proximity in time scale is.05s. To correct ECG artifacts from EEG, a modified ensembled average subtraction is proposed, which restrict the overcompensation of the EEG in the correction process. The proposed algorithm is tested on MIT/BIH Polysomnography dataset and synthetic data set with various contamination strength, together more than 45 hours of EEG data. The proposed method achieves mean positive predictive value (PPV) and failed detection rate (FDR) of 97.87% and 2.13% respectively for MIT/BIH Polysomnography EEG recordings. The mean PPV and FDR for the CAP sleep EEG recordings with various contamination levels of ECG are found to be 98.77% and 1.22% respectively. The proposed algorithm is compared against existing Continuous wavelet transform (CWT) and Empirical ensembled mode decomposition (EEMD) based algorithms where the proposed algorithm found to be performing better in terms of spike to energy ratio (SER), spike to background energy ratio (SBR), correlation factors, Mutual information (MI), Mean absolute error (MAE) and Mean square error (MSE) along with a lower change in power spectral density (Δ PSD) in various brain frequency bands. [ABSTRACT FROM AUTHOR]

Highlights • 14 more data records were added. • 800 more experiments were conducted for revision. • 2 more CS based approaches were tested. • A new subsection "Sparsity of ECG in different domains" under results and discussion section. • Detailed abstract and conclusion sections. Abstract This paper elaborates the design details of a new set of bi orthogonal wavelet filters derived from double sided exponential splines. The designed wavelets are applied in compressed sensing (CS) scenario and results were quite promising. CS is a signal acquisition paradigm, which surpasses the traditional limit of Nyquist sampling. Increasing the reconstruction quality with minimum number of samples in CS is always challenging. We have addressed this challenging task of increasing the reconstruction quality within a minimum number of measurements in CS by developing this new set of biorthogonal wavelet filters. Biorthogonal wavelets have several advantages such as linear phase as compared to orthogonal wavelets. This wavelet which we prefer to call as dew1 (double exponential wavelet 1) is applied in CS based ECG reconstruction scenarios and experimented over 21 data records from MIT arrhythmia data base. A total of 950 experiments were conducted in three CS based methodologies for ECG reconstruction and the results were noted. Over all we were able to get nearly 30% improvement in the reconstruction quality. This paper elaborates the design of these bi orthogonal filters and its application in CS based ECG reconstruction scenario. Other than endorsing the results, we also aim to familiarize this newly designed wavelet so it can be further experimented in different domains. [ABSTRACT FROM AUTHOR]

Highlights • A self-adjustable domain adaptation (SADA) strategy is devised against overfitting. • SADA builds a vital sign dataset of ECG and IR-UWB radar data by actual records. • SADA devises the SOM-based ECG clustering by transfer learning to fuse multi data. • SADA broadens the application of domain adaptation algorithms by importing OC-SVM. Abstract To enhance electrocardiogram (ECG) monitoring systems in personalized detections, deep neural networks (DNNs) are applied to overcome individual differences by periodical retraining. As introduced previously [4] , DNNs relieve individual differences by fusing ECG with impulse radio ultra-wide band (IR-UWB) radar. However, such DNN-based ECG monitoring system tends to overfit into personal small datasets and is difficult to generalize to newly collected unlabeled data. This paper proposes a self-adjustable domain adaptation (SADA) strategy to prevent from overfitting and exploit unlabeled data. Firstly, this paper enlarges the database of ECG and radar data with actual records acquired from 28 testers and expanded by the data augmentation. Secondly, to utilize unlabeled data, SADA combines self organizing maps with the transfer learning in predicting labels. Thirdly, SADA integrates the one-class classification with domain adaptation algorithms to reduce overfitting. Based on our enlarged database and standard databases, a large dataset of 73200 records and a small one of 1849 records are built up to verify our proposal. Results show SADA's effectiveness in predicting labels and increments in the sensitivity of DNNs by 14.4% compared with existing domain adaptation algorithms. [ABSTRACT FROM AUTHOR]

This paper aims to address the problem of estimating blood pressure (BP) based on specific physiological signals. However, several issues exist in current works. Firstly, some methods produce biased models by training them on a skewed distribution and failing to consider the assumptions underlying regression analysis. Secondly, data leakage can occur when overlapping samples are present in the dataset. Finally, some methods concatenate Electrocardiogram (ECG) and Photoplethysmogram (PPG) signals without fully capturing their relationship. To overcome these limitations, this paper applies the BoxCox transformation to correct for skewed label distributions and creates a non-overlapping dataset. Additionally, a novel end-to-end model, the blood pressure network (BPNet), is proposed, which can accurately estimate blood pressure. The Multi-parameter Intelligent Monitoring in Intensive Care database (MIMIC) is utilized to develop and verify the model, which includes ECG, PPG, and invasive BP data from patients in intensive care units (ICUs). The BPNet is evaluated on the MIMIC II (942 subjects) and MIMIC-III (833 subjects) datasets. In MIMIC-II, the estimation error for systolic blood pressure (SBP) and diastolic blood pressure (DBP) is −0.17 ± 4.62 mmHg and −0.24 ± 2.95 mmHg, respectively. In MIMIC-III, the estimation error for SBP and DBP is −0.30 ± 5.78 mmHg and −0.25 ± 3.80 mmHg, respectively. The experimental results exceed the performance of existing methods and meet the accuracy standards established by the Association for the Advancement of Medical Instrumentation (AAMI) and the British Hypertension Society (BHS). This demonstrates the effectiveness and accuracy of the proposed model, highlighting the potential for practical applications in clinical settings. [ABSTRACT FROM AUTHOR]

This paper aims to address the problem of estimating blood pressure (BP) based on specific physiological signals. However, several issues exist in current works. Firstly, some methods produce biased models by training them on a skewed distribution and failing to consider the assumptions underlying regression analysis. Secondly, data leakage can occur when overlapping samples are present in the dataset. Finally, some methods concatenate Electrocardiogram (ECG) and Photoplethysmogram (PPG) signals without fully capturing their relationship. To overcome these limitations, this paper applies the BoxCox transformation to correct for skewed label distributions and creates a non-overlapping dataset. Additionally, a novel end-to-end model, the blood pressure network (BPNet), is proposed, which can accurately estimate blood pressure. The Multi-parameter Intelligent Monitoring in Intensive Care database (MIMIC) is utilized to develop and verify the model, which includes ECG, PPG, and invasive BP data from patients in intensive care units (ICUs). The BPNet is evaluated on the MIMIC II (942 subjects) and MIMIC-III (833 subjects) datasets. In MIMIC-II, the estimation error for systolic blood pressure (SBP) and diastolic blood pressure (DBP) is −0.17 ± 4.62 mmHg and −0.24 ± 2.95 mmHg, respectively. In MIMIC-III, the estimation error for SBP and DBP is −0.30 ± 5.78 mmHg and −0.25 ± 3.80 mmHg, respectively. The experimental results exceed the performance of existing methods and meet the accuracy standards established by the Association for the Advancement of Medical Instrumentation (AAMI) and the British Hypertension Society (BHS). This demonstrates the effectiveness and accuracy of the proposed model, highlighting the potential for practical applications in clinical settings. [ABSTRACT FROM AUTHOR]

Prediction of cardiac disease is one the most crucial topics in the sector of medical info evaluation. The stochastic nature and the variation concerning time in electrocardiogram (ECG) signals make it burdensome to investigate its characteristics. Being evolving in nature, it requires a dynamic predictive model. With the presence of concept drift, the model performance will get worse. Thus learning algorithms require an apt adaptive mechanism to accurately handle the drifting data streams. This paper proposes an inceptive approach, Corazon Concept Drift Detection Method (Corazon CDDM), to detect drifts and adapt to them in real-time in electrocardiogram signals. The proposed methodology results in achieving competitive results compared to the methods proposed in the literature for all types of datasets like synthetic, real-world & time-series datasets. [ABSTRACT FROM AUTHOR]

Electrocardiogram (ECG) signals are used to diagnose cardiovascular diseases. During ECG signal acquisition, various noises like power line interference, baseline wandering, motion artifacts, and electromyogram noise corrupt the ECG signal. As an ECG signal is non-stationary, removing these noises from the recorded ECG signal is quite tricky. In this paper, along with the proposed denoising technique using stationary wavelet transform, various denoising techniques like lowpass filtering, highpass filtering, empirical mode decomposition, Fourier decomposition method, discrete wavelet transform are studied to denoise an ECG signal corrupted with noise. Signal-to-noise ratio, percentage root-mean-square difference, and root mean square error are used to compare the ECG signal denoising performance. The experimental result showed that the proposed stationary wavelet transform based ECG denoising technique outperformed the other ECG denoising techniques as more ECG signal components are preserved than other denoising algorithms. • ECG signals contaminated with random noises are denoised using SWT is proposed. • Qualitative and quantitative analysis is performed on the MIT-BIH arrhythmia database. • The results demonstrate the superiority of the proposed SWT denoising methodology. • Periodic or quasi-periodic biomedical signals can be denoised using the proposed SWT. [ABSTRACT FROM AUTHOR]

As an important metric of observing heart rate changes, electrocardiogram (ECG) can reflect the current changes in heart rate in real time, and is an important basis for predicting cardiovascular diseases. This paper presents a portable ECG monitoring node with small size, low power consumption and long-term real-time monitoring ability. With the raw data amplified, filtered and A/D converted, the effective ECG data is obtained, and then transmitted to the Android client through the HC-06 Bluetooth module, which can be continuously updated on the client. The heart rate and ECG waveform updated per second allowing the user to observe their heart rate changes in real time and their physical conditions. Due to the specific design of signal processing unit, the proposed ECG monitoring node can achieve low power consumption and portability. The experimental results show that the node is suitable for long-term ECG monitoring in all kinds of environments with energy-efficient ability. [ABSTRACT FROM AUTHOR]

The extensive collection of electrocardiogram (ECG) recordings stored in paper format has provided opportunities for numerous digitization studies. However, the traditional 10 s 12-lead ECG printout typically splits the ECG signals into four asynchronous sections of 3 leads and 2.5 s each. Since each lead corresponds to different time instants, developing a synchronization method becomes necessary for applications such as vectorcardiogram (VCG) reconstruction. A beat-level synchronization method has been developed and validated using a dataset of 21,674 signals. This method effectively addresses synchronization distortions caused by RR interval variations and preserves the time lags between R peaks across different leads for each beat. The results demonstrate that the proposed method successfully synchronizes the ECG, allowing a VCG reconstruction with an average Pearson Correlation Coefficient of 0.9815±0.0426. The Normalized Root Mean Squared Error (NRMSE) and Mean Absolute Error (MAE) values for the reconstructed VCG are 0.0248±0.0214 mV and 0.0133±0.0123 mV, respectively. These metrics indicate the reliability of the VCG reconstruction achieved by means of the proposed synchronization method. The synchronization method has demonstrated its robustness and high performance compared to existing techniques in the field. Its effectiveness has been observed across a wide variety of signals, showcasing its applicability in real clinical environments. Moreover, its ability to handle a large number of signals makes it suitable for various applications, including retrospective studies and the development of machine learning methods. • Novel beat-level synchronization method for ECG signals, enhancing VCG reconstruction. • Validation on a dataset of 21,674 signals, ensuring robust synchronization across various leads. • A phantom model was created on the validation set for ECG printout replication. • Achieved high accuracy in VCG reconstruction with an average Pearson Correlation of 0.9815. • Method's effectiveness in clinical settings and suitability for retrospective studies. [ABSTRACT FROM AUTHOR]

Real-time electrocardiogram (ECG) monitoring through portable or wearable devices is critical for detecting lethal arrhythmias. Despite the accuracy of 12-lead ECGs in clinical image analysis, their integration into portable devices poses challenges. This paper introduces a novel method for nonmalignant arrhythmia classification, optimized for wearable and portable devices. We utilize ECG records from Shanghai First People's Hospital, proposing a lightweight neural network strategy involving benchmark network selection, model pruning, and learning rate decay-based finetuning. The proposed Random Horizontal Flip (RHF)-based classification method demonstrated superior performance, achieving a 94.8 % accuracy on a 12-lead clinical ECG test dataset. Utilizing the modified pruning method, the classification accuracy for five-class ECGs improved by 7.2 % over the benchmark network. The model size was reduced by 51.26 %, with parameters and FLOPs decreasing by 47.6 % and 49.1 %, respectively, compared to the benchmark, all under identical hardware conditions. Further experiments were conducted on the Hold-out Test Set (HTS), designed to include ECGs that present slight variations to the original conditions, yielding a slightly lower accuracy of 92.4 %, reflecting the dataset's complexity and clinical variability. Moreover, benchmarking tests using the Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) arrhythmia database validated the method's effectiveness, achieving a 99.24 % accuracy and maintaining a lightweight model of 4366KB. Comparative analysis with existing methods confirmed the proposed method's superiority in accuracy and real-world applicability. This research presents a significant advancement in ECG analysis, offering a viable solution for efficient arrhythmia monitoring in portable healthcare devices. • 12-lead ECG data used for nonmalignant arrhythmia classification. • Model's generalization tested with noisy, varied hold-out dataset. • Lightweight neural network strategy merges selection, pruning, finetuning, and augmentation. • Method's accuracy and practicality confirmed with MIT-BIH database. • Approach tailored for wearable devices on monitoring arrhythmias. [ABSTRACT FROM AUTHOR]

Cardiac arrhythmias, deviations from the normal rhythmic beating of the heart, are subtle yet critical indicators of potential cardiac challenges. Efficiently diagnosing them requires intricate understanding and representation of both spatial and temporal features present in Electrocardiogram (ECG) signals. This paper introduces ECGTransForm , a deep learning framework tailored for ECG arrhythmia classification. By embedding a novel Bidirectional Transformer (BiTrans) mechanism, our model comprehensively captures temporal dependencies from both antecedent and subsequent contexts. This is further augmented with Multi-scale Convolutions and a Channel Recalibration Module, ensuring a robust spatial feature extraction across various granularities. We also introduce a Context-Aware Loss (CAL) that addresses the class imbalance challenge inherent in ECG datasets by dynamically adjusting weights based on class representation. Extensive experiments reveal that ECGTransForm outperforms contemporary models, proving its efficacy in extracting meaningful features for arrhythmia diagnosis. Our work offers a significant step towards enhancing the accuracy and efficiency of automated ECG-based cardiac diagnoses, with potential implications for broader cardiac care applications. The source code is available at https://github.com/emadeldeen24/ECGTransForm. [ABSTRACT FROM AUTHOR]

Abstract This paper presents an robust and efficient unsupervised method for ECG arrhythmia classification. The proposed method consists of two steps: feature selection and clustering. In proposed method, initially the input ECG data is fed into feature selection method to reduce the dimensionality. In this paper, three well known feature selection methods i.e., Principal Component Analysis, Linear Discriminant Analysis (LDA) and Regularized Locality Preserving Indexing (RLPI) are employed. Further, the reduced data is clustered using a Robust Spatial Kernel FCM (RSKFCM) method. RSKFCM is variant of FCM method which uses Gaussian kernel as distance metric and incorporates neighborhood information. To evaluate the proposed method the experimentation's are conducted on UCI arrhythmia dataset and compared the results with traditional FCM and Kernel Fuzzy C-Means (KFCM). Extensive experimental results show that, the proposed RSKFCM method with RLPI feature selection method outperforms other methods in comparison. [ABSTRACT FROM AUTHOR]

In this paper, Recurrent Neural Networks (RNN) have been applied for classifying the normal and abnormal beats in an ECG. The primary aim of this paper was to enable automatic separation of regular and irregular beats. The MIT-BIH Arrhythmia database is being used to classify the beat classification performance. The methodology used is carried out using huge volume of standard data i.e. ECG time-series data as inputs to Long Short Term Memory Network. We divided the dataset as training and testing sub-data. The effectiveness, accuracy and capabilities of our methodology ECG arrhythmia detection is demonstrated and quantitative comparisons with different RNN models have also been carried out. [ABSTRACT FROM AUTHOR]

Wireless Body Sensor Networks (WBSNs) and wearable technology are the new trends in healthcare applications. This technology can provide real-time monitoring of the patient’s bio-signals and health condition. In this context, the analysis of ECG signals, reflecting the heart activity, is considered as key tool in diagnosing cardiac disorders such as Atrial Fibrillation (AF) that can lead to strokes and heart failure. Classical approaches for sensor-based AF detection require continuous transmission of ECG signals to a remote server which can rapidly exhaust the sensor energy and shortens the lifetime of the application. In this paper, we propose a new low-power scheme for AF episodes detection in ECG signal that is intended for implementation in WBSN. The paper details the design of this scheme and demonstrates its high accuracy for AF detection. [ABSTRACT FROM AUTHOR]

Cardiovascular disease is one of the major causes of mortality worldwide. Audio signal produced by the mechanical activity of heart provides useful information about the heart valves operation. To increase discriminability between heart sound signals of different normal and abnormal persons, extraction of appropriate features is so important. An accurate segmentation of heart sound signal requires its corresponding ECG 1 1 Electrocardiogram signal. But, acquiring of ECG is generally expensive and time consuming. So, one of the main goals of this paper is to eliminate the segmentation step. In this paper, two feature extraction methods are proposed. In the first proposed method, curve fitting is used to achieve the information contained in the sequence of heart sound signal. In the second method, the powerful features extracted by MFCC 2 2 Mel frequency cepstrum coefficients are fused with the fractal features by stacking. The experiments are done on six popular datasets to assess the efficiency of different methods One of the data sets contains four classes and the rest of them include two classes (normal and pathologic). In the classification step, the nearest neighbor classifier with Euclidean distance is used. The proposed method has good performance compared to previous methods such as Filter banks and Wavelet transform. Particularly, the performance of the second method is significantly better than the first proposed method. For three data sets, the overall accuracy of 92%, 81% and 98% are achieved, respectively. [ABSTRACT FROM AUTHOR]

Arrhythmia is a cardiac condition generated by the abnormal electrical activity of the heart, and an electrocardiogram (ECG) is a tool utilized by the cardiologists for determining the arrhythmias or heart abnormalities. Owing to the existence of noise, the non-stationary nature of the ECG signal and the abnormality of the heartbeat, physicians face difficulties in the diagnosis of arrhythmias. Hence, there is a need for computer-aided diagnosis system which can achieve higher recognition accuracy. Since the existing methods of classification consumed huge time and less accurate in case of considerably similar ECG signal, this paper proposes an effective method termed as Genetic Bat optimization algorithm for training the Support Vector Neural Network (GB-SVNN) for arrhythmia classification using ECG signals. Initially, multi-resolution wavelet-based approach and the Gabor filters are used for extracting the wave interval features and other texture features from the ECG signal. Based on the features, the SVNN classifies the ECG signal as the affected arrhythmia or no arrhythmia signal. The SVNN is trained using the GB algorithm. The experimentation of the proposed method is done using MATLAB 2015.a, and the performance is evaluated with the existing methods, such as KNN, Neural Network (NN), Fuzzy Subtractive Clustering, and Support Vector Neural Network (SVNN) for accuracy, specificity, and sensitivity. From the results, it can be shown that the proposed GD-SVNN attains a maximum value of accuracy, sensitivity, and specificity at a rate of 0.9696, 0.99, and 0.9583 respectively. [ABSTRACT FROM AUTHOR]

In this paper, we introduce an approach for Electromyogram (EMG) noise level approximation in Electrocardiogram (ECG) signals. The stationary wavelet transform (SWT) is used to find efficient translation-invariant approximation of EMG noise. This is accomplished in the form of reference signal extracted as an estimation of the signal quality vs. EMG noise. The reference signal is built and then normalized after considering different heart rates and rhythms which increases its robustness and reliability to give accurate results regardless of input signal rhythm. Additionally, four applications of the extracted reference signal are suggested in this paper. For evaluation purposes both real EMG and artificial noises were used. The tested ECG signals are from MIT-BIH Arrhythmia Database Directory. The correlation coefficient between the added noise and the reference signal were computed for moving windows over the signal. Finally, the correlation between beats detection and reference signal was computed and presented. Reference signal gave high correlation with false positive values. Most false positives caused by EMG noise occur in intervals of greater amplitude reference signal and vice versa. [ABSTRACT FROM AUTHOR]

Electrocardiogram (ECG) is one of the most important physiological signals of human body, which contains important clinical information about the heart. Monitoring of ECG signal is done through QRS detection. In this paper, an improved QRS detection algorithm, based on adaptive filtering principle, has been designed. Enumeration of the effectiveness of various LMS variants used in adaptive filtering based QRS detection algorithm has been done through fidelity parameters like sensitivity and positive predictivity. Whole family of LMS algorithm has been implemented for comparison. Sign-sign LMS, sign error LMS, basic LMS and normalized LMS are re-implemented, while variable leaky LMS, variable step-size LMS, leaky LMS, recursive least squares (RLS), and fractional LMS are novel combination presented in this paper. After analysis of the obtained results, performance of leaky-LMS algorithm is found to be the best with sensitivity, positive predictivity, and processing time of 99.68%, 99.84%, and 0.45 s respectively. Reported results are tested and evaluated over MIT/BIH arrhythmia database. Presented study also concludes that the performance of most of the variants gets affected due to low SNR but the Leaky LMS performs better even under heavy noise conditions. [ABSTRACT FROM AUTHOR]

• This paper proposes a new methodology for human identification via ECG, based on tracking the dynamic change in ECG features and utilizing the Fréchet distance measures for multiclass classification of feature matrices. • The proposed dynamic feature matrices can be utilized to model nonstationary signals because they provide continues information on feature variability. • The findings of our work show that Fréchet distances perform better than the Euclidian distance for ECG data classification in the context of multiclass classification problems. Recently, the use of electrocardiogram (ECG) for human identification has attracted great attention. Generally, most existing ECG based biometric systems relay on extracting the static fiducial or non-fiducial features of the cardiac signal. However, the recorded ECG data is more likely to be different whenever it is measured. Such problem can be addressed by utilizing the dynamic change in ECG features. This paper proposes a new methodology for human identification via ECG, based on tracking the dynamic change in ECG features and utilizing the Fréchet distance measures for multiclass classification of feature matrices. The proposed dynamic feature matrices can be utilized to model nonstationary signals because they provide continues information on feature variability. Technically, we utilize the consecutive change of ECG power spectral density as significant feature. In addition, we use the dynamic change of QRS features as a distinguishable characteristic. At the classification stage, we use equations of Fréchet distances to perform multiclass classification because the covariance matrices of the dynamic feature matrices are symmetric positive definite, and their relative geometric space is not Euclidian. The performance of our methodology was evaluated using the publicly available ECG ID database of 62 subjects. To support real world applicability of our method, we randomized the reference / test data selection using data windowing techniques for examining the stability of our method by changing the datasets. The experimental results show that our methodology was able to achieve an identification accuracy of 97.03% with 0.971 precision, 0.999 specificity, 0.97 recall, 0.029 false rejection rate and 0.00048 false acceptance rate. Furthermore, the findings of our work show that Fréchet distances perform better than the Euclidian distance for ECG data classification in the context of multiclass classification problems. [ABSTRACT FROM AUTHOR]

• A GAN network is proposed to generate ECG data without supervision. • Unpaired noisy and unnoisy data are used for training. • Solving the problem of lack of training data in current ECG recognition model. Over the years, significant hospitals have scanned paper electrocardiograms and saved them into electronic health records to form digital management of diagnosis and treatment records. Therefore, the electrocardiogram(ECG) scans have substantial sample diversity, correlate with the patient's past medical records, and have significant research value. However, the scanned ECG is noisy, and it is difficult to directly use it as the training data of the intelligent diagnosis algorithm, so it is necessary to preprocess it. In recent years, some researchers have proposed methods to extract ECG signals from noisy ECG using neural networks, but the results are not good enough due to the lack of paired noise ECG and noiseless ECG to train neural networks. This paper proposes an unsupervised noise ECG image generation method to overcome this difficulty. These generated images have the same ECG signals as the input ECG image, and the noise is similar to the actual ECG image. These two kinds of input images do not need to be paired. To evaluate the global and local quality of the generated images, our method uses a two-discriminator generative adversarial network and calls them global discriminator and local discriminator separately. The output vector of the global discriminator is fed into the generator when training the model, thereby helping the generator to improve the generated results in a targeted manner. Using the data generated by this method to train the neural network for ECG signal extraction can significantly improve its extraction performance. The Dice coefficient of the proposed network reaches 0.868, which is higher than 0.798 of the robust baseline model. Therefore, the proposed method can effectively solve the problem of lacking training data in the current ECG signal extraction network. [ABSTRACT FROM AUTHOR]

IoT wearable devices that leverage the LPWAN (Low Power Wide Area Network) connectivity, in particular the NB-IoT (Narrow Band IoT) technology, commonly rely on UDP (User Datagram Protocol) packets to communicate with the endpoint to collect data. Its advantage is that of minimal bandwidth usage but its drawback is the lack of acknowledgements by the endpoint. One option is to use TCP (Transmission Control Protocol) or implement a custom acknowledgement protocol at a superior level in the network stack. This paper presents the implementation and testing of a simple and lightweight software synchronization layer on top of the UDP protocol, for the transmission of live EKG signal data, with verification of data integrity and the detection of sampling points loss. [ABSTRACT FROM AUTHOR]

Electrocardiogram (ECG) test is very important for fetus condition inspection so as to avoid stillbirth and neonatal death during pregnancy. It is well known and widely used as a medical tool as it is convenient and non-invasive. Nevertheless, analysing fetal ECG (FECG) signal by using naked eye is tedious as the observed signal is a mixed signal which consists of weak FECG, maternal ECG (MECG) and also other signals including mother's respiratory noise. Hence, in this paper, Blind Source Separation (BSS) is used to extract the estimated desired signal i.e. FECG from the mixed signal. BSS is a well-known separation method that is able to extract desired signal without knowing any information of the source signal. The aim of this study is to elucidate the performance of BSS algorithms i.e. Fast Fixed-Point for Independent Component Analysis (FastICA), Joint Approximate Diagonalization of Eigenmatrix (JADE) and Principal Component Analysis (PCA) for FECG extraction. We integrate R-peak detection algorithm as a post-separation process to the BSS system in order to distinguish the estimated FECG and MECG for easier analysis process. Estimated signals are evaluated based on waveform characteristics observation and Signal-to Interference Ratio (SIR) parameter. We can conclude that JADE performance performs better in term of accuracy while FastICA is good in term of the computational time. However, FastICA manages to get comparable result as JADE after many fine-tuning steps and it is more flexible compared to JADE as it is not sensitive to low quality input signal. [ABSTRACT FROM AUTHOR]

In this paper, a person identification system has been simulated using electrocardiogram (ECG) signals as biometrics. In this work, we propose a two-phase method to conduct human identification using the ECG signal, which are the feature extraction and the classification. In the first phase, it makes a fusion of three new types of characteristics: cepstral coefficients, ZCR, and entropy. In the second phase, the support vector machines (SVM) has been applied for the classification system. The proposed methods are evaluated using two public databases namely MIT-BIH arrhythmia and ECG-ID database obtained from the Physionet database. Experimental results show that our features can achieve high subject identification accuracy of 100% on ECG signals that are from the MIT-BIH database, ECG-ID (Five recording), and ECG-ID (Two recording), indicating that our features makes it possible to improve the efficiency of our identification system. [ABSTRACT FROM AUTHOR]

Automatic electrocardiogram beat classification is a prevalent field of research among the biomedical and computer science researchers. In the last decade, the research has seen a transition from feature centric classification approach to a classifier centric approach. The performance of conventional approach based classifiers such as probabilistic neural networks, support vector machines, is highly dependent on the performance of pre-processing and feature extraction modules. Whereas, modern approach based classifiers such as deep neural networks, convolutional neural networks, do not need handcrafted features. They can generate characteristic features automatically from raw ECG signal. This paper aims to provide a comparative analysis of conventional and modern approaches. Further, deep learning based classifier models have been investigated to design a road-map for researcher new to this field. [ABSTRACT FROM AUTHOR]

Classification of ECG signals plays an important role in the field of medical diagnosis. Despite that much progress has been made in ECG classification in recent years, most of them focus on single-lead cardiac feature extraction. In this paper, we propose a new classification method based on twelve-lead surface ECG signal by fusing improved hand-crafted ECG features and deep learning classifiers for paroxysmal atrial fibrillation (PAF) detection. Three-dimensional dominated components are extracted without ECG signal segmentation operations, and continuous wavelet transform (CWT) is adopted for time–frequency representation to reflect essential characteristics of multi-resolution frequency domain at different scales. This kind of time–frequency representation has high discriminative power to detect PAF even before pathologic changes in surface twelve-lead ECG signals. Five pre-trained deep neural networks models are used to perform transfer learning and feature fusion. ECG signals are finally classified by using a feature fusion method based on multiple deep networks. • Hand-crafted ECG features and deep learning techniques are combined. • New time–frequency representation is proposed to detect PAF. • The proposed method can detect PAF before pathologic changes in ECGs. • Five pre-trained deep models are used to perform transfer learning. [ABSTRACT FROM AUTHOR]