Feature Extraction of Electrocardiogram Signals by Applying Adaptive Threshold and Principal Component Analysis

Feasibility Analysis of ECG-Based pH Estimation for Asphyxia Detection in Neonates

Birth asphyxia is a potential cause of death that is also associated with acute and chronic morbidities. The traditional and immediate approach for monitoring birth asphyxia (i.e., arterial blood gas analysis) is highly invasive and intermittent. Additionally, alternative noninvasive approaches such as pulse oximeters can be problematic, due to the possibility of false and erroneous measurements. Therefore, further research is needed to explore alternative noninvasive and accurate monitoring methods for asphyxiated neonates. This study aims to investigate the prominent ECG features based on pH estimation that could potentially be used to explore the noninvasive, accurate, and continuous monitoring of asphyxiated neonates. The dataset used contained 274 segments of ECG and pH values recorded simultaneously. After preprocessing the data, principal component analysis and the Pan-Tompkins algorithm were used for each segment to determine the most significant ECG cycle and to compute the ECG features. Descriptive statistics were performed to describe the main properties of the processed dataset. A Kruskal-Wallis nonparametric test was then used to analyze differences between the asphyxiated and non-asphyxiated groups. Finally, a Dunn-Šidák post hoc test was used for individual comparison among the mean ranks of all groups. The findings of this study showed that ECG features (T/QRS, T Amplitude, Tslope, Tslope/T, Tslope/|T|, HR, QT, and QTc) based on pH estimation differed significantly (p < 0.05) in asphyxiated neonates. All these key ECG features were also found to be significantly different between the two groups.

Evaluation of The Fetal Heart Rate Monitoring with The Non-Invasive Electrocardiography Signals

Fetal heart rate monitoring is a crucial element in determining the health of the fetus during pregnancy. In this paper, we evaluate the fetal heart rate (FHR) and maternal heart rate (MHR) between our non-invasive fetal monitoring system, Femom, developed by a Biorithm and the Huntleigh computerized cardiotocography (cCTG) together with the Sonicaid FetalCare3 software by comparing the accuracy, sensitivity, and reliability through using Bland-Altman analysis, Positive Percent Agreement (PPA) and Intraclass Correlation Coefficient (ICC) respectively. Femom device is a part of the Femom system which collects abdominal electrocardiogram (aECG) signals. Femom sever then processes the collected signals to generate FHR and MHR using novel algorithms. We collected data from 285 pregnant participants who were at least of 28 weeks of gestational age. FHR accuracy consists of mean bias and limit-of-agreement (LoA). The FHR bias is 0.05 beat per minute (BPM) and LoA is [-8.7 8.8] with 95% confidence interval (95% CI) measured using Bland Altman analysis. The PPA of 90.9% reflects FHR sensitivity. Reliability is measured with absolute ICC and consistency ICC. The absolute ICC is of 88% and consistency ICC of 94%. For MHR evaluation, accuracy is measured using Bland Altman analysis which provided a bias of 0.35 BPM and LoA of [-7 6.2] with 95% CI. The MHR sensitivity calculated using PPA is 98% while the MHR reliability is with the absolute value of 99% and consistency ICC of 99%.

A New Method of Identifying Characteristic Points in the Impedance Cardiography Signal Based on Empirical Mode Decomposition

The accurate detection of fiducial points in the impedance cardiography signal (ICG) has a decisive impact on the proper estimation of diagnostic parameters such as stroke volume or cardiac output. It is, therefore, necessary to find an algorithm that is able to assess their positions with great precision. The solution to this problem is, however, quite challenging with regard to the high sensitivity of the ICG technique to the noise and varying morphology of the acquired signals. The aim of this study is to propose a novel method that allows us to overcome these limitations. The developed algorithm is based on Empirical Mode Decomposition (EMD)-an effective technique for processing and analyzing various types of non-stationary signals. We find high correlations between the results obtained from the algorithm and annotated by an expert. This, in turn, implies that the difference in estimation of the diagnostic-relevant parameters is small, which suggests that the method can automatically provide precise clinical information.

An Efficient Method for Wheel-Flattened Defects Detection Based on Acoustic Emission Technique

Recent research studies show that acoustic emission (AE) technologies have great potential in detecting the flattened defects of wheel; however, the wheel-rail rolling interference (WRRI) significantly influences the accuracy of wheel defect detection. Aiming to solve the above-mentioned problem, a novel detection method, which combines an improved synthesized health index (ISHI) with a time adaptive threshold (time-ATH), is proposed in this article. In order to obtain the defect information from the signals generated by the wheels, a completed feature set that contains many types of features is extracted from AE signals. Then, the ISHI is fused by several effective features that are selected from the completed feature set, according to detection rate and accuracy. Besides, a time-ATH calculation is proposed to detect the defective signals of wheels and reduce the influence of the WRRI. The method is fully verified in actual datasets, and the results show that the proposed method achieves a better detection rate and accuracy. Moreover, it provides an effective way for the AE detection of wheel-flattened defects under strong and numerous WRRI.

Driver Monitoring of Automated Vehicles by Classification of Driver Drowsiness Using a Deep Convolutional Neural Network Trained by Scalograms of ECG Signals

Driver drowsiness is one of the leading causes of traffic accidents. This paper proposes a new method for classifying driver drowsiness using deep convolution neural networks trained by wavelet scalogram images of electrocardiogram (ECG) signals. Three different classes were defined for drowsiness based on video observation of driving tests performed in a simulator for manual and automated modes. The Bayesian optimization method is employed to optimize the hyperparameters of the designed neural networks, such as the learning rate and the number of neurons in every layer. To assess the results of the deep network method, heart rate variability (HRV) data is derived from the ECG signals, some features are extracted from this data, and finally, random forest and k-nearest neighbors (KNN) classifiers are used as two traditional methods to classify the drowsiness levels. Results show that the trained deep network achieves balanced accuracies of about 77% and 79% in the manual and automated modes, respectively. However, the best obtained balanced accuracies using traditional methods are about 62% and 64%. We conclude that designed deep networks working with wavelet scalogram images of ECG signals significantly outperform KNN and random forest classifiers which are trained on HRV-based features.

ECG denoising and feature extraction techniques - a review

The electrocardiogram (ECG) is a non-invasive approach for the recording of bioelectric signals generated by the heart which is used for the examination of the electro physical state, the function of the heart, and many cardiac diseases. However, various artefacts and measurement noise usually hinder providing accurate feature extraction such as power line interference, baseline wander, electromyographic noise (EMG) and electrode motion artefact. Therefore, for better analysis and interpretation ECG signals must be noise-free. Most recent and efficient techniques for ECG denoising and feature extraction techniques have been reviewed in this paper, as feature extraction and denoising of ECG are remarkably helpful in cardiology. This paper presents the review of contemporary signal processing techniques such as discrete wavelet transform (DWT), Empirical mode decomposition (EMD), Variational mode decomposition (VMD) and Empirical wavelet transform (EWT) for ECG signal denoising and feature extraction.

A Proposal for a Data-Driven Approach to the Influence of Music on Heart Dynamics

Electrocardiographic signals (ECG) and heart rate viability measurements (HRV) provide information in a range of specialist fields, extending to musical perception. The ECG signal records heart electrical activity, while HRV reflects the state or condition of the autonomic nervous system. HRV has been studied as a marker of diverse psychological and physical diseases including coronary heart disease, myocardial infarction, and stroke. HRV has also been used to observe the effects of medicines, the impact of exercise and the analysis of emotional responses and evaluation of effects of various quantifiable elements of sound and music on the human body. Variations in blood pressure, levels of stress or anxiety, subjective sensations and even changes in emotions constitute multiple aspects that may well-react or respond to musical stimuli. Although both ECG and HRV continue to feature extensively in research in health and perception, methodologies vary substantially. This makes it difficult to compare studies, with researchers making recommendations to improve experiment planning and the analysis and reporting of data. The present work provides a methodological framework to examine the effect of sound on ECG and HRV with the aim of associating musical structures and noise to the signals by means of artificial intelligence (AI); it first presents a way to select experimental study subjects in light of the research aims and then offers possibilities for selecting and producing suitable sound stimuli; once sounds have been selected, a guide is proposed for optimal experimental design. Finally, a framework is introduced for analysis of data and signals, based on both conventional as well as data-driven AI tools. AI is able to study big data at a single stroke, can be applied to different types of data, and is capable of generalisation and so is considered the main tool in the analysis.

Robust R-Peak Detection in Low-Quality Holter ECGs using 1D Convolutional Neural Network

OBJECTIVE

Noise and low quality of ECG signals acquired from Holter or wearable devices deteriorate the accuracy and robustness of R-peak detection algorithms. This paper presents a generic and robust system for R-peak detection in Holter ECG signals. While many proposed algorithms have successfully addressed the problem of ECG R-peak detection, there is still a notable gap in the performance of these detectors on such low-quality ECG records.

METHODS

In this study, a novel implementation of the 1D Convolutional Neural Network (CNN) is used integrated with a verification model to reduce the number of false alarms. This CNN architecture consists of an encoder block and a corresponding decoder block followed by a sample-wise classification layer to construct the 1D segmentation map of R-peaks from the input ECG signal. Once the proposed model has been trained, it can solely be used to detect R-peaks possibly in a single channel ECG data stream quickly and accurately, or alternatively, such a solution can be conveniently employed for real-time monitoring on a lightweight portable device.

RESULTS

The model is tested on two open-access ECG databases: The China Physiological Signal Challenge (2020) database (CPSC-DB) with more than one million beats, and the commonly used MIT-BIH Arrhythmia Database (MIT-DB). Experimental results demonstrate that the proposed systematic approach achieves 99.30% F1-score, 99.69% recall, and 98.91% precision in CPSC-DB, which is the best R-peak detection performance ever achieved. Results also demonstrate similar or better performance than most competing algorithms on MIT-DB with 99.83% F1-score, 99.85% recall, and 99.82% precision.

SIGNIFICANCE

Compared to all competing methods, the proposed approach can reduce the false-positives and false-negatives in Holter ECG signals by more than 54% and 82%, respectively.

CONCLUSION

Finally, the simple and invariant nature of the parameters leads to a highly generic system and therefore applicable to any ECG dataset.

Arrhythmias Prediction Using an Hybrid Model Based on Convolutional Neural Network and Nonlinear Regression

In biomedical signal processing, artificial intelligence techniques are used for identifying and extracting relevant information. However, it lacks effective solutions based on machine learning for the prediction of cardiac arrhythmias. The heart diseases diagnosis rests essentially on the analysis of various properties of ECG signal. The arrhythmia is one of the most common heart diseases. A cardiac arrhythmia is a disturbance of the heart rhythm. It occurs when the heart beats too slowly, too fast or anarchically, with no apparent cause. The diagnosis of cardiac arrhythmias is based on the analysis of the ECG properties, especially, the durations (P, QRS, T), the amplitudes (P, Q, R, S, T), the intervals (PQ, QT, RR), the cardiac frequency and the rhythm. In this paper we propose a system of arrhythmias diagnosis assistance based on the analysis of the temporal and frequential properties of the ECG signal. After the features extraction step, the ECG properties are then used as input for a convolutional neural network to detect and classify the arrhythmias. Finally, the classification results are used to perform a prediction of arrhythmias with nonlinear regression model. The method is illustrated using the MIT-BIH database.

Cloud-based ECG monitoring using event-driven ECG acquisition and machine learning techniques

An approach is proposed for the detection of chronic heart disorders from the electrocardiogram (ECG) signals. It utilizes an intelligent event-driven ECG signal acquisition system to achieve a real-time compression and effective signal processing and transmission. The experimental results show that grace of event-driven nature an overall 2.6 times compression and bandwidth utilization gain is attained by the suggested solution compared to the counter classical methods. It results in a significant reduction in the complexity and execution time of the post denoising, features extraction and classification processes. The overall system precision is studied in terms of the classification accuracy, the F-measure, the area under the ROC curve (AUC) and the Kappa statistics. The best classification accuracy of 94.07% is attained. It confirms that the designed event-driven solution realizes a computationally efficient automatic diagnosis of the cardiac arrhythmia while achieving a high precision decision support for cloud-based mobile health monitoring.

The Neural Engine: A Reprogrammable Low Power Platform for Closed-Loop Optogenetics

Brain-machine Interfaces (BMI) hold great potential for treating neurological disorders such as epilepsy. Technological progress is allowing for a shift from open-loop, pacemaker-class, intervention towards fully closed-loop neural control systems. Low power programmable processing systems are therefore required which can operate within the thermal window of 2° C for medical implants and maintain long battery life. In this work, we have developed a low power neural engine with an optimized set of algorithms which can operate under a power cycling domain. We have integrated our system with a custom-designed brain implant chip and demonstrated the operational applicability to the closed-loop modulating neural activities in in-vitro and in-vivo brain tissues: the local field potentials can be modulated at required central frequency ranges. Also, both a freely-moving non-human primate (24-hour) and a rodent (1-hour) in-vivo experiments were performed to show system reliable recording performance. The overall system consumes only 2.93 mA during operation with a biological recording frequency 50 Hz sampling rate (the lifespan is approximately 56 hours). A library of algorithms has been implemented in terms of detection, suppression and optical intervention to allow for exploratory applications in different neurological disorders. Thermal experiments demonstrated that operation creates minimal heating as well as battery performance exceeding 24 hours on a freely moving rodent. Therefore, this technology shows great capabilities for both neuroscience in-vitro/in-vivo applications and medical implantable processing units.

A morphologically robust chaotic map based approach to embed patient's confidential data securely in non-QRS regions of ECG signal

In e-healthcare paradigm, the physiological signals along with patient's personal information need to be transmitted to remote healthcare centres. Before sharing this sensitive information over the unsecured channel, it is prerequisite to protect it from unauthorised access. The proposed method explores ECG signal as the cover signal to hide patient's personal information without disturbing its diagnostic features. Chaotic maps are used to randomly select the embedding locations in the non-QRS region while excluding the sensitive QRS region of ECG train. Optimum Location Selection algorithm has been designed to select the embedding locations in non-QRS embedding region. The proposed algorithm is thoroughly examined and the distortion is measured in terms of statistical parameters and clinical measures such as PRD, PRDN, PRD1024, PSNR, SNR, MSE, MAE, KL-Divergence, WWPRD and WEDD. The robustness of the algorithm is verified using the parameters such as key space and key sensitivity. The implementation has been extensively tested on all the 48 records of the standard MIT-BIH Arrhythmia database, abnormal databases [CU-VT, BIDMC-CHF and PTB (leads I, II and III)] and self-recorded data of 20 subjects. The algorithm yields average PRD, MSE, KL-Divergence, PSNR, WWPRD and WEDD of 4.7 × 10^-3, 1.13 × 10^-5, 1.29 × 10^-5, 50.28, 0.15 and 0.04 at an average maximum EC of 0.45(96876 bits) on MIT-BIH Arrhythmia database and 0.016, 3.38 × 10^-5, 1.8 × 10^-4, 46.03, 0.13 and 0.03 respectively at an average maximum EC of 0.47 (102571 bits) on self-recorded data which clearly reveals the competency of the proposed algorithm in comparison with the other state of the art ECG steganography approaches.

On the Beat Detection Performance in Long-Term ECG Monitoring Scenarios

Despite the wide literature on R-wave detection algorithms for ECG Holter recordings, the long-term monitoring applications are bringing new requirements, and it is not clear that the existing methods can be straightforwardly used in those scenarios. Our aim in this work was twofold: First, we scrutinized the scope and limitations of existing methods for Holter monitoring when moving to long-term monitoring; Second, we proposed and benchmarked a beat detection method with adequate accuracy and usefulness in long-term scenarios. A longitudinal study was made with the most widely used waveform analysis algorithms, which allowed us to tune the free parameters of the required blocks, and a transversal study analyzed how these parameters change when moving to different databases. With all the above, the extension to long-term monitoring in a database of 7-day Holter monitoring was proposed and analyzed, by using an optimized simultaneous-multilead processing. We considered both own and public databases. In this new scenario, the noise-avoid mechanisms are more important due to the amount of noise that exists in these recordings, moreover, the computational efficiency is a key parameter in order to export the algorithm to the clinical practice. The method based on a Polling function outperformed the others in terms of accuracy and computational efficiency, yielding 99.48% sensitivity, 99.54% specificity, 99.69% positive predictive value, 99.46% accuracy, and 0.85% error for MIT-BIH arrhythmia database. We conclude that the method can be used in long-term Holter monitoring systems.

Salient space detection algorithm for signal extraction from contaminated and distorted spectrum

The proposed algorithm minimizes the influence of baseline distortion and exhibits good anti-noise ability and high real-time performance.

An Adaptive and Time-Efficient ECG R-Peak Detection Algorithm

R-peak detection is crucial in electrocardiogram (ECG) signal analysis. This study proposed an adaptive and time-efficient R-peak detection algorithm for ECG processing. First, wavelet multiresolution analysis was applied to enhance the ECG signal representation. Then, ECG was mirrored to convert large negative R-peaks to positive ones. After that, local maximums were calculated by the first-order forward differential approach and were truncated by the amplitude and time interval thresholds to locate the R-peaks. The algorithm performances, including detection accuracy and time consumption, were tested on the MIT-BIH arrhythmia database and the QT database. Experimental results showed that the proposed algorithm achieved mean sensitivity of 99.39%, positive predictivity of 99.49%, and accuracy of 98.89% on the MIT-BIH arrhythmia database and 99.83%, 99.90%, and 99.73%, respectively, on the QT database. By processing one ECG record, the mean time consumptions were 0.872 s and 0.763 s for the MIT-BIH arrhythmia database and QT database, respectively, yielding 30.6% and 32.9% of time reduction compared to the traditional Pan-Tompkins method.

R Peak Detection Method Using Wavelet Transform and Modified Shannon Energy Envelope

Rapid automatic detection of the fiducial points-namely, the P wave, QRS complex, and T wave-is necessary for early detection of cardiovascular diseases (CVDs). In this paper, we present an R peak detection method using the wavelet transform (WT) and a modified Shannon energy envelope (SEE) for rapid ECG analysis. The proposed WTSEE algorithm performs a wavelet transform to reduce the size and noise of ECG signals and creates SEE after first-order differentiation and amplitude normalization. Subsequently, the peak energy envelope (PEE) is extracted from the SEE. Then, R peaks are estimated from the PEE, and the estimated peaks are adjusted from the input ECG. Finally, the algorithm generates the final R features by validating R-R intervals and updating the extracted R peaks. The proposed R peak detection method was validated using 48 first-channel ECG records of the MIT-BIH arrhythmia database with a sensitivity of 99.93%, positive predictability of 99.91%, detection error rate of 0.16%, and accuracy of 99.84%. Considering the high detection accuracy and fast processing speed due to the wavelet transform applied before calculating SEE, the proposed method is highly effective for real-time applications in early detection of CVDs.

A lightweight QRS detector for single lead ECG signals using a max-min difference algorithm

BACKGROUND AND OBJECTIVES

Detection of the R-peak pertaining to the QRS complex of an ECG signal plays an important role for the diagnosis of a patient's heart condition. To accurately identify the QRS locations from the acquired raw ECG signals, we need to handle a number of challenges, which include noise, baseline wander, varying peak amplitudes, and signal abnormality. This research aims to address these challenges by developing an efficient lightweight algorithm for QRS (i.e., R-peak) detection from raw ECG signals.

METHODS

A lightweight real-time sliding window-based Max-Min Difference (MMD) algorithm for QRS detection from Lead II ECG signals is proposed. Targeting to achieve the best trade-off between computational efficiency and detection accuracy, the proposed algorithm consists of five key steps for QRS detection, namely, baseline correction, MMD curve generation, dynamic threshold computation, R-peak detection, and error correction. Five annotated databases from Physionet are used for evaluating the proposed algorithm in R-peak detection. Integrated with a feature extraction technique and a neural network classifier, the proposed ORS detection algorithm has also been extended to undertake normal and abnormal heartbeat detection from ECG signals.

RESULTS

The proposed algorithm exhibits a high degree of robustness in QRS detection and achieves an average sensitivity of 99.62% and an average positive predictivity of 99.67%. Its performance compares favorably with those from the existing state-of-the-art models reported in the literature. In regards to normal and abnormal heartbeat detection, the proposed QRS detection algorithm in combination with the feature extraction technique and neural network classifier achieves an overall accuracy rate of 93.44% based on an empirical evaluation using the MIT-BIH Arrhythmia data set with 10-fold cross validation.

CONCLUSIONS

In comparison with other related studies, the proposed algorithm offers a lightweight adaptive alternative for R-peak detection with good computational efficiency. The empirical results indicate that it not only yields a high accuracy rate in QRS detection, but also exhibits efficient computational complexity at the order of O(n), where n is the length of an ECG signal.

A Novel Method for Classification of ECG Arrhythmias Using Deep Belief Networks

In this paper, a novel approach based on deep belief networks (DBN) for electrocardiograph (ECG) arrhythmias classification is proposed. The construction process of ECG classification model consists of two steps: features learning for ECG signals and supervised fine-tuning. In order to deeply extract features from continuous ECG signals, two types of restricted Boltzmann machine (RBM) including Gaussian–Bernoulli and Bernoulli–Bernoulli are stacked to form DBN. The parameters of RBM can be learned by two training algorithms such as contrastive divergence and persistent contrastive divergence. A suitable feature representation from the raw ECG data can therefore be extracted in an unsupervised way. In order to enhance the performance of DBN, a fine-tuning process is carried out, which uses backpropagation by adding a softmax regression layer on the top of the resulting hidden representation layer to perform multiclass classification. The method is then validated by experiments on the well-known MIT-BIH arrhythmia database. Considering the real clinical application, the inter-patient heartbeat dataset is divided into two sets and grouped into four classes (N, S, V, F) following the recommendations of AAMI. The experiment results show our approach achieves better performance with less feature learning time than traditional hand-designed methods on the classification of ECG arrhythmias.