Classification Algorithms for Fetal QRS Extraction in Abdominal ECG Signals

In this paper, we investigate the use of adaptive neuro-fuzzy inference systems (ANFIS) for fetal electrocardiogram (FECG) extraction from two ECG signals recorded at the thoracic and abdominal areas of the mother's skin. The thoracic ECG is assumed to be almost completely maternal (MECG) while the abdominal ECG is considered to be composite as it contains both the mother's and the fetus' ECG signals. The maternal component in the abdominal ECG signal is a nonlinearly transformed version of the MECG. We use an ANFIS network to identify this nonlinear relationship, and to align the MECG signal with the maternal component in the abdominal ECG signal. Thus, we extract the FECG component by subtracting the aligned version of the MECG signal from the abdominal ECG signal. We validate our technique on both real and synthetic ECG signals. Our results demonstrate the effectiveness of the proposed technique in extracting the FECG component from abdominal signals of very low maternal to fetal signal-to-noise ratios. The results also show that the technique is capable of extracting the FECG even when it is totally embedded within the maternal QRS complex.

An IoMT enabled deep learning framework for automatic detection of fetal QRS: A solution to remote prenatal care

Spatio-spectral independent component analysis for fetal ECG extraction from two-channel maternal abdominal signals

This paper proposes a new method to extract fetal ECG from multi-channel signals. The fetal ECG is extracted in phase space, which is constructed by a pregnant woman's multiple thoracic and abdominal ECG signals. Based on corresponding points in phase space, we adopt least square algorithm to estimate the maternal components of the abdominal signals and extract the fetal signals by subtracting the estimated maternal signals from the abdominal signals. Compared with traditional separation method based on information fusion of multi-channel signals, such as Independent Component Analysis (ICA), this method could be realized more easily and effectively.

The non-invasive fetal electrocardiography (NI-FECG) plays an important role in prenatal monitoring. However, the NI-FECG is inevitably affected by a variety of non-stationary interferences, making the detecting of fetal QRS (FQRS) complexes a challenging task. In this study, we propose a novel framework that dynamically assesses the quality of NI-FECG to improve multichannel FQRS detection. The novelty of the framework relies on assessing the signal quality in semantic level. Specifically, each of the detected FQRS can be considered as a semantic unit, which contains the basically semantic information (true R peak (TR) or false R peak (FR)). By obtaining the possible condition of correct detections, the signal quality of each channel can be estimated. Further, the performance of the corresponding channel on the FQRS detection becomes assessable. The procedure contains four stages: Firstly, single-channel FQRS detection is employed on each channel individually. Secondly, a convolutional neural network (CNN) is used to classify the detected FQRS as either TR or FR. Thirdly, the TR-index is used to quantity the signal quality of single channel. And the channel with the highest TR-index is selected as the optimal channel. Finally, a robust strategy that mimics the human approach is used to fuse the TRs of all channels into a new channel. Results on two databases show that the proposed method is effective in FQRS detection achieving 97.81%Precision, 98.29%Recall and 98.05%$F_{1}$. This work sheds some light to the topic of NI-FECG signal quality assessment.

Fetal heart rate estimation using fractional Fourier transform and wavelet analysis

Noninvasive fetal ECG (fECG) monitoring has potential applications in diagnosing congenital heart diseases in a timely manner and assisting clinicians to make more appropriate decisions during labor. However, despite advances in signal processing and machine learning techniques, the analysis of fECG signals has still remained in its preliminary stages. In this work, we describe an algorithm to automatically locate QRS complexes in noninvasive fECG signals obtained from a set of four electrodes placed on the mother’s abdomen. The algorithm is based on an iterative decomposition of the maternal and fetal subspaces and filtering of the maternal ECG (mECG) components from the fECG recordings. Once the maternal components are removed, a novel merging technique is applied to merge the signals and detect the fetal QRS (fQRS) complexes. The algorithm was trained and tested on the fECG datasets provided by the PhysioNet/CinC challenge 2013. The final results indicate that the algorithm is able to detect fetal peaks for a variety of signals with different morphologies and strength levels encountered in clinical practice.

Foetal electrocardiogram (FECG) signal could assist the clinicians in making appropriate and timely decisions during pregnancy and labour since it contains information about the status of the foetus. The extraction and detection of the FECG signal from the composite abdominal signals of the mother with powerful and advance methodology is becoming a very important requirement in foetal monitoring. This paper illustrates the algorithm developed based on neural network approach to provide efficient and effective way of separating FECG signal from the abdominal ECG (AECG) signals. The FECG signal is isolated from the abdominal signal by back propagation neural network approach. The input signal is considered as maternal ECG (MECG) obtained from the thorax of the mother, and the target signal is abdominal signal (AECG) which has both MECG and FECG. The output of the network is subtracted from the target input (AECG). To reduce the difference between the input and target signal the weights have been updated every step, so that acceptable FECG signal can be obtained. To enhance the FECG signal, post-processing steps are followed which involve undecimated wavelet transform (UWT), thresholding and filtering technique.

Non-invasive fetal electrocardiography is still an open research issue. The recent publication of an annotated dataset on Physionet providing four-channel non-invasive abdominal ECG traces promoted an international challenge on the topic. Starting from that dataset, an algorithm for the identification of the fetal QRS complexes from a reduced number of electrodes and without any a priori information about the electrode positioning has been developed, entering into the top ten best-performing open-source algorithms presented at the challenge.In this paper, an improved version of that algorithm is presented and evaluated exploiting the same challenge metrics. It is mainly based on the subtraction of the maternal QRS complexes in every lead, obtained by synchronized averaging of morphologically similar complexes, the filtering of the maternal P and T waves and the enhancement of the fetal QRS through independent component analysis (ICA) applied on the processed signals before a final fetal QRS detection stage. The RR time series of both the mother and the fetus are analyzed to enhance pseudoperiodicity with the aim of correcting wrong annotations. The algorithm has been designed and extensively evaluated on the open dataset A (N = 75), and finally evaluated on datasets B (N = 100) and C (N = 272) to have the mean scores over data not used during the algorithm development. Compared to the results achieved by the previous version of the algorithm, the current version would mark the 5th and 4th position in the final ranking related to the events 1 and 2, reserved to the open-source challenge entries, taking into account both official and unofficial entrants. On dataset A, the algorithm achieves 0.982 median sensitivity and 0.976 median positive predictivity.

The automatic analysis of the electrocardiogram (ECG) begins, traditionally, with the detection of QRS complexes. Afterwards, useful information can be extracted from it, ranging from the estimation of the instantaneous heart rate to nonlinear heart rate variability analysis. A plethora of works have been published on this topic; consequently, there exist many QRS complex detectors with high-performance values. However, just a few detectors have been conceived that profit from the information contained in several ECG leads to provide a robust QRS complex detection. In this work, we explore the fusion of multi-channel ECG recordings QRS detections as a means to improve the detection performance. This paper presents a decentralized multi-channel QRS complex fusion scheme that optimally combines single-channel detections to produce a single detection signal. Using six different widely used QRS complex detectors on the MIT-BIH Arrhythmia and INCART databases, a reduction in false and missed detections was achieved with the proposed approach compared with the single-channel counterpart. Furthermore, our detection results are comparable with the performance of other multi-channel detectors found in the literature, showing, in turn, various advantages in scalability, adaptability, and simplicity in the system's implementationGraphical AbstractN QRS complex detectors simultaneously monitor N ECG channels. Once a detection occurs in a given channel, a 150 ms long window is opened to look for detections in other channels. Within this window, yn = + 1 if a QRS complex is detected and yn = - 1 otherwise. A coefficient α n, obtained during a training period and related to the detection performance in channel n, multiplies the detection signal yn, so that greater weights are assigned to ECG channels where single-channel detectors performed better. Finally, the binary detection decision (f ) is obtained from the comparison of the weighted sum of single-channel detections (z) with a fixed threshold (β).

Reliable detection of the QRS complex in either a normal or an abnormal ECG and its analysis is the first and foremost task in almost every ECG signal analysis system aimed at the diagnostic interpretation of ECG. Conventionally, detection of the QRS complex is accomplished using a rule-based/algorithmic approach. This work, uses the learn and generalize approach of an artificial neural network (ANN) for the detection of QRS complexes in either a normal or an abnormal ECG. This is followed by the analysis of the QRS complex to designate and measure the morphological components within the QRS complex in all 12 standard leads. An ANN has been developed to detect the QRS complex in ECG and trained, with the help of back propagation algorithm, on more than a hundred ECGs selected from the CSE Data Set-3. The trained ANN was tested on all the recordings of the CSE Data Set-3 and the sensitivity has been found to be 99·11%. Subsequent to the identification of the QRS complex, an analysis of this complex and measurement of peak amplitudes of the component waves is done. The results are validated using the CSE multilead measurement results. Both the QRS detection and the QRS analysis software developed in C-language have been successfully implemented on a PC-AT. The results are found to be in agreement with visual measurements carried out by medical experts.

In the electrocardiogram (ECG), the detection of QRS complexes is a fundamental step in the ECG signal processing chain since it allows the determination of other characteristics waves of the ECG and provides information about heart rate variability. In this work, an automatic QRS complex detector based on continuous density hidden Markov models (HMM) is proposed. HMM were trained using univariate observation sequences taken either from QRS complexes or their derivatives. The detection approach is based on the log-likelihood comparison of the observation sequence with a fixed threshold. A sliding window was used to obtain the observation sequence to be evaluated by the model. The threshold was optimized by receiver operating characteristic curves. Sensitivity (Sen), specificity (Spc) and F1 score were used to evaluate the detection performance. The approach was validated using ECG recordings from the MIT-BIH Arrhythmia database. A 6-fold cross-validation shows that the best detection performance was achieved with 2 states HMM trained with QRS complexes sequences (Sen = 0.668, Spc = 0.360 and F1 = 0.309). We concluded that these univariate sequences provide enough information to characterize the QRS complex dynamics from HMM. Future works are directed to the use of multivariate observations to increase the detection performance.

The localization accuracy of a fingerprint-based localization system is dependent on several factors, one of which is the accuracy and efficiency at which the fingerprint database is clustered. Most highly efficient and accurate clustering algorithms have high time-dependent computational complexity (CC), which tends to limit their practical applicability. A technique that has yet to be explored is the sequential hybridization of multiple low-time CC clustering algorithms to produce a single moderate-time CC clustering algorithm with high localization accuracy. As a result, this paper proposes a clustering algorithm with a moderate time CC that is based on the sequential hybridization of the closest access point (CAP) and improved k-means clustering algorithms. The performance of the proposed sequential hybrid clustering algorithm is determined and compared to the modified affinity propagation clustering (m-APC), fuzzy c-mean (FCM), and 2-CAP algorithms presented in earlier research works using four experimentally generated and publicly available fingerprint databases. The performance metrics considered for the comparisons are the position root mean square error (RMSE) and clustering time based on big O notation. The simulation results show that the proposed sequential hybrid clustering algorithm has improved localization accuracy with position RMSEs of about 54%, 77%, and 52%, respectively, higher than those of the m-APC, FCM, and 2-CAP algorithms. In terms of clustering time, it is 99% and 79% faster than the m-APC and FCM algorithms, respectively, but 90% slower than the 2-CAP algorithm. The results have shown that it is possible to develop a clustering algorithm that has a moderate clustering time with very high localization accuracy through sequential hybridization of multiple clustering algorithms that have a low clustering time with poor localization accuracy. Doi: 10.28991/ESJ-2024-08-02-02 Full Text: PDF

Purpose. Electrocardiogram (ECG) signal is a record of the electrical activity of the heart and contains important clinical data about cardiovascular-related misfunctioning. The goal of the present work is to develop an improved QRS detection algorithm for the detection of heart abnormalities. Methods. In this present work stationary wavelet transforms (SWT) based method has been proposed for precise detection of QRS complex with ‘sym2’ mother wavelet. The stationary wavelet transform is a systematic mathematical tool to decompose the signal without downsampling using scale analysis and provides high detection of QRS complex and accurate localization of signal components. In the proposed method four level of decomposition is applied and the initial thresholding value is computed by the maximum amplitude of scale one at level four in SWT coefficients without the zero-crossing amplitude detection method. The multi-layered dynamic thresholding method has been applied to detect the true R-peak values and locate the QRS complex in the ECG signal. Results. For evaluation of results, the presented methodology is assessed on MIT-BIH, QTDB, and Noise stress test databases. In MIT-BIH, the sensitivity = 99.88%, positive predictivity = 99.93%, accuracy = 99.80% and detection error rate = 0.18% is achieved. In NSTD database, sensitivity = 97.46%, positive predictivity = 94.20%, accuracy = 91.95% and detection error rate = 8.47% and in QTDB, sensitivity = 99.95%, positive predictivity = 99.90%, accuracy = 99.71% and detection error rate = 0.16% is executed. Conclusion. In the presented proposed methodology, the computation complexity is low and exhibits a simple technique rather than an empirical approach. The proposed technique corroborates the performance for the detection of QRS complex with improved accuracy.

Big data is technology that has the ability to manage very large amounts of data, in very fast time to allow real-time analysis and reactions. Several clustering methods which are used to group data are Fuzzy C-Means (FCM) and K-Means Clustering. K-Means Clustering algorithm is a method of partitioning existing data into two or more group. This research goal was to compare the performance of K-Means and Fuzzy C-Means algorithms in clustering data using big data technology. In this research, Hadoop and Hive were chosen the big data technology. The knowledge of Shia history on student and lecturer of Syarif Hidayatullah State Islamic University Jakarta were the data which used in this research, The testing was done by constructing application K-Means Fuzzy C-Means using Java language, Hadoop and Hive and then test the performance of K-Means and Fuzzy C-Means algorithms in data clustering. It compares both algorithms in terms of accuracy, execution time, and time complexity of the algorithms. In the application K-Means Fuzzy C-Means, evaluation were performed with data filter and the average accuracy difference result of K-Means and Fuzzy C-Means is 8.03% with the better accuracy owned by K-Means. The average execution time difference is 718.58 ms, which K-Means was faster than is Fuzzy C-Means. The time complexities of both algorithms have the same value O(n2) and the Big O equation resulted in an average difference of 93,568 with the smallest value on K-Means. Thus, K-Means algorithm is better than the Fuzzy C-Means in terms of accuracy, execution time, and the time complexity.