A new method of Electrocardiogram (ECG) features extraction is proposed in this paper. The purpose of this study is to detect the main characteristics of the signal: P, Q, R, S, and T, then localize and extract its intervals and segments. To do so we first detect peaks, onsets and offsets of the signal's waveform by calculating the slope change (SC) coefficients and consequently, the peaks of the signal are determined. The SC coefficients are based on the calculation of the integral of two-scale signals with opposite signs. The simulation results of our algorithm applied on recordings of MIT-BIH arrhythmia electrocardiogram database show that the proposed method delineates the electrocardiogram waveforms and segments with high precision.

Conventional methods for determining the reproductive performance of sheep bred either after estrus synchronization during the breeding season or after induction of estrus/ovulation during the non-breeding season take a long time and may give misleading results due to the effect of environmental factors. Laparoscopic observations allow real-time monitoring of ovarian activity around estrus or ovulation. This study was aimed at assessing the superovulatory effects of follicle-stimulating hormone (FSH) and equine chorionic gonadotropin (eCG) treatments by laparoscopy during breeding (September-November, n=12) and non-breeding (April-June, n=12) seasons in Akkaraman sheep. In both seasons, after CIDR withdrawal, the ewes were injected either with 600 IU eCG or 300 μl (20 mg/ml) FSH twice at 12 hour intervals. Plasma P4, E2 and LH concentrations were determined at the time of intra-vaginal CIDR insertion (day 0) and then at its withdrawal (day 12), followed by 3 and 6 days of eCG or FSH injections. After 3 (first observation) and 6 (second observation) days of hormone injections, laparoscopy was performed to record ovarian activity in both seasons. The eCG increased (p<0.05) the numbers of large follicles (first observation) and CL (first and second observations) in the breeding season compared to FSH treatment. CL, small-moderate and large follicle numbers of eCG treated ewes were higher (p<0.05) than those of FSH at both observations in the non-breeding season. In the breeding season, eCG treated ewes had higher (p<0.05) plasma P4 (3 and 6 days after hormones injections) and E2 (3 days after hormones injections) concentrations than those of FSH. In conclusion, the results of the present study indicate that treatment with eCG during the non-breeding season can support ovarian activity, and thus increase ovulation rate and plasma hormone concentrations around induced estrus/ovulation in Akkaraman ewes.

Electrocardiography is an examination performed frequently in patients experiencing symptoms of heart disease. Upon a detailed analysis, it has shown potential to detect and identify various activities. In this article, we present a deep learning approach that can be used to analyze ECG signals. Our research shows promising results in recognizing activity and disease patterns with nearly 90% accuracy. In this paper, we present the early results of our analysis, indicating the potential of using deep learning algorithms in the analysis of both onedimensional and two–dimensional data. The methodology we present can be utilized for ECG data classification and can be extended to wearable devices. Conclusions of our study pave the way for exploring live data analysis through wearable devices in order to not only predict specific cardiac conditions, but also a possibility of using them in alternative and augmented communication frameworks.

Two-dimensional (2D) positive systems are 2D state-space models whose state, input and output variables take only nonnegative values. In the paper we explore how linear matrix inequalities (LMIs) can be used to address the stability problem for 2D positive systems. Necessary and sufficient conditions for the stability of positive systems have been provided. The results have been obtained for most popular models of 2D positive systems, that is: Roesser model, both Fornasini-Marchesini models (FF-MM and SF-MM) and for the general model.

Extraction of the foetal electrocardiogram from single-channel maternal abdominal signals without disturbing its morphology is difficult. We propose to solve the problem by application of projective filtering of time-aligned ECG beats. The method performs synchronization of the beats and then employs the rules of principal component analysis to the desired ECG reconstruction. In the first stage, the method is applied to the composite abdominal signals, containing maternal ECG, foetal ECG, and various types of noise. The operation leads to maternal ECG enhancement and to suppression of the other components. In the next stage, the enhanced maternal ECG is subtracted from the composite signal, and this way the foetal ECG is extracted. Finally, the extracted signal is also enhanced by application of projective filtering. The influence of the developed method parameters on its operation is presented.

One of the prime tool in non-invasive cardiac electrophysiology is the recording of an electrocardiographic signal (ECG) which analysis is greatly useful in the screening and diagnosis of cardiovascular diseases. However, one of the greatest problems is that usually recording an electrical activity of the heart is performed in the presence of noise. The paper presents Bayesian and empirical Bayesian approach to problem of weighted signal averaging in time domain which is commonly used to extract a useful signal distorted by a noise. The averaging is especially useful for biomedical signal such as ECG signal, where the spectra of the signal and noise significantly overlap. Using the methods of weighted averaging are motivated by variability of noise power from cycle to cycle, often observed in reality. It is demonstrated that exploiting a probabilistic Bayesian learning framework leads to accurate prediction models. Additionally, even in the presence of nuisance parameters the empirical Bayesian approach offers the method of theirs automatic estimation which reduces number of preset parameters. Performance of the new method is experimentally compared to the traditional averaging by using arithmetic mean and weighted averaging method based on criterion function minimization.

The continuous real-time monitoring of diverse physical parameters using biosignals like ECG and EEG requires the biomedical sensors. Such sensor consists of analog frontend unit for which low noise and low power Operational transconductance amplifier (OTA) is essential. In this paper, the novel chopper-stabilized bio-potential amplifier is proposed. The chopper stabilization technique is used to reduce the offset and flicker noise. Further, the OTA is likewise comprised of a method to enhance the input impedance without consuming more power. Also, the ripple reduction technique is used at the output branch of the OTA. The designed amplifier consumes 5.5 μW power with the mid-band gain of 40dB. The pass-band for the designed amplifier is 0.1Hz to 1KHz. The input impedance is likewise boosted with the proposed method. The noise is 42 nV/√H z with CMRR of 82 dB. All simulations are carried out in 180nm parameters.

The aim of this paper is to compare the efficiency of various outlier correction methods for ECG signal processing in biometric applications. The main idea is to correct anomalies in various segments of ECG waveform rather than skipping a corrupted ECG heartbeat in order to achieve better statistics. Experiments were performed using a self-collected Lviv Biometric Dataset. This database contains over 1400 records for 95 unique persons. The baseline identification accuracy without any correction is around 86%. After applying the outlier correction the results were improved up to 98% for autoencoder based algorithms and up to 97.1% for sliding Euclidean window. Adding outlier correction stage in the biometric identification process results in increased processing time (up to 20%), however, it is not critical in the most use-cases.

Obstructive Sleep Apnea is one common form of sleep apnea and is now tested by means of a process called Polysomnography which is time-consuming, expensive and also requires a human observer throughout the study of the subject which makes it inconvenient and new detection techniques are now being developed to overcome these difficulties. Heart rate variability has proven to be related to sleep apnea episodes and thus the features from the ECG signal can be used in the detection of sleep apnea. The proposed detection technique uses Support Vector Machines using Grid search algorithm and the classifier is trained using features based on heart rate variability derived from the ECG signal. The developed system is tested using the dataset and the results show that this classification system can recognize the disorder with an accuracy rate of 89%. Further, the use of the grid search algorithm has made this system a reliable and an accurate means for the classification of sleep apnea and can serve as a basis for the future development of its screening.

Epilepsy is a neurological disorder that causes seizures of many different types. The article presents an analysis of heart rate variability (HRV) for epileptic seizure prediction. Considering that HRV is nonstationary, our research focused on the quantitative analysis of a Poincare plot feature, i.e. cardiac sympathetic index (CSI). It is reported that the CSI value increases before the epileptic seizure. An algorithm using a 1D-convolutional neural network (1D-CNN) was proposed for CSI estimation. The usability of this method was checked for 40 epilepsy patients. Our algorithm was compared with the method proposed by Toichi et al. The mean squared error (MSE) for testing data was 0.046 and the mean absolute percentage error (MAPE) amounted to 0.097. The 1D-CNN algorithm was also compared with regression methods. For this purpose, a classical type of neural network (MLP), as well as linear regression and SVM regression, were tested. In the study, typical artifacts occurring in ECG signals before and during an epileptic seizure were simulated. The proposed 1D-CNN algorithm estimates CSI well and is resistant to noise and artifacts in the ECG signal.

In the diagnosis of many disease entities directly or indirectly related to disorders of respiratory parameters and heart disease, an important support would be to estimate the temporal changes in these parameters (most often respiratory wave (RW) and respiratory rate (RR)) on the basis the results of measurements of other physiological parameters of the patient. Such a possibility exists during ECG examination. The paper presents three methods for estimating RWand RR using ECG signal processing. The three procedures developed are shown: using Savitzky–Golay filtering (S-G), the ECG-Derived Respiration method (EDR) and the Respiratory Sinus Arrhythmia Analysis method (RSA). It must be clearly stated that the proposed methods are not designed to fully diagnose the patient’s respiratory function, but they can be applied to detect some conditions that are difficult to diagnose when performing an ECG, such as sleep-disordered breathing. The obtained results of the analysis were compared with those obtained from a dedicated measurement system developed by the authors. The second part of the paper will show the results of preliminary clinical verification of the developed analysis methods, taking into account the physiological parameters of the patient.

High resolution body surface potential maps and an equivalent current dipole model of the cardiac generator were used to assess the heart state in two abnormal conditions: WPW syndrome with single accessory pathway and local ventricular ischemia. Results of a simulation study and experimental verification of the method for both cardiologic abnormalities are presented. Single accessory pathway in WPW syndrome was simulated as initial ventricular activation at the atrio-ventricular ring. Using a current dipole model of the cardiac generator, the locus of arrhythmogenic tissue was assessed with a mean error of 11 mm. Experimental localization of the accessory pathway in a WPW patient was in good agreement with the invasively obtained site. Local repolarization changes were simulated as shortening of the myocytes action potentials in three regions typical for stenosis of main coronary arteries. Using surface QRST integral maps and dipolar source model, small subendocardial and subepicardial lesions of myocardium were inversely located with a mean error of 9 mm and larger transmural lesions with a considerable mean error of 17 mm. Extent and prevalence of subepicardial or subendocardial type of the lesion were reflected in the dipole moment and orientation. In experimental verification of the method, in 7 of 8 patients that underwent PCI of a single vessel, estimated equivalent current dipole position matched well the treated vessel. The results suggest that diagnostic interpretation of body surface potential maps based on dipolar source model could be a useful tool to assess local pathological changes in the heart.