Wyniki wyszukiwania - BazTech

1

Deep learning in the classification and recognition of cardiac activity patterns

Jeleń Łukasz, Ciskowski Piotr, Kluwak Konrad

International Journal of Electronics and Telecommunications

|

2024

|

Vol. 70, No. 1

79--85

EN

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.

2

Congestive heart failure detection based on Electrocardiomatrix Method with ECG Signal

Rao B. Mohan, Kumar Aman

Computer Assisted Methods in Engineering and Science

|

2023

|

Vol. 30, no. 3

291--304

EN

Congestive heart failure (CHF) is a prevalent, expensive to treat, and dangerous disease inwhich the pumping capacity of the heart muscle is reduced due to injury or stress. It causesmajor medical problems in humans and contribute to many diseases, thus increasing themortality rate. In a world with a growing population, there is a need for more precise andsimpler approaches to detect such conditions, which can prevent many diseases and lead toa lower mortality rate. The main goal here is to use electrocardiomatrix (ECM) approachto perform the task of detecting CHF. It is detected quickly and accurately with thisapproach, as ECM converts 2D electrocardiogram (ECG) data into a 3D-colored matrix.The approach is tested using ECG readings from the Beth Israel Deaconess Medical Center(BIDMC) CHF Database on the Internet (Physionet.org). The ECM outcomes of are thencompared to manual readings of ECG data. The ECM results achieved the accuracy of96.89%, the sensitivity of 97.53%, the precision of 99.1%, the F1-score of 97.76%, and thespecificity of 96.02% for CHF. This research shows that the ECM approach is a good wayfor machines and practitioners to interpret long-term ECG readings while maintainingaccuracy.

3

R peak determination using a WDFR algorithm and Adaptive threshold

Nguyen Thanh-Nghia, Nguyen Thanh-Hai, Ngo Ba-Viet

Applied Computer Science

|

2022

|

Vol. 18, no 3

19--30

EN

The determination of the R peak position in the ECG signal helps physicians not only to know the heart rate per minute, but also to monitor the patient’s health related to heart disease. This paper proposes a system to accurately determine the R peak position in the ECG signal. The system consists of a pre-processing block for filtering out noise using a WDFR algorithm and highlighting the amplitude of the R peak and a threshold value is calculated for determining the R peak. In this research, the MIT-BIH ECG dataset with 48 records are used for evaluation of the system. The results of the SEN, +P, DER and ACC parameters related to the system quality are 99.70%, 99.59%, 0.70% and 99.31%, respectively. The obtained performance of the proposed R peak position determination system is very high and can be applied to determine the R peak of the ECG signal measuring devices in practice.

4

Detection of Obstructive Sleep Apnea from ECG Signal Using SVM Based Grid Search

Valavan K. K., Manoj S., Abishek S., Gokull Vijay T. G., Vojaswwin P., Rolant Gini J., Ramachandran K. I.

International Journal of Electronics and Telecommunications

|

2021

|

Vol. 67, No. 1

5--12

EN

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.

5

Comparison of methods for correcting outliers in ECG-based biometric identification

Jun Su, Szmajda Miroslaw, Khoma Volodymyr, Khoma Yuriy, Sabodashko Dmytro, Kochan Orest, Wang Jinfei

Metrology and Measurement Systems

|

2020

|

Vol. 27, nr 3

387--398

EN

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.

6

Methods of extracting electrocardiograms from electronic signals and images in the Python environment

Zholmagambetova Bakhytgul, Mazakov Talgat, Jomartova Sholpan, Izat Adilzhan, Bibalayev Olzhas

Diagnostyka

|

2020

|

Vol. 21, No. 3

95--101

EN

High-quality signal processing of an electrocardiogram (ECG) is an urgent problem in present day diagnostics for revealing dangerous signs of cardiovascular diseases and arrhythmias in patients. The used methods and programs of signal analysis and classification work with the arrays of points for mathematical modeling that must be extracted from an image or recording of an electrocardiogram. The aim of this work is developing a method of extracting images of ECG signals into a one-dimensional array. An algorithm is proposed based on sequential color processing operations and improving the image quality, masking and building a one-dimensional array of points using Python tools and libraries with open access. The results of testing samples from the ECG database and comparing images before and after processing show that the signal extraction accuracy is approximately 95 %. In addition, the presented application design is simple and easy to use. The proposed program for analyzing and processing the ECG data has a great potential in the future for the development of more complex software applications for automatic analyzing the data and determining arrhythmias or other pathologies.

7

Heart work analysis by means of recurrence-based methods

Iwaniec J., Iwaniec M.

Diagnostyka

|

2017

|

Vol. 18, No. 4

89--96

EN

Currently, for the purposes of recorded ECG signals (electrocardiograms) interpretation, the classical methods involving analysis of geometrical properties of the recorded waveforms in time domain are used. Such an analysis consists in determining the values of parameters describing the heart rate and rhythm. However, these indicators can not be treated as an infallible criterion for diagnosis and, moreover, the limits of increasing the accuracy of ECG analysis by increasing the accuracy of determining its characteristic points have already been reached. Therefore, in the paper, for the purposes of analysis of registered ECG signals and acoustical recordings of heart work, it is proposed to use the recurrence plots and RQA analysis methods that consist in searching for the recurrence properties of the registered signals. Application of the recurrence-based methods is natural due to the cyclic character of the heart work while providing patterns characteristic for different cardiac dysfunctions supported by objective, quantitative measures will contribute to early, credible and reliable classification of cardiovascular dysfunction.

PL

Obecnie, do analizy zarejestrowanych sygnałów EKG, wykorzystywane są metody detekcji punktów charakterystycznych, czyli metody badania własności geometrycznych analizowanych sygnałów w dziedzinie czasu. Jednak wyznaczone parametry opisujące zmienność rytmu serca nie są niezawodnym kryterium rozpoznania choroby. Z tego względu, w artykule, do analizy zarejestrowanych sygnałów EKG zaproponowano łączne zastosowanie metod klasycznych (obecnie stosowanych metod badania własności geometrycznych EKG) oraz metod diagramów rekurencyjnych (RP) i analizy RQA, polegających na badaniu rekurencyjności trajektorii fazowych badanych układów. Zastosowanie metod badania własności rekurencyjnych do analizy sygnałów EKG jest naturalne ze względu na cykliczny charakter pracy serca, natomiast określenie cech dystynktywnych charakterystycznych dla różnych chorób serca przyczynia się do zwiększenia wiarygodności a także niezawodności diagnostyki i klasyfikacji chorób serca.

8

Badania wpływu układu monitorowania stanu kontaktu elektrody biomedycznej ze skórą pacjenta na mierzony sygnał elektrokardiograficzny

Marszałek Z., Gawędzki W., Turcza P., Bizoń P., Donath P.

Przegląd Elektrotechniczny

|

2015

|

R. 91, nr 5

72-75

PL

W pracy przedstawiono badania wpływu systemu monitorowania stanu kontaktu elektrod biomedycznych ze skórą na mierzony sygnał elektrokardiograficzny. Stan kontaktu elektrody biomedycznej określany jest na podstawie wartości mierzonej pojemności elektrycznej odizolowanych elektrod testowych umieszczonych w pobliżu elektrody biomedycznej. Pomiar pojemności elektrycznej odbywa się za pomocą przetwornika pojemność-częstotliwość, zintegrowanego konstrukcyjnie z elektrodami testowymi oraz z elektrodą biomedyczną.

EN

This paper presents the study of an electrode-skin contact state monitoring system's impact on the measured ECG signal. The electrodeskin contact state monitoring system is based on capacitance measurements between two isolated test electrodes, which are placed near the biomedical electrode plate. Capacitance measurement is performed indirectly by measuring the output frequency of a capacitance-to-frequency converter. The capacitance-to-frequency converter is integrated with biomedical electrode.

9

QRS complex morphologies identification by the Lipschitz exponents of Wavelet Transform

Jóśko A.

Przegląd Elektrotechniczny

|

2014

|

R. 90, nr 8

161-163

PL

Transformacje falkowe są narzędziem, za pomocą którego można otrzymać dokładny opis analizowanego sygnału. Zapis elektrokardiograficzny (EKG) nie jest tu wyjątkiem. Narzędziem pomocniczym są wykładniki Lischitza, dzięki którym z kolei można wyznaczyć miarę lokalnej regularności/kształtu sygnału. W artykule przedstawione zostały wyniki analizy możliwości wykorzystania wykładników Lipschitza do rozróżniania podstawowych morfologii zespołów QRS.

EN

Wavelet transform is the effective tool for detailed description of the analysed signal. The electrocardiography (ECG) signal is not the exception in this term. Lipschitz exponents represent an additional tool that can be used to define the measure of the local signal shape/regularity. There are results of the wavelet transform Lipschitz exponents analysis presented in the paper. The main goal was to find their usability in the task of different QRS complex types discrimination.

10

Adaptacyjna transmisja sygnału EKG z użyciem predykcji interwałów R-R za pomocą odpornej funkcji regresji

Kowalski P., Momot M., Stankiewicz A., Wiśniowski R., Różanowski K.

Elektronika : konstrukcje, technologie, zastosowania

|

2014

|

Vol. 55, nr 4

57-60

PL

W artykule przedstawiono koncepcję selektywnej transmisji sygnału elektrokardiograficznego pomiędzy rejestratorem znajdującym się na ciele osoby monitorowanej a urządzeniem mobilnym. Koncepcja ta zasadza się na możliwości oszczędności energii, niezbędnej do przetransmitowania sygnału, na drodze przesyłu jedynie jego wybranych fragmentów. Dla sygnału EKG, którego najważniejsze fragmenty składają się z załamków P-QRS-T, istotna informacja zawarta jest jedynie w pewnym otoczeniu czasowym punktu centralnego. To sugeruje poszukiwanie metod predykcji położenia punktów centralnych kolejnych cykli pracy serca w celu wyboru fragmentów przeznaczonych do transmisji. Zaproponowano wykorzystanie funkcji regresji w celu wyznaczenia położeń tych punktów na podstawie skończonej liczby wartości zarejestrowanych w niedawnej historii. Parametry funkcji regresji są dobierane za pomocą algorytmu odpornej estymacji.

EN

This paper presents the idea of selective transmission of EC G signal from recorder located on a monitorem persons body and mobile device. This concept is based on ability of sparing energy sufficient for transmitting signal, because only the most relevant parts of it are selected for transmission. This part is located in neighbaourhood of fiducial point which suggests looking for methods of predicting these points in subsequent heart beat cycles. Authors suggest using robust regression function for the purpose of R-R intervals prediction, based on final history of these values recorded in nearest past.

11

An adaptive level dependent wavelet thresholding for ECG denoising

Awal M. A., Mostafa S. S., Ahmad M., Rashid M. A.

Biocybernetics and Biomedical Engineering

|

2014

|

Vol. 34, no. 4

238--249

EN

This paper describes the research carried out to eliminate the noise found in ECG signal and cardiac rhythm. For this, ECG signals were collected carefully from BIOPAC data acquisition system and MIT-BIH database. MIT-BIH noise stress test database was used for generating realistic noises. In addition, to get a better denoised ECG, Symlet wavelet was chosen because its scaling function is closely related to the shape of ECG. For denoising ECG signal, a novel modified S-median thresholding technique is proposed and evaluated in this paper. The optimal Symlet wavelet of order 6 and decomposition level of 8 are attained for modified S-median thresholding technique. The evaluation results showed that the proposed system performed better than S-median and other existing techniques in the time domain. The frequency domain analysis also showed the preservation of important phenomena of ECG. The scalogram difference of 0.004% indicates the well preservation of time–frequency information.

12

Performance comparison of wavelet thresholding techniques on weak ECG signal denoising

Üstündağ M., Şengür A., Gökbulut M., Ata F.

Przegląd Elektrotechniczny

|

2013

|

R. 89, nr 5

63-66

EN

The Electrocardiogram (ECG) signal is a biological non-stationary signal which contains important information about rhythms of heart. ECG signals can be buried by various types of noise. These types can be electrode movement, strong electromagnetic effect and muscle noise. Noisy ECG signal has been denoised using signal processing. This paper presents a weak ECG signal denoising method based on intervaldependent thresholds of wavelet analysis. Several experiments were conducted to show the effectiveness of the interval-dependent thresholding method and compared the results with the soft and hard wavelet thresholding methods for denoising. The results are evaluated by calculating the root mean square error and the correlation coefficient.

PL

W artykule przedstawiono metodę odszumiania sygnałów elektrokardiografu w oparciu o analizę falkową. W rozwiązaniu zastosowano progowanie przedziałowo-zależne. Na podstawie poczynionych eksperymentów oraz wyznaczonych wartości RMS błędu i współczynnika korelacji wykazano jego skuteczność. Dodatkowo dokonano porównania otrzymanych wyników z działaniem metod miękkiego i twardego progowania falkowego.

13

An application of the Lp-norm in robust weighted averaging of biomedical signals

Pander T., Przybyła T., Czabański R.

Journal of Medical Informatics & Technologies

|

2013

|

Vol. 22

71--78

EN

Averaging is one of the basic methods of statistical analysis of experimental data where the response of the system is periodic or quasi-periodic. As long as the noise are Gaussian, the standard averaging leads to good results and effective noise reduction. However, when the distortions have impulsive nature, then such an approach leads to a deterioration of the system. In this case the robust methods should be applied which are characterized by resistance to a statistical sample spoken. In this work a robust averaging method based on the minimization of a scalar criterion function using a Lp-norm functions are presented. The effectiveness of the proposed method was tested in an averaging periods aligned ECG signal cycles in the presence of impulse noise.

14

Układ detekcji zespołów QRS w sygnale EKG do synchronizacji sztucznej komory wspomagania pracy serca

Malcher A., Pietraszek S., Komorowski D.

Elektronika : konstrukcje, technologie, zastosowania

|

2013

|

Vol. 54, nr 9

58-61

PL

Urządzenia do sztucznego wspomagania pracy serca wymagają synchronizacji z odpowiednią fazą cyklu pracy serca pacjenta. W artykule przedstawiono opis konstrukcji wzmacniacza sygnału EKG i detektora zespołów QRS przeznaczonego do współpracy z takim systemem. Układ detektora zrealizowano wykorzystując programowalną matrycę analogową typu AN231E04, natomiast wzmacniacz sygnału EKG z przetwornikiem A/C oparto na programowalnym układzie ADS 1298. Dzięki użyciu elementów programowalnych i wykorzystaniu możliwości dynamicznej rekonfigurowalności matrycy analogowej, uzyskano pożądane cechy detektora takie jak: małe opóźnienie detekcji zespołów QRS, automatyczną regulację wzmocnienia i możliwość zmiany stałej czasowej na drodze programowej. Badania układu prototypowego potwierdziły wysoką skuteczność detekcji zespołów QRS dla przebiegów EKG zarejestrowanych z elektrod nasercowych.

EN

Cardiac assist devices require synchronization with the proper phase of the heart cycle. This paper presents an ECG amplifier and QRS complexes detector designed for application in a ventricular assist device. The ECG amplifier with the A/D converter was built using ADS 1298 - low-power, 8-channel, 24-bit analog front-end for biopotential measurements. The analog path of the QRS complexes detector was implemented in a Field Programmable Analog Array (FPAA) AN231E04. The dynamic reconfigurability of the FPAA makes it possible to obtain desired features such as: the automatic gain control, low time delay of the QRS detection and automatic time constant correction function. The research works on the prototype circuit proved high detection efficiency for the real ECG signals registered from the epicardial electrodes.

15

Porównanie metod ważonego uśredniania sygnału elektrokardiograficznego

Momot A.

Studia Informatica

|

2012

|

Vol. 33, nr 2A

567-580

PL

Ważone uśrednianie jest jedną z metod pozwalającą na redukcję poziomu zakłóceń w sygnałach o charakterze pseudocyklicznym, których przykładem jest sygnał EKG. Artykuł przedstawia kilka metod, w których do wyznaczania odpowiednich wag stosowany jest aparat analizy matematycznej oraz podejście statystyczne. Skuteczność działania tych metod przebadano dla zaszumionego sygnału ANE 20000.

EN

Weighted averaging is a method that allows to reduce the level of interference in the quasi-cyclic signals such as the ECG signal. This paper presents several methods, in which to determine the appropriate weights is used apparatus of mathematical analysis as well as the statistical approach. The performance of these methods were tested for the noisy signal ANE 20000.

16

Application of coherence function for calculating time shifts between axial corneal displacements and electrical heart activity

Danielewska M., Kowalska M., Kasprzak H.

Biocybernetics and Biomedical Engineering

|

2011

|

Vol. 31, no. 1

17-25

EN

The heart activity is one of the most important factors influencing the ocular pulsation. It is known that the high correlation between axial corneal displacements and cardiovascular system activity exists. However, phase relationships between those factors are still unknown. The main goal of the research was to measure noninvasively longitudinal corneal apex displacement (LCAD) of the left eye, applying an ultrasonic sensor. Synchronically, the electrical heart activity (ECG) was recorded in Einthoven's triangle. To find phase dependencies between these signals the coherence function was used. It is observed that coherence value, computed between the first five harmonics of both signals, is different for shifted signals along each other. Therefore, the time delay between the ECG and LCAD signals, for which particular harmonic achieves the maximum of coherence function, was examined. It can be noticed that for increasing number of the signals' harmonic, the time delay between considered signals decreases. This tendency is clear for both of examined subjects. To receive more information about this phenomenon more subjects should be measured and the statistical test should be introduced to calculate the time delay values. The presented noninvasive method might be helpful in the future for measuring the IOP pulse and estimating hemodynamic status of the eye.

17

Ważone uśrednianie sygnału EKG wykorzystujące rozmyty podział sygnału oraz wnioskowanie Bayesowskie

Momot A.

Studia Informatica

|

2009

|

Vol. 30, nr 2A

287-297

PL

Akwizycja sygnału EKG wymaga tłumienia zakłóceń, co w przypadku sygnałów quasi-cyklicznych może być dokonywane przez ich uśrednianie. W warunkach rzeczywistych obserwuje się zmienność szumu z cyklu na cykl, co stanowi motywację dla stosowania metod ważonego uśredniania. W artykule proponuje się nową metodę uśredniania przy użyciu rozmytego podziału sygnału i bayesowskiego wnioskowania.

EN

cquisition of ECG signals needs noise attenuation which, in case of quasi-cyclic signals, may be made by means of averaging. In reality the variability of noise power from cycle to cycle is observed, which constitutes a motivation for using methods of weighted averaging. This paper proposes a new weighted method incorporating fuzzy partitioning of the signal and Bayesian inference.

18

Analiza czasowo-częstotliwościowa sygnału EKG

Pieniężny A.

Biuletyn Wojskowej Akademii Technicznej

|

2009

|

Vol. 58, nr 1

269-279

PL

Sygnały biomedyczne stanowią bardzo szczególną klasę sygnałów zarówno ze względu na ich strukturę, jak i szczególne podejście do ich analizy. Są one sygnałami niestacjonarnymi. Podstawowe metody analizy tego typu sygnałów obejmują analizę czasową i częstotliwościową, realizowane rozdzielnie. Rozdzielność analizy czasowej i częstotliwościowej sygnałów biomedycznych nie pozwala na pełną diagnozę z uwagi na zmienność ich struktury częstotliwościowej w czasie. Artykuł przedstawia pewne wyniki czasowo-częstotliwościowej analizy sygnału EKG.

EN

Biomedical signals are specific type of signals due to their structure and specific approach to their analysis. They are usually non-stationary signals. Basic methods of analysis include time and frequency analyses performed separately. Frequency structure of biomedical signals varies in time so, patient diagnose could be better when time-frequency analysis concept will be applied. The paper presents some results of time-frequency analysis of ECG signal.

19

Weighted averaging of ECG signals based on partition of input set in time domain

Momot A., Momot M., Łęski J.

Journal of Medical Informatics & Technologies

|

2007

|

Vol. 11

165--170

EN

The paper presents new approach to problem of signal averaging 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. In reality can be observed variability of noise power from cycle to cycle which is motivation for using methods of weighted averaging. Performance of the new method, based on partition of input set in time domain and criterion function minimization, is experimentally compared with the traditional averaging by using arithmetic mean, weighted averaging method based on empirical Bayesian approach and weighted averaging method based on criterion function minimization.

20

Characteristic points detection in ECG signal using Bayesian learning and fuzzy system

Momot M., Momot A.

Journal of Medical Informatics & Technologies

|

2007

|

Vol. 11

171--176

EN

Characteristic points detection such as beginnings and ends of P-wave, T-wave or QRS complex is one of primary aims in automated analysis of ECG signal. The paper presents one possible approach based on Bayesian inference to design of kernel based classifier. The classification function is constructed using the probability distribution function of standard normal distribution and independent Gaussian random variables. The parameters of such variables are computed using iterative Expectation-Maximization algorithm. This approach is used to calculate parameters of classification function to modelling Takagi-Sugeno-Kang fuzzy systems. Numerical experiment of characteristic points detection in ECG signal using CTS database is also presented.