National Repository of Grey Literature 137 records found  1 - 10nextend  jump to record: Search took 0.01 seconds. 
Segmentation of ECG signals based on their quality
Roháček, Adam ; Smital, Lukáš (referee) ; Vítek, Martin (advisor)
This work is about ECG quality assessment. In the first part of this work I am introducing the reader to the theory of this topic. I am also explaining basic terms and possible methods of quality assessment. In the second part I am trying to solve the assessment by either creating an algorithm of my own or applying an existing algorithm. In the end I am testing the algorithm and judging the results.
Blood pressure estimation using smartphone
Šíma, Jan ; Vítek, Martin (referee) ; Němcová, Andrea (advisor)
This diploma thesis describes an experimental cuffless measurement of systolic and diastolic blood pressure (SBP and DBP) using only a smartphone. Photoplethysmographic signal (PPG), which was measured by the smartphone camera and phonocardiographic signal (PCG), which was captured by an external microphone in the mitral valve area, were used to estimate blood pressure (BP). The BP estimate was divided into 2 parts. The first was the regression estimation of BP and comparison of several machine learning (MLR) and convolutional neural network (CNN) methods according to the use of the color channel to extract PPG from the video. The second objective was the classification of BP into the category of normotension or hypertension. The PPG signal was filtered for extraction using a bandpass filter with finite impulse response (FIR) (0,5–5 Hz) followed by feature extraction. For estimation of vascular transit time (VTT) and cardiac ejection time (ET), two main cardiac echoes S1 and S2 were detected in the PCG signal. Furthermore, raw sections of PPG signals (RGB video channels) and PCG signals of different time lengths were used for the CNN models. Among the regression approaches, the most accurate algorithm was the support vector regression (SVR) method, which achieved acceptable error according to the standards of the Association for the Advancement of Medical Instrumentation (AAMI) and the British Hypertension Society (BHS) in experimental work. The mean absolute error (MAE) was determined to be 7.64±6.87 mmHg for SBP and 5.07±4.88 mmHg for DBP. The red channel was evaluated as the most appropriate color channel for extracting PPG from the video recordings for regression estimation. For classification, the AdaBoost algorithm with weak random forest (RF) classifiers proved to be the most reliable. It achieved an F1 score of almost 80 % on the PPG features extracted from the combination of red and green color channels of the video.
HRV analysis based on PPG signal
Martinů, Žaneta ; Vítek, Martin (referee) ; Smital, Lukáš (advisor)
The thesis deals with the detection of systolic and diastolic peaks of pulse waves in a photoplethysmographic database. The detectors are implemented in MATLAB. The following part of the thesis uses the signal delineation of the photoplethysmographic signal to determine pulse rate variability. The final part of the thesis evaluates the use of pulse rate variability and compares it to the heart rate variability.
P Wave Detection in Pathological ECG Signals
Šaclová, Lucie ; Černý, Martin (referee) ; Tkacz, Ewaryst (referee) ; Vítek, Martin (advisor)
Důležitou součástí hodnocení elektrokardiogramu (EKG) a následné detekce srdečních patologií, zejména v dlouhodobém monitorování, je detekce vln P. Výsledky detekce vln P umožňují získat ze záznamu EKG více informací o srdeční činnosti. Podle správně detekovaných pozic vln P je možné detekovat a odlišit patologie, které současné programy používané v medicínské praxi identifikovat neumožňují (např. atrioventrikulární blok 1., 2. a 3. stupně, cestující pacemaker, Wolffův-Parkinsonův-Whiteův syndrom). Tato dizertační práce představuje novou metodu detekce vln P v záznamech EKG během fyziologické a zejména patologické srdeční činnosti. Metoda je založena na fázorové transformaci, inovativních pravidlech detekce a identifikaci možných patologií zpřesňující detekci vln P. Dalším důležitým výsledkem práce je vytvoření dvou veřejně dostupných databází záznamů EKG s obsahem patologií a anotovanými vlnami P. Dizertační práce je rozdělena na teoretickou část a soubor publikací představující příspěvek autora v oblasti detekce vlny P.
Estimation of Respiration Activity from ECG Using Mechine Learning
Ondrejková, Eliška ; Vítek, Martin (referee) ; Plešinger, Filip (advisor)
This Bachelor thesis deals with methods to estimate respiration activity from ECG. For a better understanding of a subject, the anatomy and physiology of the respiratory and cardiovascular systems are described. Furthermore, several estimation methods are explained as well. A public dataset of ECG signals read from polysomnography was used in the practical part. An algorithm for estimation was implemented in the programming language Python using the PyTorch library. Finally, results are discussed and compared to other methods.
Analysis of the acute effect of cardiac resynchronization therapy on electrocardiogram
Holík, Jiří ; Vítek, Martin (referee) ; Pospíšil,, David (advisor)
This bachelor thesis deals with the non-pharmacological treatment of symptomatic heart failure, specifically cardiac resynchronization therapy. The introductory research develops the topic as a whole and prepares the author and the reader for the subsequent practical part. The latter focuses on the analysis of selected parameters that undergo acute change after pacemaker implantation. According to the instructions of the assignment, a functional pilot software for QRS complex detection, heart rate calculation and QRS complex dimensioning for some leads has been implemented. Furthermore, the heart rate variability in the frequency domain is analysed and the results are tabulated.
PPG signal quality assessment and heart rate estimation
Vargová, Enikö ; Vítek, Martin (referee) ; Němcová, Andrea (advisor)
This work deals with photoplethysmographic (PPG) signals, their processing, quality assessment, estimation of heart rate from PPG signals and the ability to record biological signals with smartphones. The aim of this work is to record PPG signals using a smartphone and reference ECG signals using an ECG recorder. The work also includes the design of two algorithms, one for signal quality assessment and the other for heart rate estimation from PPG signals.
ECG quality evaluation
Vencel, Michal ; Vítek, Martin (referee) ; Smital, Lukáš (advisor)
This seminar work deals with the topic of evaluating the quality of ECG signals. The introductory chapters explain the basic characteristics of ECG signals - measurement, the form of the measured signal, methods of analysis. The cardiac physiology and pathology is presented. The most common types of noise that occur in ECG signals are also mentioned. Further, the reader is acquainted with the importance of the issue of evaluating the quality of ECG signals. In the practical part of the work, two own methods for ECG quality evaluation are presented. First, a brief theoretical introduction to the techniques used in the creation of methoda is given, followed by a description of the principle of algorithms. In order to compare the functionality of the proposed methods, three more methods from other authors are presented. Their principle is briefly described. In the final chapter, all methods are subjected to functionality testing. The results are examined and all methods are compared with each other.
ECG based human authentication and identification
Waloszek, Vojtěch ; Smital, Lukáš (referee) ; Vítek, Martin (advisor)
In the past years, utilization of ECG for verification and identification in biometry is investigated. The topic is investigated in this thesis. Recordings from ECG ID database from PhysioNet and our own ECG recordings recorded using Apple Watch 4 are used for training and testing this method. Many of the existing methods have proven the possibility of using ECG for biometry, however they were using clinical ECG devices. This thesis investigates using recordings from wearable devices, specifically smart watch. 16 features are extracted from ECG recordings and a random forest classifier is used for verification and identification. The features include time intervals between fiducial points, voltage difference between fiducial points and PR intervals variability in a recording. The average performance of verification model of 14 people is TRR 96,19 %, TAR 84,25 %.
Compression and Quality Assessment of ECG Signals
Němcová, Andrea ; Tkacz,, Professor Ewaryst (referee) ; Kudrna,, Petr (referee) ; Vítek, Martin (advisor)
Ztrátová komprese signálů EKG je užitečná a v současnosti stále se rozvíjející oblast. Stále se vyvíjí nové a nové kompresní algoritmy. V této oblasti ale chybí standardy pro hodnocení kvality signálu po kompresi. Existuje tedy sice mnoho různých kompresních algoritmů, které ale buď nelze objektivně porovnat vůbec, nebo jen zhruba. V oblasti komprese navíc nikde není popsáno, zda mají na výkon kompresních algoritmů vliv patologie, popřípadě jaký. Tato dizertační práce poskytuje přehled všech nalezených metod pro hodnocení kvality signálů EKG po kompresi. Navíc bylo vytvořeno 10 nových metod. V rámci práce byla provedena analýza všech těchto metod a na základě jejích výsledků bylo doporučeno 12 metod vhodných pro hodnocení kvality signálu EKG po kompresi. Také je zde představen nový kompresní algoritmus „Single-Cycle Fractal-Based (SCyF)“. Algoritmus SCyF je inspirován metodou založenou na fraktálech a využívá jednoho cyklu signálu EKG jako domény. Algoritmus SCyF byl testován na čtyřech různých databázích, přičemž kvalita signálů po kompresi byla vyhodnocena 12 doporučenými metodami. Výsledky byly porovnány s velmi populárním kompresním algoritmem založeným na vlnkové transformaci, který využívá metodu „Set Partitioning in Hierarchical Trees (SPIHT)“. Postup testování zároveň slouží jako příklad, jak by měl vypadat standard hodnocení výkonu kompresních algoritmů. Dále bylo statisticky prokázáno, že existuje rozdíl mezi kompresí fyziologických a patologických signálů. Patologické signály byly komprimovány s nižší efektivitou a kvalitou než signály fyziologické.

National Repository of Grey Literature : 137 records found   1 - 10nextend  jump to record:
See also: similar author names
11 VITEK, Michal
2 Vítek, Marek
4 Vítek, Martin
4 Vítek, Matouš
11 Vítek, Michal
2 Vítek, Milan
3 Vítek, Miroslav
Interested in being notified about new results for this query?
Subscribe to the RSS feed.