|
|
Interpreting the learning process of an atrial fibrillation classifier
Lichtblauová, Anna ; Ředina, Richard (referee) ; Novotná, Petra (advisor)
In the theoretical part of the bachelor thesis the problems of atrial fibrillation (AF) detection and principles of convolutional neural networks (CNN) are discussed. Next, two classifiers were created in the practical part. The first was designed to classify sinus rhythm, atrial fibrillation and other pathologies, while the second further distinguished the category "atrial fibrillation" according to whether it was present in the whole recording or only in a part of it. The resulting accuracies are 82.12 \% and 85.14 \% for the first and second classifiers, respectively.
|
|
|
Advanced sleep quality estimation
Benáček, Petr ; Ředina, Richard (referee) ; Filipenská, Marina (advisor)
This thesis deals with the assessment of sleep quality using modern deep learning methods. The thesis describes metrics for automatic classification of sleep stages. A selected database of sleep data is discussed. Due to the low number of data in the wakefulness phase, different methods of data augmentation are described and implemented. Models based on 1D convolutional networks are the basis for the classification. As a result, models for binary classification and classification of 3 and 4 sleep phases are prepared. Finally, sleep quality metrics are calculated using these models and the results are compared with the literature.
|
|
|
Analysis of time-frequency characteristics of signals
Vitouš, Jiří ; Ředina, Richard (referee) ; Poměnková, Jitka (advisor)
This thesis focuses on time-frequency analysis of discrete signals. The aim of this work is to compare the most well known methods for spectro/scalegram estimation. The two main topics discussed are: The compromise between time and frequency resolution and the effect of noise in input data on the quality of estimated spectrograms. To achieve this a database has been created. This database consists of real and artificial signals on which the analysis can be performed and evaluated. This database is used in created demonstration application. This application is also used in a created laboratory task.
|
|
|
Clustering of ECG cycles
Ředina, Richard ; Smíšek, Radovan (referee) ; Ronzhina, Marina (advisor)
The bachelor thesis explores the aplication of cluster analysis on diferent ECGs in order to create a reliable algorithm for detecting different QRS complexes. Algorithm comprises filtration, R-wave positions adjustment, model cycle creation and comparasion based on mean square error and correlation. Both, correlation and mean square error, become data for k-means clustering. The number of clusters is derived from silhouette values for diferent numbers of clusters.
|
|
|
Algorithms for improving the detection of selected cardiac arrhythmias
Šandová, Hana ; Ředina, Richard (referee) ; Novotná, Petra (advisor)
The work deals with the generation of ECG arrhythmias that are underrepresented in databases. The theoretical part of the thesis is devoted to a literature search of academic publications that deal with the classification of arrhythmia by using deep learning and data augmentation metod for ECG. The practical part of the thesis deals with noise generator, because adding noise to signals could make the dataset richer. Functions for augmentation of atrial flutter and 3rd and 2nd atrioventricular block were created. It has been tried generation of 2nd atrioventricular block using generative adversarial networks (GAN). Deep learning-based ECG classifiers were used for evaluating the efficiency of the proposed technique in generating synthetic ECG data.
|
|
|
Atrial fibrillation model
Ředina, Richard ; Smíšek, Radovan (referee) ; Ronzhina, Marina (advisor)
The aim of this master thesis is to create a 3D electroanatomical model of a heart atria, which would be able to perform atrial fibrillation. To control the model, the differential equations of the FitzHugh-Nagumo model were chosen. These equations describe the change of voltage on the cell membrane. The equations have established parameters. The modification of them leads to changes in the behavior of the model. The simulations were performed in the COMSOL Multiphysics environment. In the first step, the simulations were performed on 2D models. Simulations of healthy heart, atrial flutter and atrial fibrillation were created. The acquired knowledge served as a basis for the creation of a 3D model on which atrial fibrillation was simulated on the basis of ectopic activity and reentry mechanism. Convincing results were obtained in accordance with the used literature. The advantages of computational modeling are its availability, zero ethical burden and the ability to simulate even rarer arrhythmias. The disadvantage of the procedure is the need to compromise between accuracy and computational complexity of simulations.
|
|
|
Epidemiological modeling of Covid-19
Motlíčková, Klára ; Ředina, Richard (referee) ; Mézl, Martin (advisor)
This bachelor thesis deals with matematical compartment modeling of the COVID-19 pandemic. The basic epidemiological models are presented and six studies that deal with the behavior of the SARS-CoV-2 virus under different conditions are presented. On the SIR model are estimated parameters for first and fourth wave of the epidemic, using algorithm in MATLAB is made optimalization for all the waves of epidemic in the Czech Republic and also for the fourth wave on the SEIR model. The impact of antiepidemic measures is modelled on the SIR model.
|
|
|
Detection of selected cardiac arrhythmias in ECG
Němečková, Karolína ; Ředina, Richard (referee) ; Ronzhina, Marina (advisor)
This thesis deals with classification of ECG records focusing on less classifiable arrhythmia (atrial flutter, atriventricular block I. and II. degree). In the theoretical part of the thesis deep learning used in classification of ECG records with a focus on the convolutional neural networks are described. The database of ECG records with a brief description of detected arrhythmias is further described. The practical part implements the proposed convolutional neural network in the Python environment. The evaluation of the arrhythmia detection quality was done using mainly the F1 score. The results were discussed at the end of the thesis.
|
|
|
Automatické měření efektivní refrakterní periody srdeční tkáně
Ředina, Richard ; Filipenská, Marina
Elektrofyziologické vyšetření jako jedna z možností léčby arytmií je i v dnešní době stále časově náročný výkon. S cílem snížení této časové zátěže prezentujeme vyvinutý algoritmus, který z měřeného EKG automaticky určuje efektivní refrakterní periodu (ERP) tkáně. Algoritmus sestává z především filtrace a detekce lokálních extrémů v signálech. Algoritmus byl testován na interní databázi signálů získaných od deseti pacientů, kteří podstoupili elektrofyziologické vyšetření. Výstup algoritmu se shodoval s elektrofyziologem stanovenou ERP v devíti z deseti případů (σ = 6 ms). Pro svou relativní úspěšnost a nenáročnou implementaci slibuje možné využití v real-time aplikaci během vyšetření, při kterém by mohl plně automatizovat a tím i urychlit stimulační protokoly.
|
|
|
Spatial-temporal epidemiologic models of Covid-19
Schubert, Richard ; Ředina, Richard (referee) ; Mézl, Martin (advisor)
This work aims to establish a fundamental framework for studying spatially diffusive models that describe the dynamics of infectious disease spread with constant parameters in a homogeneous domain. Initially, compartmental models and their extension to spatial domains are examined, followed by the theory of metapopulation models, where the degree of coupling between populations and the overall reproductive number R0 is discussed. Furthermore, the relationship between R0 and the shape of the spatial distribution of infected individuals in a simple diffusive SIR model is modeled. The influence of Neumann boundary conditions versus Dirichlet boundary conditions on R0 is demonstrated. In the second part of the work, selected findings and conclusions of studies that applied models in the spatiotemporal domain to analyze and predict the COVID-19 pandemic are summarized. In the third part of the work, a model with diffusive and metapopulation elements is fitted to epidemiological data from Lombardy in 2020, and the suitability of this approach is discussed.
|
guest ::
RSS feed.