|
|
Advanced scoring of sleep data
Jagošová, Petra ; Novotná, Petra (referee) ; Ronzhina, Marina (advisor)
The master´s thesis is focused on advanced scoring of sleep data, which was performed using deep neural network. Heart rate data and the movement information were used for scoring measured using an Apple Watch smartwatch. After appropriate pre-processing, this data serves as input parameters to the designed networks. The goal of the LSTM network was to classify data into either two groups for sleep and wake or into three groups for wake, Non-REM and REM. The best results were achieved by network doing classification of sleep vs. wake using the accelerometer. The statistical evaluation of this best-designed network reached the values of sensitivity 71,06 %, specificity 57,05 %, accuracy 70,01 % and F1 score 81,42 %.
|
|
|
Detection of poorly differentiated cardiac arrhythmias
Kantor, Marek ; Ronzhina, Marina (referee) ; Novotná, Petra (advisor)
This thesis focusses on the detection methods of atrial fibrilation, atrial flutter and sinus rhythm from ECG. Thesis also concentrate on the description of this arrhythmias and the learning algorithms used. In this thesis are implemented several classification approaches. For extraction of features is used convolution neural network and classification artifitial neural network. Selected 1D CNN method achived classification accuracy global F1 - score is 91 %. Moreover, the proposed CNN optimized with GA appears to be fast shallow network with better accuracy than the deep network. Created model are used for classification other type of arrhythmias too.
|
|
|
Apartment Building
Novotná, Petra ; Komínková, Kateřina (referee) ; Čupr, Karel (advisor)
This diploma thesis solver the newly apartment building in Kuřim. It is a building with tree floors and basemet. The claccing of Porotherm 300mm and is insulated by contact insulation. The roofs are flat. The windows are plastic. In the basement asre garages, cellars, technical room and bicycle room. The other floors are flats.
|
|
|
Deep-learning based localization of cardiac arrhythimas in ECG
Khaliullina, Sabina ; Novotná, Petra (referee) ; Ronzhina, Marina (advisor)
The thesis deals with the localization and classification of atrial atrial fibrillation. In Python, a detection method using convolutional neural networks with multi-instance learning (MIL) and the method of local maxima for localization were implemented. Segments from two ECG leads were used. In the binary classification using the first subset and subsequent post processing, the F1 score reached 100 %, in the classification using the second subset 92 %. In the discussion and conclusion of the work, the success of classification and localization was evaluated, the achieved results were discussed and compared the with the results of other authors.
|
|
|
Segmentation of intracardial ECG
Řehoř, Jan ; Ronzhina, Marina (referee) ; Novotná, Petra (advisor)
This master´s thesis deals with the segmentation of intracardiac ECG recordings and is divided into several parts. The first part is connected with a theoretical acquaintance with the issue, such as how the heart works, what is an intracardiac ECG and a convolutional neural network. Other parts of the work are already formed by the practical part, ie, signal annotation and model design automatically segmenting the intracaridal record. After the practical part, the evaluation of the results of the solution continues, comparison with the solution of third parties and with foreign studies dealing with a similar topic. The last part of the work is a discussion and conclusion, which summarizes the results of the work.
|
|
|
Premature atrial contraction detection in ECG
Mistrová, Jana ; Ronzhina, Marina (referee) ; Novotná, Petra (advisor)
This thesis discuses detection of premature atrial contraction from ECG. In the first part, thesis describes electrocardiogram, cardiac conduction system and extrasystoles. Extrasystoles are premature contraction caused by ectopic heartbeats. Next part is devoted to signal preprocessing, the feature description methods, reduction of feature vector and methods of classification. Realized method and results of classifier are discused in the last part.
|
|
|
Detection of premature ventricular contractions in ECG
Kantor, Marek ; Ronzhina, Marina (referee) ; Novotná, Petra (advisor)
This thesis focusses on the detection methods of extrasystoles from ECG and description of electrocardiogram, cardiac conduction system, extrasystoles and ventricular tachycardia. Extrasystoles are premature ventricular contraction caused by ectopic heartbeats. Classification is based on signal preprocessing, detection of R peak, the heartbeat segmentation, the feature description methods, normalization of features and the learning algorithms used. Selected and realized methods achieved classification accuracy ACC = 98 %, sensitivity SE = 100 % and specificity SP = 96,1 %. Gained features are also used for detection bundle branch block.
|
|
|
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.
|
|
|
Assessment of chosen aromatic compounds in cosmetics
Novotná, Petra ; Souralová Popelková, Miriam (referee) ; Vítová, Eva (advisor)
This master thesis deals with the assessment of selected fragrant substances in cosmetic products. At the beginning the occurrence, methods of acquiring and application of these substances is described. They are essential components primarily in cosmetic products, however they can cause an allergic reaction in sensitive individuals. The theoretical part of this thesis also describes the cause and the progress of these undesirable effects. There are several hundreds, up to thousands fragrant substances used in the perfume industry, from which 26 was designated by the European regulations as potential allergenic fragrant substances and their content is regulated. Legislative standards as well as the overview of the methods used to determine these fragrances are given here. The experimental part is focused on the development and validation of the separation methods for determining of the selected and potentially allergenic fragrant substances. The method used was a solid phase microextraction using Carboxen/Polydimethylsiloxane fiber combined with a gas chromatography coupled to a flame ionization detector (SPME-GC-FID). Amylcinnamyl alcohol, benzyl alcohol, cinnamyl alcohol, coumarin, lyral, ?-isomethyl ionone were among the determined allergenic substance. Consequently, this method was also applied on 10 selected cosmetic products specimens, in which the linalool and geraniol were identified as the most common allergenic substances.
|
|
|
HRV analysis in the context of daily activities
Indrák, Václav ; Smital, Lukáš (referee) ; Novotná, Petra (advisor)
The aim of this bachelors thesis is to measure ECG recordings on voulenteers, and following analysis of HRV from these recordings. It persues the explanation of basic metrics used to evaluate HRV, used both in clinical and scientific practice and their following programming implementation in Matlab environment to achieve the most accurate results possible, which are than assessed.
|
guest ::
RSS feed.