|
|
Stresss and fatique detection in complex driver's data
Šimoňáková, Sabína ; Králík, Martin (referee) ; Mézl, Martin (advisor)
Main aim of our thesis is fatigue and stress detection from biological signals of a driver. Introduction contains information on published methods of detection and thoroughly informs readers about theoretical background necessary for our thesis. In the practical application we have firstly worked with a database of measured rides and subsequently chose their most relevant sections. Extraction and selection of features followed afterward. Five different classification models for tiredness and stress detection were used in the thesis and prediction was based on actual data. Lastly, the final section compares the best model of our thesis with the already published results.
|
|
|
Detection and localization of microbial colonies by means of deep learning algorithms
Čičatka, Michal ; Vičar, Tomáš (referee) ; Mézl, Martin (advisor)
Due to massive expansion of the mass spectrometry and constant price growth of the human labour the optimalisation of the microbial samples preparation comes into question. This master thesis deals with design and implementation of a machine learning algorithm for segmentation of images of microbial colonies cultivated on Petri dishes. This algorithm is going to be a part of a controlling software of a MBT Pathfinder device developed by the company Bruker s. r. o. that automates the process of smearing microbial colonies onto a MALDI target plates. In terms of this thesis a several models of neural networks based on the UNet, UNet++ and ENet architecture were implemented. Based on a number of experiments investigating various configurations of the networks and pre-processing of the training datatset there was chosen an ENet model with quadruplet filter count and additional convolutional block of the encoder trained on a dataset pre-processed with round mask.
|
|
|
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.
|
|
|
Segmentation of cardiac tissue fibrosis in MRI data
Sokol, Norbert ; Mézl, Martin (referee) ; Kolář, Radim (advisor)
Late gadolinium enhancement cardiovascular magnetic resonance imaging can be used to visualize pre-ablation fibrosis or post-ablation myocardial scar. This can significantly helps patients with myocardial fibrosis to determine region of fibrosis and for post-operative validation of intervention after radio-frequency catheter ablation. In this thesis, i introduce an algorithm for successful distinguish of fibrosis on datasets of patients with myocardial fibrosis, scanned at Faculty hospital at St. Anne’s University Hospital.
|
|
|
Text recognition with artificial neural networks
Peřinová, Barbora ; Hesko, Branislav (referee) ; Mézl, Martin (advisor)
This master’s thesis deals with optical character recognition. The first part describes the basic types of optical character recognition tasks and divides algorithm into individual phases. For each phase the most commonly used methods are described in the next part. Within the character recognition phase the problematics of artificial neural networks and their usage in given phase is explained, specifically multilayer perceptron and convolutional neural networks. The second part deals with requirements definition for specific application to be used as feedback for robotic system. Convolution neural networks and CNTK library for deep learning using algorithm implementation in .NET is introduced. Finally, the test results of the individual phases of the proposed solution and the comparison with the open source Tesseract engine are discussed.
|
|
|
Data Transfer Protocol for Mobile Control Unit for Transporting Lungs
Trávníčková, Hana ; Mézl, Martin (referee) ; Sekora, Jiří (advisor)
The aim of this thesis is a data transfer protocol implementation for a mobile control unit for transporting lungs. Apart from this thesis the data transfer protocol is used in AlveoPic project. The introductory part is focused on an anatomical and physiological background of a human respiratory system. Consequently it describes the i-Lung module and the mobile circulation module (MCM). It deals with the healthcare informatics interoperability standards with an emphasis to the ISO/IEEE 11073 standard. The subsequent part is represented by MCM’s simulator realization and design of a monitoring application. The final part aims at an analysis of the test cases for a monitoring application’s and a protocol framework’s control.
|
|
|
Laboratory exercises for ultrasound medical imaging
Jordánek, Tomáš ; Králík, Martin (referee) ; Mézl, Martin (advisor)
This thesis is about ultrasound imaging systems. In the beginning, there are described ultrasonic waves and principles of physics. Next part is about clinical use of ultrasound system. There are described modes of imaging and probes used in practise. Doppler systems are also mentioned. Next part is about evaluation of image. In practical part of my thesis I am evaluating quality of image produced by GE Vingmed Ultrasound System Five REM. From this part had been created a laboratory exercise about basics of working with ultrasound systems. Next semester, I worked with ultrasound produced by 3B Scientific. There were made several laboratory exercises for this ultrasound and they were tested. For scanning in B-mode was made simple construction. Last part was about creating own phantom.
|
|
|
Blood vessel segmentation in fundus images
Šťastný, Pavel ; Mézl, Martin (referee) ; Odstrčilík, Jan (advisor)
Segmentation blood vessel the local images of retinal is very important for evaluation and for diagnostics eye’s disease, especially diabetic retinopathy and glaucoma. This bachelor’s thesis is deal with segmentation blood vessel by classification methods. I used gabor filtrer as a classifier. First was created filter bank and then using the convolution applicator pan the image. At the end I compared all information with gold standard. Average values from score for healthy images were sensitivity 0,8340, specificity 0,8709 and accuracy score 0,8663.
|
|
|
Data analysis for quantitative MR relaxometry
Páralová, Hana ; Jiřík, Radovan (referee) ; Mézl, Martin (advisor)
Tato práce se zabývá implementací algoritmu pro analýzu dat pro kvantitativní relaxometrii magnetické rezonance. Magnetická rezonance (MR) je neinvazivní zobrazovací technika využívající magnetických vlastností atomových jader. Motivací pro využívání relaxačních parametrů tkání je nezávislost na MR skenerech či jednotlivých pacientech. V práci jsou popsány nezbytné teoretické základy MR mechanizmů a vzniku kontrastu v obrazech. S jejich využitím je navržen algoritmus v jazyce Python pro fitování relaxačních parametrů vzorku. Fitování probíhá podle exponencíálních modelových funkcí pro tři různé kombinace parametrů - individuální fitování T1 nebo T2 relaxačního času a simultánní fitování obou časů. Pro výpočet směrodatné odchylky fitovaných parametrů je použit lokálně linearizovaný model a dolní meze podle teorie Cramér-Rao. Výsledky práce byly úspěšně ověřeny na relaxometrii fixovaného potkaního mozku.
|
|
|
Kinetic and kinematic gait analysis using VICON system
Hrdličková, Alžběta ; Mézl, Martin (referee) ; Svozilová, Veronika (advisor)
The Vicon optoelectronic system can be used to analyze human walking. This measurement greatly helps to diagnose problems with the motion apparatus. This work deals with the use of this system for the measurement of kinematic and kinetic values of joints for lower body model. The main aim of the bachelor thesis is to compare the results of healthy patients and patients with cerebral palsy. The theoretical part deals with the description of the gait cycle from kinematics and kinetics, and also description of the device for the analysis. In the practical part, automatic detection of values is proposed, which were evaluated, compared and discussed in the last part.
|
guest ::
