|
|
3D Slicer Extension for Tomographic Images Segmentation
Chalupa, Daniel ; Jakubíček, Roman (referee) ; Mikulka, Jan (advisor)
This work explores machine learning as a tool for medical images' classification. A literary research is contained concerning both classical and modern approaches to image segmentation. The main purpose of this work is to design and implement an extension for the 3D Slicer platform. The extension uses machine learning to classify images using set parameters. The extension is tested on tomographic images obtained by nuclear magnetic resonance and observes the accuracy of the classification and usability in practice.
|
|
|
Ultrasonic Directional Speaker
Sedlák, Jiří ; Michalec, Jaroslav (referee) ; Mikulka, Jan (advisor)
The master´s thesis deals with theoretical research and practical application of the principle of spreading acoustic waves through nonlinear medium. The theoretical part describes five different types of amplitude modulation and their mathematic representation, which were verified by the program Matlab. Next, the impedance characteristic of ultrasound PZT transducer was measured and the design of PWM modulator and class D amplifier was described. The practical part of the master´s thesis contains the realization of the parametric loudspeaker assembled from the class D amplifier and the PWM modulator. In conclusion, the designed parametric loudspeaker was measured and the individual types of amplitude modulation were compared with respect to the total harmonic distortion of transmitted useful signal.
|
|
|
Operating parameters of LED light sources
Janík, Daniel ; Mikulka, Jan (referee) ; Havlíková, Marie (advisor)
The aim of the thesis is to introduce the basic photometric quantities and operating parameters of LED light sources, according to which the light sources are evaluated and compared. The thesis examines effects of high temperature and elevated stress on LED retrofits and a design of measurement methods to measure these influences. According to the proposed methods, nine samples of light sources were measured and compared to each other on a basis of the measurements. Comparison was made from the point of view of the energy as well as the quality of the produced light. The results were also compared to the parameters specified by the producers.
|
|
|
Advertisements In Textbooks: A New Medium?
Mikulka, Jan ; Vochocová, Lenka (advisor) ; Zezulková, Markéta (referee)
This master thesis Advertisements in Textbooks: A New Medium? covers the field of school textbooks for primary and secondary schools. Its aim is to analyse advertisements, which have become part of some textbooks. The thesis is also examining if the advertisements are in compliance with the Czech law. The project contains descriptive analysis of the found advertisements. It also comprises statements by the textbook publishers and by the Ministry of Education.
|
|
|
Evaluation of the Financial Situation in the Firm and Proposals to its Improvement
Gelnar, Jiří ; Mikulka, Jan (referee) ; Bartoš, Vojtěch (advisor)
Bachelor's thesis is focused on the evaluation of the financial position of the company Baťa, a.s. during the four years between 2005 and 2008. The results are taken from the company's financial statements for the period under consideration. The first part of the thesis is based on clear theory, which is important to the overall understanding of the financial position. Then secondly we introduce information about the firm and its neighbourhood in the form of basic factual information, and provide a SWOT analysis, a Porter's model and a 4P marketing mix analysis. In the third part of the thesis we provide information on the current implemented financial analysis position of the company and then most importantly in the final part there are proposals to help improve the financial position of the company on the basis of the information provided.
|
|
|
Fast signal processing
Rychlý, Ivo ; Langerová, Petra (referee) ; Mikulka, Jan (advisor)
Zvětšující se množství dat v moderním zpracování obrazu vyžaduje nový postupy v psaní algoritmů. Největší překážkou pro úspěšné zrychlení algoritmu je paralelizace a následná optimalizace. Programy jako CUDA a OpenCL s modifikovaným programovacím jazykem a rozhraním pomáhají s tímto problémem a otevírají paralelní zpracování širšímu okruhu lidí. V této práci zabývám základy zpracování obrazu a tomu jak paralelizace algoritmů může urychlit zpracování obrazu.
|
|
| |
|
|
Emerging Trends in Dendrochronology
Horáček, Tomáš ; Neuwirthová, Ludmila (referee) ; Mikulka, Jan (advisor)
Tato práce se zabývá popisem současných a experimentálních metod odběru vzorků pomocí presslerova nebozezu, výřezů z kmene, fotografie, rentgenu, počítačové tomografie a magnetické rezonance na poli dendrochronologického výzkumu. V práci jsou rozebírány destruktivní a nedesktruktivní metody odběru vzorků. Je také kladen důraz na původ vzorků: zdali je možno využít destruktivní metody nebo zdali je to nemožné jako v případě vzácných archeologických objektů. Dále popisuje standardní optometrickou metody a další experimentální metody fungujicí na principu kontranstního zpracování obrazu za účelem rozeznání letokruhů. V práci jsou také popsány různé druhy metod softwarového zpracovnání kde jako vstup slouží buď série dat nebo obraz letokruhů. Další rozdíly tvoří vymezené spektrum uvedených prací, některé práce se zaměřují na zpracování obrazu od píky tedy od pořízené fotografie až po hotové datovaní, některé však zajímá pouze úzký sektor dendrochronologie jako jsou například vady či špatně rozeznatelné letokruhy.
|
|
|
Methods for evaluation of quality of automotive filters
Sedlák, Jiří ; Drexler, Petr (referee) ; Mikulka, Jan (advisor)
This bachelor thesis deals with theoretical research, description and design of three individual methods of defective air filters detection. Individual methods are described and compared in terms of their technical difficulty and expected efficiency. These methods are optical test, acoustic test, pressure test and the method of detection of gas CO2. All researched methods were proved practically and the measurements of detection of defective air filters were taken. The defect of air filter was detected by use of optical test.
|
|
|
Segmentation of MR images using machine learning algorithms
Dorazil, Jan ; Mikulka, Jan (referee) ; Dvořák, Pavel (advisor)
This thesis concerns with magnetic resonance image segmentation using Random Forests algorithm. Employed technologies accomplishing the specified task include C++ progra- mming language with libraries ITK and OpenCV. This work descibes the technique of processing images from loading through preprocessing to the actual segmentation. The outcome from this work is a programme that automatically segmentates MR images of mouse’s head to the brain and the surroundings.
|
guest ::
RSS feed.