|
|
Ultrasound Simulation in Python
Černý, David ; Olšák, Ondřej (referee) ; Jaroš, Jiří (advisor)
k-Wave je MATLAB nástroj pro simulaci šíření zvukových vln. Cílem této práce je reimplementovat část nástroje k-Wave v jazyce Python se zaměřením na výpočetní výkon. Druhým cílem je formulace sady doporučení pro transformaci zdrojových kódu z jazyka MATLAB do jazyka Python, které by mohly přispět při dalším vývoji. Tato práce nejprve shrnuje klíčové funkce nástroje k-Wave, zkoumá technologie pro vysoce výkonné výpočty dostupné v jazyce Python a zdůrazňuje nejzásadnější aspekty transformace zdrojových kódů z jazyka MATLAB do jazyka Python. Druhá část práce se zabývá architekturou, testováním a měřením výkonu výsledné Python implementace. Výsledkem této práce je implementace trojrozměrné simulace šíření zvuku, která je kompatibilní s k-Wave. Nová implementace vylepšuje strukturu původního nástroje a poskytuje výkon srovnatelný s původním nástrojem, v určitých případech výkon původního balíku převyšuje.
|
|
|
Stress detection
Jindra, Jakub ; Vítek, Martin (referee) ; Němcová, Andrea (advisor)
Stress detection based on non-EEG physiological data can be useful for monitoring drivers, pilots, and also for monitoring of people in ordinary situation, where standard EEG monitoring is unsuitable. This work uses Non-EEG database freely available from Physionet. The database contains records of heart rate, saturation of blood oxygen, motion, a conductance of skin and temperature recorded for 3 type of stress alternated with relax state. Two final models were created in this thesis. First model for Binary classification stress/relax, second for classification of 4 different type of psychical state. Best results were reached using model created by decision tree algorithm with 8 features for binary classification and with 8 features for classification of 4 psychical state. Accuracy of final models is aproximately 95 % for binary model and 99 % for classification of 4 psychical state. All algorithms were implemented in Python.
|
|
|
Digital Audio Steganography
Kabelka, Petr ; Malaník, Petr (referee) ; Strnadel, Josef (advisor)
The field of steganography deals with concealing information with the goal of hiding their very existence. The goal of this work is to create a summary of existing digital audio steganography methods and implement some of them. This work presents easily extensible and usable multiplatform library for audio steganography written in the Python programming language and a program that uses it. At the end of this work are the implemented methods compared against each other and against the published methods. Because it is hard to find concrete implementations of various published methods, the presented library enables almost anyone to easily use the implemented steganographic methods and to continue working on research in this field without the need to reimplement all of them.
|
|
|
Ultrasound Simulation in Python
Černý, David ; Olšák, Ondřej (referee) ; Jaroš, Jiří (advisor)
k-Wave je MATLAB nástroj pro simulaci šíření zvukových vln. Cílem této práce je reimplementovat část nástroje k-Wave v jazyce Python se zaměřením na výpočetní výkon. Druhým cílem je formulace sady doporučení pro transformaci zdrojových kódu z jazyka MATLAB do jazyka Python, které by mohly přispět při dalším vývoji. Tato práce nejprve shrnuje klíčové funkce nástroje k-Wave, zkoumá technologie pro vysoce výkonné výpočty dostupné v jazyce Python a zdůrazňuje nejzásadnější aspekty transformace zdrojových kódů z jazyka MATLAB do jazyka Python. Druhá část práce se zabývá architekturou, testováním a měřením výkonu výsledné Python implementace. Výsledkem této práce je implementace trojrozměrné simulace šíření zvuku, která je kompatibilní s k-Wave. Nová implementace vylepšuje strukturu původního nástroje a poskytuje výkon srovnatelný s původním nástrojem, v určitých případech výkon původního balíku převyšuje.
|
|
|
Comparison of cryptography performance of microcontrollers ARM Cortex-A
Škurla, Tomáš ; Zeman, Václav (referee) ; Slavíček, Karel (advisor)
The bachelor thesis deals with the measurement of cryptographic performance of ARM Cortex-A series microcontrollers. The theoretical part focuses on the description of concepts of cryptography, while at the same time explaining the principles of operation of individual cryptographic systems. Afterwards, thesis also describes the inner workings of ARM processors, their historical development, support for cryptography and detection of said support within processors. This is followed by defining the metrics for testing, part of which includes enumerating the hardware used in the testing process, with the focus being on the cryptography acceleration and encryption support. This also includes a description of the planned environment and software used in the testing. The practical part includes a description of the actual preparation of the defined environment and its possible modifications within the individual testing needs. The thesis concludes with an evaluation of the processed data and subsequent drawing of conclusions
|
|
|
Visual inspection of component dimensions
Kadaňka, Jan ; Holoubek, Tomáš (referee) ; Matoušek, Radomil (advisor)
This master thesis deals with the comparison of an industrial system for object recognition and measurement with an affordable camera on the Raspberry Pie platform. The theoretical part briefly describes several methods for measuring dimensions, which are commonly used in industry, along with a general description of technical equipment for image recording. The next section describes 3 industrial systems for image analysis. The practical part of the work deals with the design of the measuring stand, the description of the technical equipment, the implementation of measurements using both platforms and the subsequent evaluation.
|
|
|
Weather Forecast Based on Different Sources
Hořák, Martin ; Kořenek, Jan (referee) ; Novotný, Tomáš (advisor)
Bachelor thesis deals with the weather forecast through the artificial neural network with backpropagation method. The forecast is based on data obtained from freely accessible services offering weather information. The created application downloads and saves the forecasts from servers and creates a new forecast. The results of the prediction are being compared with the reality and the original services.
|
|
|
Stress detection
Jindra, Jakub ; Vítek, Martin (referee) ; Němcová, Andrea (advisor)
Stress detection based on non-EEG physiological data can be useful for monitoring drivers, pilots, and also for monitoring of people in ordinary situation, where standard EEG monitoring is unsuitable. This work uses Non-EEG database freely available from Physionet. The database contains records of heart rate, saturation of blood oxygen, motion, a conductance of skin and temperature recorded for 3 type of stress alternated with relax state. Two final models were created in this thesis. First model for Binary classification stress/relax, second for classification of 4 different type of psychical state. Best results were reached using model created by decision tree algorithm with 8 features for binary classification and with 8 features for classification of 4 psychical state. Accuracy of final models is aproximately 95 % for binary model and 99 % for classification of 4 psychical state. All algorithms were implemented in Python.
|
|
|
3D reconstruction from multiple views
Sládeček, Martin ; Klečka, Jan (referee) ; Richter, Miloslav (advisor)
This thesis deals with the task of three-dimensional scene reconstruction using image data obtained from multiple views. It is assumed that intrinsic parameters of the utilized cameras are known. The theoretical chapters describe the basic priciples of individual reconstruction steps. Variuous possible implementaions of data model suitable for this task are also described. The practical part also includes a comparison of false keypoint correspondence filtering, implementation of polar stereo rectification and comparison of disparity map calculation methods that are bundled with the OpenCV library. In the final portion of the thesis, examples of reconstructed 3D models are presented and discussed.
|
|
|
Data Mining with Python
Krestianková, Tamara ; Burgetová, Ivana (referee) ; Zendulka, Jaroslav (advisor)
This thesis deals with principles of data mining process, available Python packages for data mining and a demonstration of Python script capable of data analyisis focused on classification techniques. Created classifiers are able to classify subjects into two groups - healthy people and people suffering from Parkinson's disease - based on their biomedical vocal analysis data.
|
guest ::
