|
|
The GPU Based Acceleration of Neural Networks
Šimíček, Ondřej ; Jaroš, Jiří (referee) ; Petrlík, Jiří (advisor)
The thesis deals with the acceleration of backpropagation neural networks using graphics chips. To solve this problem it was used the OpenCL technology that allows work with graphics chips from different manufacturers. The main goal was to accelerate the time-consuming learning process and classification process. The acceleration was achieved by training a large amount of neural networks simultaneously. The speed gain was used to find the best settings and topology of neural network for a given task using genetic algorithm.
|
|
|
The GPU Accelerated Optimisation of the Water Management Systems
Marek, Jan ; Petrlík, Jiří (referee) ; Jaroš, Jiří (advisor)
Subject of this thesis is optimalization of storage function of water management system. The work is based on dissertation thesis of Ing. Pavel Menšík Ph.D. Automatization of storage function of water management system. As optimalization method was chosen diferential evolution. Sequential version of the method will be implemented as a first step, followed by CPU accelerated and GPU accelerated versions.
|
|
|
Realistic Roundabouts Simulator
Molnár, Miroslav ; Petrlík, Jiří (referee) ; Korček, Pavol (advisor)
Constant increase of the road traffic brings some new problems. Finding solutions requires an exploration of road transportation. The aim of this work is to design and develop the microscopic simulator based on the cellular automaton for simulating roundabouts. Such simulator allows to create different types of roundabouts that can be connected to each other by roads. Within the simulator, there is possibility to change different parameters, e.g. value of the visibility, the sliding friction, the maximum speed and the adherence to a safe distance on the road. At the end of this work there are the results of the simulations in the different traffic situations summarized.
|
|
|
Telemetry for Dragon IV Formula
Bezdíček, Jan ; Petrlík, Jiří (referee) ; Šimek, Václav (advisor)
The aim of this master's thesis was to design and construct complete telemetry system for the student formula Dragon IV constructed for international Formula Student competition. At first, the work deals with the measurement of the physical quantities, telemetry system and automotive sensors of the formula, their mutual communication and communication with the CAN bus. It also describes the procedure of hardware design including choosing right inertial sensors and a GPS module and their using in telemetry system. The work contains materials for production of two-layer printed circuit board extending the microcomputer BeagleBone Black on the inertial sensors and the GPS module. The bigger part of the telemetry system is the firmware for hardware and software for the computer user. Both written in programming language C++ and C# are included in this work as well. This user application serves for wireless receiving data from the hardware and their showing and logging. In addition this user application can be used for wireless hardware configuration. The final product is the complete telemetry system and it is suitable for selling to end customer.
|
|
|
DNA Computing and Applications
Fiala, Jan ; Petrlík, Jiří (referee) ; Bidlo, Michal (advisor)
This thesis focuses on the design and implementation of an application involving the principles of DNA computing simulation for solving some selected problems. DNA computing represents an unconventional computing paradigm that is totally different from the concept of electronic computers. The main idea of DNA computing is to interpret the DNA as a medium for performing computation. Despite the fact, that DNA reactions are slower than operations performed on computers, they may provide some promising features in the future. The DNA operations are based on two important aspects: massive parallelism and principle of complementarity. There are many important problems for which there is no algorithm that would be able to solve the problem in a polynomial time using conventional computers. Therefore, the solutions of such problems are searched by exploring the entire state space. In this case the massive parallelism of the DNA operations becomes very important in order to reduce the complexity of finding a solution.
|
|
|
Multiobjective Cartesian Genetic Programming
Petrlík, Jiří ; Schwarz, Josef (referee) ; Sekanina, Lukáš (advisor)
The aim of this diploma thesis is to survey the area of multiobjective genetic algorithms and cartesian genetic programming. In detail the NSGAII algorithm and integration of multiobjective optimalization into cartesian genetic programming are described. The method of multiobjective CGP was tested on selected problems from the area of digital circuit design.
|
|
| |
|
|
Competitive Coevolution in Cartesian Genetic Programming
Skřivánková, Barbora ; Petrlík, Jiří (referee) ; Drahošová, Michaela (advisor)
Symbolic regression is a function formula search approach dealing with isolated points of the function in plane or space. In this thesis, the symbolic regression is performed by Cartesian Genetic Programming and Competitive Coevolution. This task has already been resolved by Cartesian Genetic Programming using Coevolution of Fitness Predictors. This thesis is concerned with comparison of Coevolution of Fitness Predictors with simpler Competitive Coevolution approach in terms of approach effort. Symbolic regression has been tested on five functions with different complexity. It has been shown, that Competitive Coevolution accelerates the symbolic regression task on plainer functions in comparison with Coevolution of Fitness Predictors. However, Competitive Coevolution is not able to solve more complex functions in which Coevolution of Fitness Predictors succeeded.
|
|
|
Multi-objective genetic algorithms in road traffic prediction
Petrlík, Jiří ; Brandejský, Tomáš (referee) ; Snášel,, Václav (referee) ; Sekanina, Lukáš (advisor)
Porozumění chování silniční dopravy je klíčem pro její efektivní řízení a organizaci. Tato úloha se stává čím dál více důležitou s rostoucími požadavky na dopravu a počtem registrovaných vozidel. Informace o dopravní situaci je důležitá pro řidiče a osoby zodpovědné za její řízení. Naštěstí v posledních několika dekádách došlo k značnému rozvoji technologií pro monitorování dopravní situace. Stacionární senzory, jako jsou indukční smyčky, radary, kamery a infračervené senzory, mohou být nainstalovány na důležitých místech. Zde jsou schopny měřit různé mikroskopické a makroskopické dopravní veličiny. Bohužel mnohá měření obsahují nekorektní data, která není možné použít při dalším zpracování, například pro predikci dopravy a její inteligentní řízení. Tato nekorektní data mohou být způsobena poruchou zařízení nebo problémy při přenosu dat. Z tohoto důvodu je důležité navrhnout obecný framework, který je schopný doplnit chybějící data. Navíc by tento framework měl být také schopen poskytovat krátkodobou predikci budoucího stavu dopravy. Tato práce se především zabývá vybranými problémy v oblasti doplnění chybějících dopravních dat, predikcí dopravy v krátkém časovém horizontu a predikcí dojezdových dob. Navrhovaná řešení jsou založena na kombinaci současných metod strojového učení, například Support vector regression (SVR) a multikriteriálních evolučních algoritmů. SVR má mnoho meta-parametrů, které je nutné dobře nastavit tak, aby byla dosažena co nejkvalitnější predikce. Kvalita predikce SVR dále silně závisí na výběru vhodné množiny vstupních proměnných. V této práci používáme multiktriteriální optimalizaci pro optimalizaci SVR meta-parametrů a množiny vstupních proměnných. Multikriteriální optimalizace nám umožňuje získat mnoho Pareto nedominovaných řešení. Mezi těmito řešeními je možné dynamicky přepínat dle toho, jaká data jsou aktuálně k dispozici tak, aby bylo dosaženo maximální kvality predikce. Metody navržené v této práci jsou především vhodné pro prostředí s velkým množstvím chybějících hodnot v dopravních datech. Tyto metody jsme ověřili na reálných datech a porovnali jejich výsledky s metodami, které jsou v současné době používány. Navržené metody poskytují lepší výsledky než stávající metody, a to především ve scénářích, kde se vyskytuje mnoho chybějících hodnot v dopravních datech.
|
|
|
Java Byte-Code Interpreter for FITKit Platform
Husák, Jiří ; Petrlík, Jiří (referee) ; Fučík, Otto (advisor)
The aim of this bachelor's thesis is to design and implement the Java bytecode interpreter for FITkit platform. At first is analyzed issues of Java programming language, especially properties of portable Byte-Code and Java Virtual Machine. The study also describes the MSP430 microcontroller from Texas Instruments. The result of bachelor's thesis is the interpreter written in C for microprocessor and application for PC that provides compilation and loading Byte-Code with serial port to the device FITkit. At the end of the work are presented some demonstration applications written in Java that use FITkit peripherals or FPGA to accelerate calculations.
|
guest ::
RSS feed.