|
| |
|
|
Climate Monitoring at Home
Pillár, Andrej ; Dobrovský, Ladislav (referee) ; Šoustek, Petr (advisor)
Cieľom tejto bakalárskej práce je vyvinúť, zostaviť a otestovať zariadenie na meranie enviromentálnych veličín v interiéri. Zariadenie obsahuje senzory teploty, relatívnej vlhkosti, tlaku a koncentrácie CO2. Aktuálne hodnoty su zobrazené na vstavanej obrazovke spolu s časom a odosielané pomocou IoT protokolu MQTT na server. Práca obsahuje aj riešenie tohoto serveru. Dáta sú ním spracovávané, ukladané do SQL databázy a ďalej sprístupnené cez JSON API implementované v jazyku Python. Aplikácia vyvinutá pomocou niekoľkých webových technológií ponúka prehľad aktuálnych aj historických hodnôt. Serverové riešenie je hostované na http serveri. Demonštračná verzia riešenia využíva server NGINX ktorý tiež poskytuje zabezpečenie komunikácie so serverom pomocou TLS pre všetky služby. Celá práca je spracovaná s dôrazom na otvorenosť, modularitu a rozšíriteľnosť. V práci sú preferenčne používané Libre a Open Source technológie.
|
|
|
Deep reinforcement learning and snake-like robot locomotion design
Kočí, Jakub ; Dobrovský, Ladislav (referee) ; Matoušek, Radomil (advisor)
This master thesis is discussing application of reinforcement learning in deep learning tasks. In theoretical part, basics about artificial neural networks and reinforcement learning. The thesis describes theoretical model of reinforcement learning process - Markov processes. Some interesting techniques are shown on conventional reinforcement learning algorithms. Some of widely used deep reinforcement learning algorithms are described here as well. Practical part consist of implementing model of robot and it's environment and of the deep reinforcement learning system itself.
|
|
|
Raspberry Pi: intelligent door peephole
Miček, Adam ; Dobrovský, Ladislav (referee) ; Matoušek, Radomil (advisor)
The goal of this diploma thesis is to create the functional prototype of intelligent peephole (video doorman) on Raspberry Pi 3B+ platform. It will support face recognition of the people, alternatively authorization by QR code and the record of the situations in form of picture, video, and text. Furthermore, it will allow remote control from Android application with possibility to see live stream of Raspberry Pi’s video in this application. Creation of the project is preceded by brief introduction of Raspberry Pi platform, its alternatives and process of face recognition. Python programming language was primarily used for software development on Raspberry Pi platform. Two approaches were used for image processing, direct processing on Raspberry Pi and on more powerful computer. This work describes use of various modern libraries, platforms, and frameworks, used during the creation of the project, with goal to provide beginners in this field insight into this technology, way of its use, and offer starting point for further work.
|
|
|
Model visualization in virtual reality
Cmajdálka, Ondřej ; Dobrovský, Ladislav (referee) ; Hůlka, Tomáš (advisor)
This thesis deals with phenomenon called virtual reality, its historical development and nowadays used technologies. The next part is dedicated to game engines, their history and structure. In practical part a proposal and development of virtual reality environment is described. The proposed environment demonstrates selected features of the game engine that make it a suitable tool for developing virtual reality environments.
|
|
| |
|
|
Using machine learning for quality control in industrial applications
Gaško, Viktor ; Dobrovský, Ladislav (referee) ; Parák, Roman (advisor)
Goal of this bachelor´s thesis is to get acquainted with issue of quality control in industrial applications with focus on deep learning. For this and similar issues was created several libraries which have a purpose of simplifying these issues. Main task is to create program for quality control with help of programming language Python and framework Tensorflow. This program will be comprised of three neural network, from which one will identify the approximate position of the part, second its color, and third will check the correctness of its production.
|
|
|
Number Plate Recognition using Deep Learning Techniques
Dobrovský, Ladislav ; Dvořák, Jiří (referee) ; Matoušek, Radomil (advisor)
Focus of this thesis is research of deep convolutional artificial neural networks and their usage as solution to automatic license plate recognition problem. After summary of theory and current trends the further direction of development has been chosen. Thesis investigates several types of convolutional neural networks and complex architecture of system of collaborating applications. In practical part is described implementation and results of experiments with assessment of networks’ suitability for practical use.
|
|
|
Synchronization and Drive Control by Means of the Controller Area Network
Dobrovský, Ladislav ; Kaštovský, Petr (referee) ; Eysselt, Miloš (advisor)
System for motion control via CAN-Bus with USB-CAN converter. Software is divided to two parts. The first part is a server application that enables client applications to use CAN-Bus as a service available on sockets, because the IMF software company "USB-CAN hardware converter" can't be accessed directly by more applications. Client applications control different devices connected to CAN-Bus. Motion control using actuator Berger Lahr IclA D065 in application of 3 axes omni-wheel robot has been impemented. Interroll omni-wheels are used. This application has a graphical user interface done with the GTK+ library. The second, practical part, of the work has been developed in Dept. of Applied Computer Science, FME, Brno University of Technology, under supervision of Ing. Radomil Matousek, Ph.D.
|
|
| |
guest ::
RSS feed.