|
|
OCR of image based web form protection
Peluch, Tibor ; Hrabec, Jakub (referee) ; Honzík, Petr (advisor)
The thesis deals with programming of application in operating system Windows. Main features of application system Microsoft Foundation Class are resumed in brief here. In following part there is idea about implementing an application with graphic user interface that makes, using schema, work with data, possible. The third part deals with implementation of blocks into dynamic linked libraries and there is outlined a possibility to use data of this programme as an external module and a possibility of realtime data processing e.g. picture and sound. The verification of a good functionality of this application is in the last part. The application is really tested in diagnosing of devaluated texts for protecting web forms www.centrum.cz. There were designed blocks making picture read possible just from internet, preprocessing, segmentation, feature extraction, evaluationg in neural network and blocks that make possible to read and save processed data into the disc.
|
|
|
Smart distance measurement module for football robot
Hrbáček, Jan ; Honzík, Petr (referee) ; Havránek, Zdeněk (advisor)
Diplomová práce se zabývá vývojem dálkoměrného modulu určeného pro rozšíření senzorické výbavy fotbalového robotu kategorie MiroSot. Tento modul na vstupu přijímá data ze senzorické jednotky vyvinuté na Ústavu automatizace a měřicí techniky a z těchto dat extrahuje polohu míčku. Je srovnáno využití neuronové sítě a zjednodušené Houghovy transformace pro získání polohy těžiště míčku. V práci je popsána pomocná implementace funkcionality v prostředích MATLAB a C#.NET i hlavní implementace pro signálový mikrokontrolér Freescale MC56F8013. Výsledný modul splňuje nároky zadání a je plně funkční.
|
|
|
Sběr a zpracování dat při měření LED modulů předních světlometů
Polák, Petr ; Honzík, Petr (referee) ; Holek, Radovan (advisor)
The aim of this is devise a file of measured parameters for LED Module Check device which is using for measurement of headlamps LED modules and for following generating reports of measurements. At the beginning of the thesis is described LED Module Check functionality and LED parameters to following up. In the following section is decribed main class written in C# language, own measured values and their interpretation to XML format. Finally, are introduced tools for making and adjustment documents and conversion to PDF format.
|
|
|
Simulator of mobile robots in Matlab/Simulink
Havlát, Petr ; Honzík, Petr (referee) ; Hrabec, Jakub (advisor)
The main goal is the programming scene MATLAB/Simulink creation of graphic user interface (GUI), which allows the simulation of mobile robots movement. The work covers two types of these robots – first one is the robot with differentially controlled truck and second one auto robot (car-like robot). As a part of this draft GUI, there are also possibilities of showing all trajectory or only actual position, selection of step after which the robot can delineate and possibility of layout between the positions by using the button back and forwards.
|
|
|
Feature Selection Based on Dynamic Mutual Information
Manga, Marek ; Klusáček, Jan (referee) ; Honzík, Petr (advisor)
This work analyzes and discuss a issue of implementation feature selection method called Dynamic mutual information (DMIFS). Original description of the DMIFS contains several irregularities, therefore DMIFS can not be implemented exactly as original method. Results of implemented DMIFS is compared with results of original DMIFS. This results shows that implemented DMIFS is similar to the DMIFS. Next part of the work describes design of two new methods based on the DMIFS. The first method called DmRMR merges mRMR and DMIFS. Better performance but worse stability of DmRMR was proved by several tests. The second method called WDMIFS is weighted version of the DMIFS based on AdaBoost algorithm. The WDMIFS has worse performance than DMIFS. Finnaly, manual for implementing DMIFS to RapidMiner and Weka is provided.
|
|
|
Swarm Intelligence Based Experiment in RDS
Kolář, Ladislav ; Florián, Tomáš (referee) ; Honzík, Petr (advisor)
The thesis consists of two parts. In the first one the overview of robotic simulators is compiled with more detailed focus on the Microsoft Robotics Developer Studio (MRDS). The process of development of the new project including both programming languages C# and Visual Programming Language (VPL) is described in form of manual. The second part of the thesis is aimed to explain the term swarm intelligence, to describe the concrete experiment and to implement it in MRDS. Finally the achieved results are summarized and discussed.
|
|
|
Ingelligent Import of OSM into the Traffic Simulator TRASI
Muzika, Dávid ; Klusáček, Jan (referee) ; Honzík, Petr (advisor)
The thesis deals with the design and implementation of algorithms for import maps into the simulator TRASI. These algorithms are capable of import map from map portal OpenStreetMaps to the simulation environment. The work deals with adjusting the internal structure of the imported intersections, so that their structure was correct according to the rules of traffic. The work deals with the design and implementation of differential evolution for the design of the structure of intersections.
|
|
|
New methods and trends of e-learning
Šprta, Vlastimil ; Honzík, Petr (referee) ; Valenta, Jan (advisor)
This bachelor thesis follows the mid-term work in which I have dealt with e-learning in general. Seeing that e-learning is very broad subject and that in specialized branches it is transformed all the time, in this work I describe and evaluate its forms, standards and essential components from different points of view. I characterise every component individually and I name both its necessary and ideal parameters. I do leave out neither the links between individual components of e-learning nor the hardware. I especially focus on the Moodle system. I characterise it and I describe its origin and history. I pay special attention to the evaluation of statistics related to the usage of the Moodle system. The main content of this work is concerned with e-learning resources at Brno University of Technology, Faculty of Electrical Engeneering and Communication, Department of Control and Instrumentation. In great detail I describe and evaluate all the most used e-learning resources. This work contains suggestions for optimalization of these e-learning resources and for making them more effective. Those suggestions are based on my evaluation, on questionnaires and on the general knowledge, while taking in consideration both students and members of the staff approach.
|
|
|
Pattern Finding in Dymanical Data
Budík, Jan ; Hynčica, Ondřej (referee) ; Honzík, Petr (advisor)
First chapter is about basic information pattern learning. Second chapter is about solutions of pattern recognition and about using artificial inteligence and there are basic informations about statistics and theory of chaos. Third chapter is focused on time series, types of time series and preprocessing. There are informations about time series in financial sector. Fourth charter discuss about pattern recognition problems and about prediction. Last charter is about software, which I did and there are informations about part sof program.
|
|
|
Effect of HFS Based Feature Selection on Cluster Analysis
Malásek, Jan ; Klusáček, Jan (referee) ; Honzík, Petr (advisor)
Master´s thesis is focused on cluster analysis. Clustering has its roots in many areas, including data mining, statistics, biology and machine learning. The aim of this thesis is to elaborate a recherche of cluster analysis methods, methods for determining number of clusters and a short survey of feature selection methods for unsupervised learning. The very important part of this thesis is software realization for comparing different cluster analysis methods focused on finding optimal number of clusters and sorting data points into correct classes. The program also consists of feature selection HFS method implementation. Experimental methods validation was processed in Matlab environment. The end of master´s thesis compares success of clustering methods using data with known output classes and assesses contribution of feature selection HFS method for unsupervised learning for quality of cluster analysis.
|
guest ::
