|
|
The Use of SVM in Environment of Financial Markets
Štechr, Vladislav ; Prochocká, Kristína (referee) ; Budík, Jan (advisor)
This thesis deals with use of regression or classification based on support vector machines from machine learning field. SVMs predict values that are used for decisions of automatic trading system. Regression and classification are evaluated for their usability for decision making. Strategy is being then optimized, tested and evaluated on foreign exchange market Forex historic data set. Results are promising. Strategy could be used in combination with other strategy that would confirm decisions for entering and exiting trades.
|
|
| |
|
|
Determination of the formwork strength of concrete using a Silver Schmidt hardness tester
Janka, Marek ; Kocáb, Dalibor (referee) ; Cikrle, Petr (advisor)
This bachelor thesis deal with the issues of nondestructive testing of the formwork removal strength of concrete. It works with two different compositions of concrete and for both of them, it determines the relation between compressive strength and surface hardness obtained by the SilverSchimdt hammer with mushroom plunger. It shows inappropriateness of ultrasonic impulse method to determine formwork removal strength. It compares obtained relations with each other and with the literature. The goal of this thesis is to utilize determined relations for verification of minimal requested formwork removal strength during construction.
|
|
|
Deconvolution of hemodynamic response from fMRI data
Bartoň, Marek ; Kolář, Radim (referee) ; Havlíček, Martin (advisor)
This paper deals with the variability of HRF, which may have crucial impact on outcomes of fMRI neuronal activation detection in some cases. There are three methods described - averaging, regression deconvolution and biconjugate gradient method - which provide HRF shape estimation. In frame of simulations regression method, which uses B-spline curves of 4-th order for window length of 30 s, was chosen as the most robust method. Deconvolution estimates was used as HRF models for classic analyse of fMRI data, concretely visual oddball paradigm, via general linear model. Enlargement of localizated areas was observed and after expert consultation with scientific employees from neurology clinic, outcomes was evaluated as relevant. Furthermore Matlab application, which provides confortable observation of HRF variability among brain areas, was made.
|
|
|
Location Aware Analytics in the Context of Mobile Network Performance Optimization
Urbanová, Lucie ; Miloš, Jiří (referee) ; Slanina, Martin (advisor)
Předmětem této práce je polohově orientovaná analýza v kontextu optimalizace mobilních sítí. Popisuje nástroj pro odhadování základních parametrů sítě na místech s neznámými parametry sítě na základě databáze RTR NetTest. Je zde stručně představena oblast velkých dat, strojového učení a shrnutí o konceptu a funkcionalitě aplikace NetTest. Práce ukazuje a porovnává skupinu regresních metod na základě jejich komplexnosti a vhodnosti pro vytvoření map odhadovaných parametrů sítě. Po jejich důkladné 1D analýze je IDW a GPR analyzováno ve 2D a využito pro vytvoření skupiny map odhadu parametrů sítě. Je posouzena i jejich přesnost na základě referenčního měření aplikací NetTest.
|
|
|
Visipedia - Embedding-driven Visual Feature Extraction and Learning
Jakeš, Jan ; Beran, Vítězslav (referee) ; Zemčík, Pavel (advisor)
Multidimenzionální indexování je účinným nástrojem pro zachycení podobností mezi objekty bez nutnosti jejich explicitní kategorizace. V posledních letech byla tato metoda hojně využívána pro anotaci objektů a tvořila významnou část publikací spojených s projektem Visipedia. Tato práce analyzuje možnosti strojového učení z multidimenzionálně indexovaných obrázků na základě jejich obrazových příznaků a přestavuje metody predikce multidimenzionálních souřadnic pro předem neznámé obrázky. Práce studuje příslušené algoritmy pro extrakci příznaků, analyzuje relevantní metody strojového účení a popisuje celý proces vývoje takového systému. Výsledný systém je pak otestován na dvou různých datasetech a provedené experimenty prezentují první výsledky pro úlohu svého druhu.
|
|
|
Re-Identification of Vehicles in Video
Zapletal, Dominik ; Sochor, Jakub (referee) ; Herout, Adam (advisor)
This thesis deals with the vehicle re-identification in video problem. Vehicle re-identification is based on matching image parts obtained from different cameras. This work is focues on the re-identification itself assuming that the vehicle detection problem is already solved including extraction of a full-fledged 3D bounding box. The re-identification problem is solved by using color histograms, histograms of oriented gradients by a linear regressor. The features are used in separate models in order to get the best results in the shortest CPU computation time. The proposed method works with a high accuracy (60% true positives retrieved with 10% false positive rate on a challenging subset of the test data) in 85 milliseconds of the CPU (Core i7) computation time per one vehicle re-identification assuming the Full HD resolution video input. The applications of this work include finding important parameters like travel time, traffic flow, or traffic information in a distributed traffic surveillance and monitoring system.
|
|
|
Creation of New Prediction Units in Data Mining System on NetBeans Platform
Havlíček, David ; Bartík, Vladimír (referee) ; Lukáš, Roman (advisor)
The issue of this master's thesis is a creation of new prediction unit for existing system of knowledge discovery in database. The first part of project deal with general problems of knowledge discovery in database and predictive analysis. The second part of the project deal with system developed on FIT, for which is module implemented, used technologies, concept and implementation of mining module for this system. The solution is implemented in Java language and is a built on the NetBeans platform.
|
|
|
An Examination of Financial Situation of the Company Using Time Series
Pšenčík, Jiří ; Novotná, Veronika (referee) ; Doubravský, Karel (advisor)
This thesis deals with financial analysis and evaluation of the situation of PKD, Ltd. between 2004 and 2008. Work consists of practical and theoretical parts. The theoretical parts are used in specified economic indicators and the theoretical basis of statistical analysis. The practical part will focus on the assessment of the financial situation with financial indicators and their representation in the time series by using regression curves.
|
|
|
Water cooling intensity prediction for given thickness of oxide layer
Haluza, Vít ; Hrabovský, Jozef (referee) ; Pohanka, Michal (advisor)
This diploma thesis is dealing with the impact of oxide scales on heat conduction. One of the main tools that were used are numerical simulations. Heat conduction is modelled by solving partial differential equations. Regression models and artificial neural networks are used for the prediction of the influence of oxides on cooling intensity. Determination of the conditions when the cooling was intensified and comparison of individual methods of prediction are the main results of the thesis.
|
guest ::
