|
Klasifikátor založený na inverzních hodnotách indexů II. teorie a příloha
Jiřina, Marcel ; Jiřina jr., M.
A theory of a new method for the classification of data into classes is presented. The method is based on the sum of reciprocals of neighbors' indexes. We show that neighbors' indexes are in close relation to the approximate polynomial transform of the neighbors' distances. The sum of the reciprocals of indexes for all neighbors forms truncated harmonic series due to a finite number of its elements. For the neighbors of one class there is a sum of the selected elements of this truncated series. It is proved that the ratio of these sums gives just the probability that the point to be classified - the query point - is of that class.
Fulltext: content.csg -  PDF
Plný tet: v1041-08 - PDF
|
|
Klasifikátor založený na inverzních hodnotách indexů
Jiřina, Marcel ; Jiřina jr., M.
A new method for the classification of data into classes is presented. The method is based on the sum of reciprocals of neighbors' indexes. We show that neighbors' indexes are in close relation to the polynomial transform of the neighbors' distances. The sum of the reciprocals of indexes for all neighbors forms truncated harmonic series due to a finite number of its elements. For the neighbors of one class there is a sum of the selected elements of this truncated series. It is proved that the ratio of these sums gives just the probability that the point to be classified -- the query point -- is of that class. The classification ability is demonstrated on real-life data from the Machine Learning Repository and the results are compared with published results obtained through other methods.
Fulltext: content.csg - PDF
Plný tet: v1034-08 - PDF
|
|
Quantitative analysis by X-Ray powder diffraction
Stachová, Sandra ; Havlíček, David (advisor) ; Vojtíšek, Pavel (referee)
Quantitative analysis methods using X-ray powder diffraction are still highly actual conception in the area of research of modern materials. The Reference Intensity Ratio (RIR) method is used here for quantitative analysis by X-ray powder diffraction of model samples in this bachelor thesis. The model samples are three mixtures of corundum, mullite and calcite. To get diffraction patterns of the mixtures, two different diffractometers are used and their outputs are then compared.
|
|
Controlled structuring of self–assembled polystyrene microsphere arrays by two different plasma systems
Domonkos, Mária ; Ižák, Tibor ; Štolcová, L. ; Proška, J. ; Kromka, Alexander
In this study we present a successful manipulation of microspheres by reactive ion etching (RIE). A self-assembled monolayer close-packed array of monodisperse polystyrene microspheres (PM) with diameter of 471 nm was used as the primary template. The PM templates were processed in two different RIE systems: (i) capacitively coupled radiofrequency plasma (CCP) and (ii) dual plasma system which combines CCP and pulsed linear-antenna microwave plasma (PLAMWP). The influence of process conditions on the PM geometry was systematically studied by scanning electron microscopy (SEM). The process conditions were controlled by varying radiofrequency (RF) power, gas mixture (O2:CF4 ratio) and process duration.
|
|
Soil microorganisms as controllers of methane emission from soils
Elhottová, Dana ; Němcová, Anna ; Chroňáková, Alica ; Šimek, Miloslav
The pilot study on functional microbial groups responsible for methanogenic and methanotrophic processes in soil of specific model ecosystem – the cattle overwintering pasture was given. The enrichment by methanogenic archaea was shown in soils strongly impacted due to cattle pasture. The increased methanogenic abundance was accompanied by increased abundance of methylotrophic bacteria. Nevertheless, the ratio of methylotrophic to methanogenic microorganisms was significantly higher in the control soils without cattle impact in comparison to the cattle-impacted soils.
|
|
Numerical Modeling of Ice Sheet Dynamics
Souček, Ondřej ; Martinec, Zdeněk (advisor) ; Málek, Josef (referee) ; Ivins, Erik R. (referee)
Title: Numerical modeling of ice sheet dynamics Author: Ondřej Souček Department: Department of Geophysics, Faculty of Mathematics and Physics, Charles University in Prague Supervisor: Prof. RNDr. Zdeněk Martinec, DrSc. Supervisor's e-mail address: zdenek@cp.dias.ie Abstract: The main topic of the presented thesis is the numerical modeling of large-scale ice-sheet evo- lution over several glacial cycles. For this purpose a "Shallow Ice Approximation" (SIA) is traditionally adopted, a scaling approximation utilizing the fact that the vertical-to-horizontal aspect ratio in ice sheets is typically a small parameter allowing for a perturbation expansion of the governing equations with respect to this parameter. We present a formulation of the boundary value problem for a polythermal ice sheet based on the rational thermodynamics of mixtures and derive its "shallow-ice" form. We then provide a novel SIA-I algorithm for iterative improvement of the SIA and thoroughly test its performance in a series of benchmarks including the ISMIP-HOM benchmark and a realistic simulation for the Dronning Maud Land region, Antarctica. The SIA-I algorithm is implemented to an evolutionary thermo-mechanical numerical ice-sheet model and this model is tested in the SIA regime in two EISMINT benchmarks, EISMINT - Effect of...
|
| |
|
Determinants of Social Expenditure Levels in the EU
Roženský, Vojtěch ; Ochrana, František (advisor) ; Izák, Vratislav (referee) ; Nemec, Juraj (referee)
The aim of the thesis is to identify the determiants of social expenditure levels in EU member states and estimate the sensitivities. The analysis is based on the fixed effects model with robust standard errors. Seven out of the 24 variables, that have been tested, are statistically significant. Social expenditure levels are positively dependent on population ageing, unemployment rate and economic level, and negatively on economic growth. The openness of economy and public debt ratio are also robust. The presence of a christian party in government is also statistically significant, however, the coefficient is not theoretically consistent. The sensitivity of social expenditure level to the share of population aged 65 years and over on the total population, is about 0,30. It means, that on average, the rise in the share of the old by 1 percentage point, is followed by the rise of social expenditure level by 0,3% of the GDP. In case of unemployment rate, economic growth and the openness of economy, the sensitivity estimates are 0,3, -0,1 and -0,03. The sensitivities to the other three robust variables cannot be quantified due to a strong dependence on the exact model specification or a bias, caused by extreme values. The expenditure on pensions are relatively more dependent on population ageing, whereas other social expenditure are more sensitive to current position in economic cycle. The determinants in the old and the new EU member states are similar, with only one exception, as the expenditure levels in the new member states are less dependent on demographic structure. The model explains international differences and the changes during the period between 1990 and 2010.
|
|
Prediction of Stock Returns Usig Financial Statement Analysis
Hájková, Petra ; Jakubík, Petr (advisor) ; Hollmannová, Monika (referee)
This diploma thesis should contribute to research in the area of fundamental analysis. Its aim is to study whether financial statement data of Czech non-financial companies capture information that is not reflected in prices. Therefore, the question is whether investment strategy based on financial statement analysis could earn excess returns. In order to test this hypothesis, a three-step estimation procedure based on a logit model is used to identify financial ratios relevant for prediction of future earnings. The final estimated model includes four financial ratios and is then used to set a one-year investment strategy. Although the performance of the estimated model is not too sound, this investment strategy brings positive abnormal returns during the monitored period of time. Despite the fact that results were influenced by several factors, they could indicate that financial statement analysis of companies listed on the Prague Stock Exchange is able to predict stock returns. Powered by TCPDF (www.tcpdf.org)
|
|
Step by step credit risk model construction
Rychnovský, Michal ; Hanzák, Tomáš (referee) ; Charamza, Pavel (advisor)
Nazev pracc: Postnpna vyslavba modelu ohoduoconi kroditniho ri/,ika Autor: Michal Ryclmovsky Katedra: Kaledra pravdepoelobnejsti a maternal icke statistiky Vedouci bakalafske pracc: RNDr. Pavel Charam/a, CSc. E-mail vedouciho: pavol.charani/a''^media research.ex Abstrakt: Ciloni toto pracc je pfibli/it podstatu vvstavby skoringovych mo- eleln. Popisnjeme zde metodu logisticke regrese, odhaelovani jejich paramotrn a testovani jcjicli vy/,nanmosti. Na /aklado, proiiioiniych odds ratio potoin zavadimo indei>endence model jako odhad podminone saneo s]>laceni klienta.. Tento ... dale zoljecnHJinne pfidavanini vah jedmjtlivyni sku])inani a ka- tegoriini charakt.eristik klienta.. Ta.kto pficha/Jnie k WOE niodeln a jjlnemu logistickemn niodeln. Vennjeine se take nicfeni divcr/ilikacni schopnosti ino- deln pomoci Lorenxovy kfivky a Somerovy d statistiky jako odhadu Giuiho koeficientn. Nakonec a])likujeine popsane nietody na praktiekon vystavbn yk(')riiigovych niodeln a na realnych dateeh porovnanie vhodnost a di\erx,ifi- kacni scho])nost pi'edstavovanych niodelu. Soneast.i ])race je take vystup na. int.ernetovon encyklo]>edii \\ikiiiedia. Klicova slova: kreditni rixiko, skoringove niodely, logisticka. 1'egrese. Title: Step by step credit risk model construction Author: Michal Rychnovsky Department: Department...
|
guest ::
