|
|
Mathematical modelling of thin films of martensitic materials
Pathó, Gabriel ; Kružík, Martin (advisor) ; Kalamajska, Agnieszka (referee) ; Šilhavý, Miroslav (referee)
The aim of the thesis is the mathematical and computer modelling of thin films of martensitic materials. We derive a thermodynamic thin-film model on the meso-scale that is capable of capturing the evolutionary process of the shape-memory effect through a two-step procedure. First, we apply dimension reduction techniques in a microscopic bulk model, then enlarge gauge by neglecting microscopic interfacial effects. Computer modelling of thin films is conducted for the static case that accounts for a modified Hadamard jump condition which allows for austenite--martensite interfaces that do not exist in the bulk. Further, we characterize $L^p$-Young measures generated by invertible matrices, that have possibly positive determinant as well. The gradient case is covered for mappings the gradients and inverted gradients of which belong to $L^\infty$, a non-trivial problem is the manipulation with boundary conditions on generating sequences, as standard cut-off methods are inapplicable due to the determinant constraint. Lastly, we present new results concerning weak lower semicontinuity of integral functionals along (asymptotically) $\mathcal{A}$-free sequences that are possibly negative and non-coercive. Powered by TCPDF (www.tcpdf.org)
|
|
|
Random marked sets and dimension reduction
Šedivý, Ondřej ; Beneš, Viktor (advisor) ; Janáček, Jiří (referee) ; Mrkvička, Tomáš (referee)
Random closed sets and random marked closed sets present an important general concept for the description of random objects appearing in a topological space, particularly in the Euclidean space. This thesis deals with two major tasks. At first, it is the dimension reduction problem where dependence of a random closed set on underlying spatial variables is studied. Solving this problem allows to find the most significant regressors or, possibly, to identify the redundant ones. This work achieves both theoretical results, based on extending the inverse regression techniques from classical to spatial statistics, and numerical justification of the methods via simulation studies. The second topic is estimation of characteristics of random marked closed sets which is primarily motivated by an application in the microstructural research. Random marked closed sets present a mathematical model for the description of ultrafine-grained microstructures of metals. Methods for statistical estimation of their selected characteristics are developed in the thesis. Correct quantitative characterization of microstructure of metals allows to better understand their macroscopic properties.
|
|
|
A point process driven by a Gaussian field
Scheib, Karel ; Beneš, Viktor (advisor) ; Šedivý, Ondřej (referee)
The thesis investigates the search for dimension reduction subspace for the Poisson point process driven by a Gaussian random eld. The work describes the method called sliced inverse regression, which is applied to a point process driven by random eld. Its functionality in mentioned context is then proved. This method is in several ways implemented and tested in R software environment on random data. The individual implementations are described and results are then compared with each other.
|
|
|
Robust Knowledge Discovery from High-Dimensional Data
Kalina, Jan
The paper is devoted to advanced robust methods for information extraction from highdimensional data. The concept of knowledge discovery is discussed together with its two important aspects: high dimensionality of the data and sensitivity to the presence of outlying data values. We propose new robust methods for knowledge discovery suitable for highdimensional data. They are based on the idea of implicit weighting, which is inspired by the least weighted squares regression estimator. We propose a highly robust method for a dimension reduction, which can be described as a robust alternative of the principal component analysis based on implicit down-weighting of less reliable data values. Further, we propose a novel robust approach to cluster analysis, which is a popular knowledge discovery method of unsupervised learning. A two-stage cluster analysis method tailor-made for highdimensional data is obtained by combining the robust principal component analysis with the robust cluster analysis. The procedure can be interpreted as a robust knowledge discovery method tailor made for high-dimensional data.
|
|
| |
guest ::
