This thesis deals with predicting the latency between two network nodes, such as the two stations, two servers or server and station. The main reason for adoption of effective latency prediction techniques is the elimination of network load caused by unnecessary repeated transmissios or by direct measurement of the latency. Of the many proposed methods of latency estimation, this thesis is focused on methods using artificial coordinate systems with primary focus on the Vivaldi algorithm. Characteristics of the latency prediction methods and properties of various coordinate systems used in practice are evaluated. The issue of the number of dimensions of space defined only by the latency matrix between nodes is also mentioned. Furthermore, some other systems, based on logical clustering of nearby nodes, are mentioned. Description of simulation software VivaldiMonitor developed as part of the thesis is included. The primary purpose is analysis of the behavior of overlay networks implementing Vivaldi algorithm with less than a few hundred nodes. The Vivaldi algorithm is assessed by several simulations carried out using the aforementioned software.

The number of experimentally resolved protein structures in the Protein Data Bank has been growing fast in the last 20 years, which motivates the develop- ment of many computational tools for protein-ligand binding sites prediction. Binding sites prediction from protein 3D structure has many important applica- tions; it is an essential step in the complex process of rational drug design, it helps to infer the side-effects of drugs, it provides insight into proteins biological functions and it is helpful in many other fields, such as protein-ligand docking and molecular dynamics. As far as we know, there has not been a study that would systematically investigate general properties of known ligand binding sites on a large scale. In this thesis, we examine these properties using existing experimen- tal and predicted residue-level annotations of protein sequence and structure. We present an automated pipeline for statistical analysis of these annotations, based on hypothesis testing and effect size estimation. It is implemented in Python and it is easily extensible by user-defined annotations. The usage is demonstrated on 33 existing annotations and 4 different datasets. The practical significance of the results is tested with P2Rank prediction method. We hope that the results as well as the pipeline...

Identification of individuals with low and high risk for future dementia has emerged as an important clinical and public health issue. To address this issue, we compared two commonly used memory tests initially in non-demented elderly persons with subjective memory complaint or mild cognitive impairment and followed them for an average of two years. The first test called Enhanced Cued Recall (ECR), provides support for the semantic encoding of memorandum at the time of the study and supplies category cues at the time of retrieval whereas the second test, the Auditory Verbal Learning Test (AVLT), does not support this paradigm. In this retrospective study, we compared initial neuropsychological performance of patients from the Memory Disorders Clinic in the Department of Neurology at Motol University Hospital. The results were analyzed among the patients who developed dementia and those who did not. Then, the prediction abilitities of the two measures of memory were compared. Our results showed that the test AVLT predicts incident dementia better than the test ECR. The group likely to develop dementia becomes a target for early therapeutic interventions. Keywords: prediction of dementia, conversion to dementia, Alzheimer's disease, test AVLT, test ECR

The aim of this thesis is to investigate possible improvement of scoring models prediction power in retail credit segment by using structural models estimating the future development of behavioral score. These models contain the informa- tion about past development of the behavioral score by parameters which take into account the sensitivity of clients' probability of default on individual market and life changes. These parameters are estimated by Markov Chain Monte Carlo methods based on score history. Eight different types of structural models were applied to real data. The diversification measure of individual models is compared using the Gini coefficient. These structural models were compared with each other and also with the existing scoring model of the credit institution which provided the underlying data. 1

This thesis examines the results of public budgets in the CR in the period 1993 to 2009. This is a hot topic, with the growth of public debt is becoming increasingly important. The aim of this work is a comprehensive analysis of public finances, specifically addressing issues of access to public deficit and reform public finances. The theoretical part is focused on defining the area being examined and the theory describing this area have their roots back more than sixty years ago in the USA. Although the idea is relatively old data, their content is still current. This is particularly important now that the growing indebtedness of many countries of the European Union, including the Czech Republic. The paper reviewed the current action by governments in the management of public finances. In the analytical part, I analyze using appropriate statistical data trends, correlations and patterns of past and current periods. Based on the trends observed and outline possible scenarios for future development. Reported research findings are interpreted in the form of text, supplemented by a series of graphic illustrations. Not forgetting the situation in the Czech Republic comparison with other developing countries of the European Union. The conclusion summarizes the findings and recommendations and outline likely future developments.

The goal of this thesis is to investigate the existing graph embedding methods. We aim to represent the nodes of undirected weighted graphs as low-dimensional vectors, also called embeddings, in order to create a rep- resentation suitable for various analytical tasks such as link prediction and clustering. We first introduce several contemporary approaches allowing to create such network embeddings. We then propose a set of modifications and improvements and assess the performance of the enhanced models. Finally, we present a set of evaluation metrics and use them to experimentally evalu- ate and compare the presented techniques on a series of tasks such as graph visualisation and graph reconstruction. 1

The thesis describes the stock exchange environment, the system and its basic operating principles. The thesis further focuses on the stock exchange data and its analysis. The author describes the development of the technical analysis; he mentions the classical theory and the classical graphical methods, the modern graphical methods, the technical indicators and finally the latest analytical methods, the so-called Artificial Intelligence. The research focuses on the real stock market prediction using the artificial intelligence methods and knowledge of the modern technical analysis.

The thesis "Actual role of knowledge discovery in databases˝ is concerned with churn prediction in mobile telecommunications. The issue is based on real data of a telecommunication company and it covers all steps of data mining process. In accord with the methodology CRISP-DM, the work looks thouroughly at the following stages: business understanding, data understanding, data preparation, modeling, evaluation and deployment. As far as a system for knowledge discovery in databases is concerned, the tool IBM SPSS Modeler was selected. The introductory chapter of the theoretical part familiarises the reader with the issue of so called churn management, which comprises the given assignment; the basic concepts related to data mining are defined in the chapter as well. The attention is also given to the basic types of tasks of knowledge discovery of databasis and algorithms that are pertinent to the selected assignment (decision trees, regression, neural network, bayesian network and SVM). The methodology describing phases of knowledge discovery in databases is included in a separate chapter, wherein the methodology of CRIPS-DM is examined in greater detail, since it represents the foundation for the solution of our practical assignment. The conclusion of the theoretical part also observes comercial or freely available systems for knowledge discovery in databases.

The aim of the presented work is to investigate possible improvement of scor- ing models prediction power in retail credit segment by using structural models estimating the future development of behavioral score. These models contain the information about past development of the behavioral score by parameters which take into account the sensitivity of clients' probability of default on in- dividual market and life changes. These parameters are estimated with Markov Chain Monte Carlo methods based on score history. Eight different types of struc- tural models were applied on the real data. The diversification measure of indivi- dual models is compared using the Gini coefficient. These structural models were compared with each other and also with the existing scoring model of the credit institution which provided the underlying data. 1

This diploma thesis deals with the creation and testing of trading strategies based on technical analysis and prediction of time series using neural networks. The the-oretical part introduces the reader to basic methods of market analysis, especially with technical analysis. In the practical part there are analyzed available options for testing trading strategies and designed functions and structure, which are used to implement web application.