Ústav teorie informace a automatizace

Nejnovější přírůstky:
2018-01-11
18:42
Optimal Value of Loans via Stochastic Programming
Kaňková, Vlasta
A question of mortgage leads to serious and complicated problems of financial mathematics. On one side is a bank with an aim to have a “good” profit, on the other side is the client trying to invest money safely, with possible “small” risk.Let us suppose that a young married couple is in a position of client. Young people know that an expected and also unexpected unpleasant financial situation can happen. Many unpleasant financial situation can be caused by a random factor. Consequently stochastic methods are suitable to secure against them. The aim of the suggested model is not only to state a maximal reasonable value of loans, but also to endure unpleasant financial period. To this end we employ stochastic optimization theory. A few suitable models will be introduced. The choice of the model depends on environment of the young people. Models will be with “deterministic” constraints, probability constraints, but also with stochastic dominance constraints. The suggested models will be analyzed both from the numerical point of view and from possible method solution based on data. Except static one-objective problem we suggest also multi–objective models.

Úplný záznam
2018-01-11
18:42
A machine learning method for incomplete and imbalanced medical data
Salman, Issam ; Vomlel, Jiří
Our research reported in this paper is twofold. In the first part of the paper we use\nstandard statistical methods to analyze medical records of patients suffering myocardial\ninfarction from the third world Syria and a developed country - the Czech Republic.\nOne of our goals is to find whether there are statistically significant differences between\nthe two countries. In the second part of the paper we present an idea how to deal with\nincomplete and imbalanced data for tree-augmented naive Bayesian (TAN). All results\npresented in this paper are based on a real data about 603 patients from a hospital in\nthe Czech Republic and about 184 patients from two hospitals in Syria.

Úplný záznam
2018-01-11
18:42
Analýza korozního poškození potrubí s proudící párou pomocí akustické emise:\nteoretická východiska a první výsledky
Tichavský, Petr
Zpráva popisuje první vysledky analýzy dat akustické emise získané měřením na parovodním potrubí v Atomové elektrárně Jaslovské Bohunice pořízené za účelem zkoumání korozního poškození potrubí.

Úplný záznam
2018-01-11
18:42
Odhad rychlosti šíření akustických vln ve vzorku oceli pro sledování creepových změn pomocí akustické emise
Tichavský, Petr ; Slunéčko, T. ; Svobodová, M. ; Chmela, T.
Zpráva popisuje měření rychlosti šíření zvuku ve vzorku materiálu podrobeném tepelnému a mechanickému namáhání pomocí signálu akustické emise.

Úplný záznam
2018-01-11
18:42
Sledování creepových změn na tepelně a mechanicky namáhaném vzorku oceli pomocí akustické emise II
Tichavský, Petr
Zpráva popisuje data získaná pří experimentu s tepelným a mechanickým namáháním vzorku oceli za účelem detekce creepových změn v materiálu. Akustická emise byla snímána současně dvěmi snímači.

Úplný záznam
2018-01-11
18:42
Sledování creepových změn na tepelně a mechanicky namáhaném vzorku oceli pomocí akustické emise
Tichavský, Petr
Zpráva popisuje data získaná pří experimentu s tepelným a mechanickým namáháním vzorku oceli za účelem detekce creepových změn v materiálu.

Úplný záznam
2017-12-20
13:37
Exact Inference In Robust Econometrics under Heteroscedasticity
Kalina, Jan ; Peštová, Barbora
The paper is devoted to the least weighted squares estimator, which is one of highly robust estimators for the linear regression model. Novel permutation tests of heteroscedasticity are proposed. Also the asymptotic behavior of the permutation test statistics of the Goldfeld-Quandt and Breusch-Pagan tests is investigated. A numerical experiment on real economic data is presented, which also shows how to perform a robust prediction model under heteroscedasticity. Theoretical results may be simply extended to the context of multivariate quantiles

Úplný záznam
2017-12-07
15:36
Avoiding overfitting of models: an application to research data on the Internet videos
Jiroušek, Radim ; Krejčová, I.
The problem of overfitting is studied from the perspective of information theory. In this context, data-based model learning can be viewed as a transformation process; a process transforming the information contained in data into the information represented by a model. The overfitting of a model often occurs when one considers an unnecessarily complex model, which usually means that the considered model contains more information than the original data. Thus, using one of the basic laws of information theory saying that any transformation cannot increase the amount of information, we get the basic restriction laid on models constructed from data: A model is acceptable if it does not contain more information than the input data file.

Úplný záznam
2017-12-07
15:36
Hidden Auto-Conflict in the Theory of Belief Functions
Daniel, M. ; Kratochvíl, Václav
Hidden conflicts of belief functions in some cases where the sum of all multiples of conflicting belief masses being equal to zero were observed. Relationships of hidden conflicts and auto-conflicts of belief functions are pointed out. We are focused on hidden auto-conflicts here - on hidden conflicts appearing when three or more numerically same belief functions are combined. Hidden auto-conflict is a kind of internal conflict. Degrees of hidden auto-conflicts and full non-conflictness are defined and analysed. Finally, computational issues of hidden auto-conflicts and non-conflictness are presented.

Úplný záznam
2017-12-07
15:36

Úplný záznam