|
|
Language Identification of Text Document
Cakl, Jan ; Pešán, Jan (referee) ; Szőke, Igor (advisor)
The thesis deals with a language identification of a text document. The final program includes three different implementation methods of language identification. The first method is based on a frequency statistics of N-gram. The second one represents Markov chains and the last one uses the simulated neural net for the identification purposes. The result is implemented in the Python language.
|
|
|
Fuzzy Markov chains and their use in risk management
Šindelková, Petra ; Vymazal, Tomáš (referee) ; Misák, Petr (advisor)
This thesis deals with the application of Markov chains for the production of concrete products. The theoretical part is focused on clarifying the concepts of risk management and describes the procedures for dealing with classical Markov chains. There are presented basics of fuzzy logic and finally there is explained the procedure using fuzzy logic in calculating of classical Markov chains in the subsection entitled Fuzzy Markov chains. The practical part describes production process, namely concrete pavements. On this production process is applied knowledge from the theoretical part and there is a comparison and evaluation of two methods of Marcov chains calculation (classic and fuzzy approach).
|
|
|
Music Improvisation
Angelov, Michael ; Hradiš, Michal (referee) ; Fapšo, Michal (advisor)
The thesis deals with problems concerning algorithmic music compositon, especially the domain of musical improvisation. There is an opening presentation of some of existing tools and approaches that are commonly used in domain of computer music. Consenquently there is a proposal of a new system, using main principles of markov chains and prediction suffix trees (PST) with description of its implementation. The main task of developped application is to analyze an external MIDI recording that is proposed to the system by user and create a new and inovative musical material in MIDI format that would sound close to the original recording giving an impression of a computer improvised music to the listener.
|
|
|
Counter-Example Generation in the Analysis of Markov Models
Molek, Martin ; Matyáš, Jiří (referee) ; Češka, Milan (advisor)
This thesis deals with generating counterexamples in context of probabilistic models. Counterexamples are generated for Markov models (specifically DTMC). Definitions of model properties are given by logic PCTL. Two algorithms (Best-first search and Recursive Enumration Algorithm) are used to generate these counterexamples. Thesis describes implementation of algorithms into verification tool STORM. The results of experiments show that REA is capable of handling models containg millions of states.
|
|
| |
|
| |
|
|
Application of (geo)demographic methods in education
Šebestík, Libor ; Hulíková Tesárková, Klára (advisor) ; Fialová, Ludmila (referee)
Application of (geo)demographic methods in education Abstract This master's thesis presents the possibilities of application of demographic, geodemographic and statistical methods on data published by the educational sector. The methods of demographic analysis are represented by the usage of rates, the concept of multistate demography (Markov chains) and the application of life tables. The enrollment ratio at particular levels of education, the average length of schooling and the number of dropouts from school grades are evaluated by these procedures. Markov chains which are based on the probabilities of transition between grades are also examined in terms of their use for forecasting purposes. These methods analyze the situation at the preschool, primary and secondary levels and are used on data from the annual Statistical Yearbooks on Education. In the field of geodemography, the so called preferential model of migration flows is presented. This model examines how applicants for tertiary education prefer or reject the regions of the Czech Republic for their tertiary education studies. The last method is the binary logistic regression which analyzes the inequalities in access to tertiary education. Both preferential model and logistic regression are based on data files on the admission process at...
|
|
|
Mixing cards and convergence of Markov chains
Drašnar, Jan ; Prokešová, Michaela (advisor) ; Beneš, Viktor (referee)
This thesis presents mixing of a deck of cards as a random walk on the group of permutations. Perfectly shuffled deck of cards is defined as uniform distribution on this group. For analysis of the distance between the uniform distribution and the current distribution of the Markov chain generated by the shuffling quite general methods are used that can be applied to many other problems - i.e. strong stacionary time, coupling and transformation to an inverse distribution. In the last chapter the riffle shuffle is studied and a rather well-known fact is proved that seven or eight shuffles should be enough to shuffle a deck of 52 cards.
|
|
|
Estimation in continuous time Markov chains
Nemčovič, Bohuš ; Prokešová, Michaela (advisor) ; Kadlec, Karel (referee)
Title: Estimation in continuous time Markov chains Author: Bohuš Nemčovič Department: Department of Probability and Mathematical Statistics Supervisor: RNDr. Michaela Prokešová, Ph.D., Department of Probability and Mathematical Statistics Abstract: In this work we deal with estimating the intensity matrices of continu- ous Markov chains in the case of complete observation and observation at selected discrete time points. To obtain an estimate we use the maximum likelihood met- hod. In the second chapter we first introduce the general EM algorithm and then adjust it for finding the intensity matrix estimate based on observations at disc- rete time points. In the last chapter we will illustrate the impact of the discrete step size on the quality of intensity matrix estimate. Keywords: Markov chains, intensity matrix, maximum likelihood estimation, EM algorithm 1
|
|
|
Analysis of number lotteries
Jedličková, Veronika ; Pawlas, Zbyněk (advisor) ; Lachout, Petr (referee)
This bachelor thesis focuses on most well-known lotteries on the Czech market, in particular Sportka and Loto. Thesis observes many aspects influencing progress of these games. Winnning prices and lottery participant's expectations are examined. Total sum of these winnings is influenced by the amount of money in jackpot. Therefore, jackpot sum modelling and period between wins is taken into account. Moreover, expected period between two jackpot hits, distribution of drawn numbers and probability of drawing the same winning sequence is examined.
|
guest ::
