|
|
Prediction of Values on a Time Line
Maršová, Eliška ; Bařina, David (referee) ; Zemčík, Pavel (advisor)
This work deals with the prediction of numerical series whose application is suitable for prediction of stock prices. They explain the procedures for analysis and works with price charts. Also explains the methods of machine learning. Knowledge is used to build a program that finds patterns in numerical series for estimation.
|
|
|
Fundamental Analysis of Numerical Data for Automatic Trading
Huf, Petr ; Szőke, Igor (referee) ; Černocký, Jan (advisor)
This thesis is aimed to exploitation of fundamental analysis in automatic trading. Technical analysis uses historical prices and indicators derived from price for price prediction. On the opposite, fundamental analysis uses various information resources for price prediction. In this thesis, only quantitative data are used. These data sources are namely weather, Forex, Google Trends, WikiTrends, historical prices of futures and some fundamental data (birth rate, migration, \dots). These data are processed with LSTM neural network, which predicts stocks prices of selected companies. This prediction is basis for created trading system. Experiments show major improvement in results of the trading system; 8\% increase in success prediction accuracy thanks to involvement of fundamental analysis.
|
|
|
Optical Character Recognition Using Convolutional Networks
Csóka, Pavel ; Behúň, Kamil (referee) ; Hradiš, Michal (advisor)
This thesis aims at creation of new datasets for text recognition machine learning tasks and experiments with convolutional neural networks on these datasets. It describes architecture of convolutional nets, difficulties of recognizing text from photographs and contemporary works using these networks. Next, creation of annotation, using Tesseract OCR, for dataset comprised from photos of document pages, taken by mobile phones, named Mobile Page Photos. From this dataset two additional are created by cropping characters out of its photos formatted as Street View House Numbers dataset. Dataset Mobile Nice Page Photos Characters contains readable characters and Mobile Page Photos Characters adds hardly readable and unreadable ones. Three models of convolutional nets are created and used for text recognition experiments on these datasets, which are also used for estimation of annotation error.
|
|
|
Dolování znalostí z rozsáhlých statistických souborů lékařských dat
Badelita, Elvyn-George
Final thesis deals with information-mining from large sets of medical data using methods and machine learning algorithms. The subject of the theoretical part is machine learning and its distribution, description of the basic data types in data mining, most important classifications and predictions methods, criterion defining the quality of prediction methods, description of data mining methodology and frequently used systems. The practical part focuses on statistical and informatics survey of provided medical data, appropriate transformation, subsequent design and implementation of experiments using machine learning methods to acquire new knowledge and hidden information and finally interpretation of the results together with conclusions for target groups.
|
|
|
Analýza pokrytí území metodami dálkového průzkumu země
Chodúr, Martin
This thesis deals with the use of remote sensing methods for the land use analysis. On the evaluation of already used methods and procedures, own solution that simplifies the whole process at the expense of accuracy of classification is designed and tested. The proposed method offers a different view on the issue and possibilities for its further development.
|
|
|
Použití evolučních a genetických algoritmů v ekonomických aplikacích
Popelka, Ondřej
This thesis describes new evolutionary artificial intelligence methods suitable for solving complex tasks. These include planning, optimization, decision, prediction and other problems. All of these are tasks which an intelligent human being can quickly learn to solve, yet they cannot be solved by machines in reasonable time. For this type of problems usually no analytical method or algorithm exists. These challenges represent the domain for artificial intelligence. This work concentrates on evolutionary methods of artificial intelligence based on genetic algorithms. Specifically grammatical evolution and differnetial evolution are described. The first part of this thesis describes the principles of genetic algorithms especially those used in grammatical evolution. Later the grammatical evolution method is described. Grammatical evolution is a genetic algorithm extended with a context-free grammar processor. This enables it to generate structured strings in an arbitrary language defined by a regular or context-free grammar. Second part of this work focuses on description of a generic computational system, which enables user-friendly control of grammatical evolution. The architecture of the system is thoroughly described. It composes of a computation service, database server and completely separated user interface. Also the problems solved using this system are described. These include symbolic regression, classification and generation of combinatorial logic circuits. All of these tasks were solved using the described implementation.
|
|
|
Automatic recognition of meaning in texts
Jeleček, Jiří ; Dvořák, Pavel (referee) ; Povoda, Lukáš (advisor)
As part of this work it was designed and implemented a system using data mining techniques from the text in order to detect emotions in Czech, English and German language texts. Because the system is built mostly on machine learning techniques, was designed and created training set, which was later used to build the model classifier using the selected algorithms.
|
|
| |
|
|
Segmentation of MR images using machine learning algorithms
Dorazil, Jan ; Mikulka, Jan (referee) ; Dvořák, Pavel (advisor)
This thesis concerns with magnetic resonance image segmentation using Random Forests algorithm. Employed technologies accomplishing the specified task include C++ progra- mming language with libraries ITK and OpenCV. This work descibes the technique of processing images from loading through preprocessing to the actual segmentation. The outcome from this work is a programme that automatically segmentates MR images of mouse’s head to the brain and the surroundings.
|
|
|
Procedural programming in database
Nimrichter, Adam ; Povoda, Lukáš (referee) ; Uher, Václav (advisor)
Thesis deals with verification of concept of performing calculations inside database. Describes PostgreSQL database, its features and procedural language PL/pgSQL. Also focuses on machine learning methods, implementation of forward selection algorithm and verification of his functionality. Frequently used tool is MADlib, which is an open-source library of scalable in-database algorithms for machine learning, statistics and other analytic tasks.
|
guest ::
