|
|
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.
|
|
|
Musical genre classification
Káčerová, Erika ; Říha, Kamil (referee) ; Uher, Václav (advisor)
The aim of this bachelor thesis is creating a system for automatic music genre recognition. The thesis deals with two main issues, which are feature extraction of a genre and machine learning process. For the purpose of feature extraction a source code is written in JAVA programming language based on jAudio library. Six machine learning models are created in RapidMiner Studio software. The most appropriate one of them, Neural Networks method is then improved and tested on different parts of songs from database.These database contains 250 training songs and 25 test songs from five music genres: classical music, disco, drum and bass, hip hop and rock.
|
|
|
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.
|
|
|
Feature Selection Based on Combination of Uncorrelated Evaluation Functions
Vaculík, Karel ; Klusáček, Jan (referee) ; Honzík, Petr (advisor)
In order to process large amount of data, it is necessary to use computers. It is possible to use statistical methods or machine learning in some cases. In either case, data can be represented with large number of features. Selection of suitable subset of features can be crucial for efficient processing. This thesis explores a subgroup of feature selection methods which are called filter methods. Comparison of such methods is carried out and the results are used in the design of a new method. This new method uses a combination of existing methods.
|
|
|
Scalable machine learning using Hadoop and Mahout tools
Kryške, Lukáš ; Atassi, Hicham (referee) ; Burget, Radim (advisor)
This bachelor’s thesis compares several tools for building a scalable, machine learning platform and describes their advantages and disadvantages. It also practically demonstrates functionality of this scalable platform based on the Apache Hadoop and Apache Mahout tools and measures performance of the K-Means algorithm for total of five computing nodes.
|
|
|
Gender recognition from the text data
Mačát, Jakub ; Burda, Karel (referee) ; Červenec, Radek (advisor)
This bacheor`s work is focused on gender identification from a text just from an e-mail`s form and also contemporary techniques of data mining and text mining. The technique`s advantages and disadvantages and options of use. There was realized a program for recognizing gender in Java. In a program Rapid Miner is demostrated processing various learning methods. By both programs thete are described their basic attributes, used methods and operators used in the implementation. The programs were tested ona real data. Then there are mentioned methods for program`s extends. eventually there are given examples as the programs process stated assignment.
|
|
|
Methods for fast sequence comparison and identification in metagenomic data
Kupková, Kristýna ; Škutková, Helena (referee) ; Sedlář, Karel (advisor)
Předmětem této práce je vytvoření metody sloužící k identifikaci organismů z metagenomických dat. Doposud k tomuto účelu spolehlivě dostačovaly metody založené na zarovnání sekvencí s referenční databází. Množství dat ovšem s rozvojem sekvenačních technik rapidně roste a tyto metody se tak stávají díky své výpočetní náročnosti nevhodnými. V této diplomové práci je popsán postup nové techniky, která umožňuje klasifikaci metagenomických dat bez nutnosti zarovnání. Metoda spočívá v převedení sekvenovaných úseků na genomické signály ve formě fázových reprezentací, ze kterých jsou následně extrahovány vektory příznaků. Těmito příznaky jsou tři Hjorthovy deskriptory. Ty jsou dále vystaveny metodě maximalizace věrohodnosti směsi Gaussovských rozložení, která umožňuje spolehlivé roztřídění fragmentů podle jejich příslušnosti k organismu.
|
guest ::
