|
|
Text Classification Methods in the Context of Web Pages
Trstenský, Patrik ; Bartík, Vladimír (referee) ; Burget, Radek (advisor)
This work deals with the issue of text classification in the context of websites. It examines available classification methods and their accuracy over web page plain text. It deals with constructing a dataset for training these methods for a specific domain. We obtain data for creating the dataset from publicly available websites that utilize RDF documents defined in HTML code. The conclusion of the work consists of the creation of two datasets for two different domains. Furthermore, the use of these datasets for training models and testing of their accuracy.
|
|
|
Checking SQL Code Properties
Bali, Filip ; Bartík, Vladimír (referee) ; Rychlý, Marek (advisor)
This thesis focuses on checking the properties of SQL code based on static analysis using predefined rules. The rule represents a basic element of the check. The user can define their own rule and include it in the check. A rule usually contains a set of conditions that are contained in an algorithm that checks nodes in an abstract syntactic tree. Abstract syntactic tree is created from an input SQL statement and customized so that rules can be applied over its nodes. If the rule detects an error, then it can generate a report. These reports are then displayed on the selected output. Based on the thesis, an open source program in the Python3 programming language was implemented. This program is publicly available.
|
|
|
System for Service Workers’ Routes Planning
Mlčoch, Michal ; Bartík, Vladimír (referee) ; Hynek, Jiří (advisor)
This bachelor’s thesis deals with the issue of service requests arising in smart cities and their planning into the routes for service workers. The thesis discusses the issue of the concept of smart cities, route optimization and analysis of services providing route optimization. This work aims to create a system for planning the routes of service workers for the smart city platform developed by Logimic. The main functionality is to enable route optimization through third-party services, and the emphasis is on being able to easily change the thirdparty service providing the optimization.
|
|
|
Classification with Use of Neural Networks in the Keras Environment
Pyšík, Michal ; Burgetová, Ivana (referee) ; Bartík, Vladimír (advisor)
Tato práce zkoumá problematiku klasifikace pomocí umělých neuronových sítí s využitím knihovny Keras, poskytující vysokoúrovňové rozhraní pro práci s umělými neuronovými sítěmi v programovacím jazyce Python. Cílem práce je prozkoumat rozsáhlé možnosti této knihovny v oblasti klasifikace a porovnat různé typy a topologie umělých neuronových sítí formou experimentů na vybraných datasetech, což je doplněno jednoduchou experimentální aplikací sloužící především jako rozhraní pro tyto experimenty.
|
|
|
Application for Communication between Volunteers and Seniors
Pomkla, František ; Hynek, Jiří (referee) ; Bartík, Vladimír (advisor)
The Moudrá Síť app provides a platform for seniors and volunteer assistants to communicate and help seniors solve digital technology problems. The main goal of this project is to educate seniors and to increase their digital literacy. This thesis focuses also on technologies for web application development, the use of CRM systems for database development, Vercel web hosting, and web accessibility. Next, the basic principles and technologies for creating chatbots are presented. The result of the thesis is a functional web application already tested by seniors as well as a comparison of two chatbot solutions based on the GPT model and the Dialogflow platform using its knowledge base.
|
|
|
Knowledge Discovery from Spatio-Temporal Data
Liptáková, Daša ; Burgetová, Ivana (referee) ; Bartík, Vladimír (advisor)
This thesis deals with knowledge discovery from spatio-temporal data. Firstly, it describes the general principles of knowledge discovery and then knowledge discovery from spatio-temporal data, where it mainly focuses on methods for detecting outlying trajectories of moving objects. In the next section, the thesis describes the design and implementation of the mining task and demonstration application. Finally, several experiments are performed over three different datasets.
|
|
|
Layout-based Data Extraction from Documents
Sedláček, Martin ; Bartík, Vladimír (referee) ; Burget, Radek (advisor)
This thesis deals with automated data extraction from medical reports in PDF format based on document layout analysis. The main content of the thesis is an introduction to data extraction, a comparison of existing tools and a presentation of the design and requirements of the developed tool, which will be based on the FitLayout application framework. The thesis then describes the actual implementation of the tool in Java and comments on the results achieved by the tool on real data.
|
|
|
Machine Learning Methods for Web Documents
Katrňák, Josef ; Bartík, Vladimír (referee) ; Burget, Radek (advisor)
This work aims to use machine learning techniques for the classification of specific parts of web page content. First, current methods for representing and classifying web page content using machine learning methods are described. For web page representation, the thesis focuses on the experimental tool FitLayout, whose visual representation of web pages serves as input for further processing and subsequent training of machine learning models. The work results in trained models that classify specific parts of the web page content. The model architecture is based on graph neural networks. For the experiments, a dataset of publicly available websites containing pages of products sold online is used. The advantage of the proposed and implemented approach is information extraction independent of the structure and language of a web page.
|
|
|
K-Nearest Neighbour Search Methods
Cigánik, Marek ; Bartík, Vladimír (referee) ; Burgetová, Ivana (advisor)
The thesis describes the basic concept of the K-nearest neighbors algorithm and its connection with the human concept of object similarity. Concepts and key ideas such as the distance function or the curse of dimensionality are elaborated. The work includes a detailed description of the methods KD-Tree, Spherical Tree, Locality-Sensitive Hashing, Random Projection Tree and families of algorithms based on the nearest neighbor graph. An explanation of the idea with visualizations, pseudocodes and asymptotic complexities is provided for each method. The methods were subjected to experiments and both basic and more advanced metrics were measured and appropriate use cases for individual methods were evaluated.
|
|
|
Use of Data Mining for Payment Identification
Bartoš, Stanislav ; Burget, Radek (referee) ; Bartík, Vladimír (advisor)
This master thesis concentrates on design and implementation of a system for payment identification, even if the reliable identifier (e.g. variable symbol) is missing. Data mining techniques, such as classification and prediction, were used as a solution to this problem. This master thesis is company assignment for company "Platební instituce Roger a.s.".
|
guest ::
