|
|
Digital Steganography for Executables
Bever, Ľuboš ; Šimek, Václav (referee) ; Strnadel, Josef (advisor)
Steganography for executable files is the least common steganography. Research in this area has subsided after several, not many, attempts to implement it. The aim of this work is the implementation of existing methods and its modification proposal. Extensible software that has been created, can be also used to implement other methods. The implemented methods were properly tested, evaluated and compared. The comparison results show, that the used instruction substitution method, roughly corresponds to its reference value 1/110, however the results are highly dependent on the input binaries. The proposed extension of this method averages a data rate of 1/84, which is only 1.5 times less than the value obtained from another existing implementation in which specialized software was used to search for equivalence classes. The maximum data rate obtained from test programs is 1/38.
|
|
|
A Tool for Recognition and Verification of Spedition Orders
Kalivoda, Vojtěch ; Hradiš, Michal (referee) ; Herout, Adam (advisor)
The aim of this work is to design and implement a web tool that will facilitate the work of dispatchers of forwarding and transport companies through automated recognition of important information in orders. Thanks to the recognition, not all information has to be manually rewritten by dispatchers, which saves time. Order recognition is based on finding entities in a document, representing its surroundings with vectors using word2vec models and subsequent classification using convolutional neural networks. The tool can recognize 20 types of information in real time with an average success rate of 72.35~\%. As part of the work, a dataset of almost 1~700 orders was collected and 141 of them were annotated. Part of the work is a web application that serves as an interface for the tool and data collection.
|
|
|
Detecting semantic relations in texts and their integration with external data resources
Kríž, Vincent ; Vidová Hladká, Barbora (advisor)
We present a strategy to automate the extraction of semantic relations from texts. Both machine learning and rule-based techniques are investigated and the impact of different linguistic knowledge is analyzed for the various approaches. To implement the extraction system RExtractor, several natural language processing tools have been improved: from sentence splitting and tokenization modules to dependency syntax parsers. Furthermore, we created the Czech Legal Text Treebank with several layers of linguistic annotation, which is used to train and test each stage of the proposed system. As a result of the performed work, new Semantic Web resources and tools are available for automatic processing of texts.
|
|
|
System for Web Data Source Integration
Kolečkář, David ; Bartík, Vladimír (referee) ; Burget, Radek (advisor)
The thesis aims at designing and implementing a web application that will be used for the integration of web data sources. For data integration, a method using domain model of the target information system was applied. The work describes individual methods used for extracting information from web pages. The text describes the process of designing the architecture of the system including a description of the chosen technologies and tools. The main part of the work is implementation and testing the final web application that is written in Java and Angular framework. The outcome of the work is a web application that will allow its users to define web data sources and save data in the target database.
|
|
|
Extraction of information from identity documents
Hudcovský, Erik ; Lattenberg, Ivo (referee) ; Caha, Tomáš (advisor)
This thesis is about the processing information from personal documents (ID card or passport) into the form that is further easily to be processed for computers and the IT industry in general. This process is implemented by the application I developed as part of my bachelor's thesis. The application contains the scanned document, the document type and the form of the required output. As the output we get the document type in the required format. The entire application is using in process an external OCR tool (OpticalCharacter Recognition), which is implemented so that it can be easily replaced by another OCR tool. I used Tesseract in my application. This OCR tool is the simpliest and most accurate of the free OCR tools at the same time. It also has strong community support and is still being developed. In this thesis, I also focused on its testing, both on the samples of text I created, and on real scans of documents. The application is also processed as an installation package, so it can be easily imported into other projects. The entire application is displayed as OpenSource on GitHube under the free license of MIT.
|
|
|
Brno Communication Agent
Jurkovič, Juraj ; Fajčík, Martin (referee) ; Smrž, Pavel (advisor)
The goal of this thesis is explore and subsequently apply techniques and technical solutions in development of information agents. Thesis primarily focuses on solving individual sub tasks using state of the art systems, interconnecting these systems, their adoption for specific domain and implementation of individual modules of communication agent system. User interface is based on multi-platform chat application Telegram. Information extraction from user input is executed by Dialogflow. Several external services are used for user request fulfillment. Elasticsearch is used for searching structured data. For answering open domain questions from free text we use R-net implementation. The resulting can have both ,its knowledge base and range of requests it can fulfill, easily extended and can be deployed to chat platform of choice.
|
|
|
Extraction of Semantic Relations from Text
Pospíšil, Milan ; Schmidt, Marek (referee) ; Smrž, Pavel (advisor)
Today exists many semi-structured documents, whitch we want convert to structured form. Goal of this work is create a system, that make this task more automatized. That could be difficult problem, because most of these documents are not generated by computer, so system have to tolerate differences. We also need some semantic understanding, thats why we choose only domain of meeting minutes documents.
|
|
|
Detecting semantic relations in texts and their integration with external data resources
Kríž, Vincent ; Vidová Hladká, Barbora (advisor) ; Harašta, Jakub (referee) ; Pecina, Pavel (referee)
We present a strategy to automate the extraction of semantic relations from texts. Both machine learning and rule-based techniques are investigated and the impact of different linguistic knowledge is analyzed for the various approaches. To implement the extraction system RExtractor, several natural language processing tools have been improved: from sentence splitting and tokenization modules to dependency syntax parsers. Furthermore, we created the Czech Legal Text Treebank with several layers of linguistic annotation, which is used to train and test each stage of the proposed system. As a result of the performed work, new Semantic Web resources and tools are available for automatic processing of texts.
|
|
|
Detecting semantic relations in texts and their integration with external data resources
Kríž, Vincent ; Vidová Hladká, Barbora (advisor)
We present a strategy to automate the extraction of semantic relations from texts. Both machine learning and rule-based techniques are investigated and the impact of different linguistic knowledge is analyzed for the various approaches. To implement the extraction system RExtractor, several natural language processing tools have been improved: from sentence splitting and tokenization modules to dependency syntax parsers. Furthermore, we created the Czech Legal Text Treebank with several layers of linguistic annotation, which is used to train and test each stage of the proposed system. As a result of the performed work, new Semantic Web resources and tools are available for automatic processing of texts.
|
|
|
Automated Extraction of Information from Emails
Kanda, Rastislav ; Zbořil, František (referee) ; Vídeňský, František (advisor)
The purpose of this thesis is to familiarize oneself with methodology of information extraction from text. On the basis of acquired knowledge, propose a design and implement a system, which should be capable of gathering information from email messages. Proposed system should help Kiwi.com s.r.o. with processing of incoming email messages from travel companies. In current situation it is possible to process those email messages automatically. However, to process those messages automatically, it is necessary to manually create a template suitable for extraction. Possible alteration could be algorithm ROBULA+, which can generate more robust XPath locator from given XPath locator. These locators should be more resistant to changes in the HTML structure. ROBULA+ algorithm is a central point of automated creation of templates suitable for parsing email messages. Implemented system can be qualified with satisfactory successivity (approximately 75%). This means that system is able to find reference to created reservation in three out of four cases.
|
guest ::
