|
|
Semantic annotation of domain dependent data
Fišer, Dominik ; Vojtáš, Peter (advisor) ; Kopecký, Michal (referee)
One of the problems of semantic web is automated getting annotated data - web pages. Therefore this work is engaged in manual annotation of web pages and try to simplify this process for users using proposed methods. First part contains analysis of annotated data, users and vocabularies used for annotation. Afterwards are proposed methods which simplify annotation creation for users, the possibility of usage similar annotations or possibility highlight interesting parts of web page suitable for annotation. The work includes proposal of annotation tool user interface also that verifies proposed methods in practice. On the basis of this proposal was created a prototype implementation of the annotation tool Semantic Annotator as an extension for Google Chrome browser, which was also used for experiment verifying user-friendliness especially.
|
|
|
Koordinace mezi logickými agenty
Krištofič, Milutín ; Štěpánek, Petr (advisor) ; Vojtáš, Peter (referee)
In this thesis, we study the recent models for coordination and we propose a new model based on argumentation system. This system, named Argumentation BlackBoard for Coordination (ABBC), and its extension, Abstract ABBC, are based on successful argumentation approaches, such as abstract argumentation framework and defeasible logic programming. Our aim is to present necessary argumentation elements in open multi-agent system that consists of logic agents. In this work, we also describe a brief software design for the system.
|
|
|
Using Ontologies in GUHA Procedures
Zeman, Martin ; Ralbovský, Martin (advisor) ; Vojtáš, Peter (referee)
The goal of this master thesis is to implement some of the previously suggested ways of usage of Ontologies in Knowledge Database Discovery (KDD) process. The implementation is done in the Ferda environment, a modular environment for visual GUHA data mining. The work argues about each of the suggested ways of usage of ontologies in consideration of their successive implementation. Great part of the work is devoted to selection of the right language for representation of ontologies. Furthermore, the implementation of the selected modules in Ferda is described. The functionality of these modules is then tested on an example and there is evaluated the contribution of the modules for KDD process. At the end of the work the suggestions for future development of support of ontologies during the KDD process in Ferda DataMiner are described.
|
|
|
Recommender systems - models, methods, experiments
Peška, Ladislav ; Vojtáš, Peter (advisor) ; Jannach, Dietmar (referee) ; Krátký, Michal (referee)
This thesis investigates the area of preference learning and recommender systems. We concentrated recommending on small e-commerce vendors and efficient usage of implicit feedback. In contrast to the most published studies, we focused on investigating multiple diverse implicit indicators of user preference and substantial part of the thesis aims on defining implicit feedback, models of its combination and aggregation and also algorithms employing them in preference learning and recommending tasks. Furthermore, a part of the thesis focuses on other challenges of deploying recommender systems on small e-commerce vendors such as which recommending algorithms should be used or how to employ third party data in order to improve recommendations. The proposed models, methods and algorithms were evaluated in both off-line and on-line experiments on real world datasets and on real e-commerce vendors respectively. Datasets are included to the thesis for the sake of validation and further research. Powered by TCPDF (www.tcpdf.org)
|
|
|
Constraint Programming in Planning
Surynek, Pavel ; Barták, Roman (advisor) ; Vojtáš, Peter (referee) ; Štěpánková, Olga (referee)
This thesis deals with planning problems and Boolean satisfiability problems that represent major challenges for artificial intelligence. Planning problems are stated as finding a sequence of actions that reaches certain goal. One of the most successful techniques for solving planning problems is a concept of plan- ning graphs and the related GraphPlan algorithm. In the thesis we identified a weak point of the original GraphPlan algorithm which is the search for actions that support certain goal. We proposed to model this problem as a constraint satisfaction problem and we solve it by maintaining arc-consistency. Several propagation variants for maintaining arc-consis- tency in the model are proposed. The model and its solving process were integrated into the general GraphPlan-based planning algorithm. The performed experimental evaluation showed improvements in order of magnitude in several measured characteristics (overall solving time, number of backtracks) compared to the standard version of the GraphPlan algorithm. Next we proposed a stronger consistency technique for pruning the search space during solving the problem of finding supports. It is called projection consistency and it is based on disentangling the structure of the problem formulation. If the problem of finding sup- porting actions is...
|
|
|
User anotation of web resources using microformats
Toušek, Jiří ; Vojtáš, Peter (advisor) ; Dědek, Jan (referee)
This thesis explores the feasibility of using the principles of user-assisted annotation for semantic annotation of web resources using microformats. The main concept explored is the approach using the user assistance not to mine the data but to create a set of "annotation rules" that could then be used repeatedly to annotate the target data, without requiring further user assistance. The thesis considers multiple ways to represent these annotation rules. An important attribute of this approach is a chance these annotation rules could withstand changes in the data annotated as well as minor changes in the web resource structure. A prototype implementation is created as a part of this thesis on which these concepts are then verified.
|
|
|
Preferencev querying, indexing, optimisation
Horničák, Erik ; Vojtáš, Peter (advisor) ; Ondreička, Matúš (referee)
In this thesis we discuss the issue of searching the best k objects from the multi-users point of view. Every user has his own preferences, which are represented by fuzzy functions and aggregation function. This thesis designs and implements several solutions of searching the best k objects when attributes data are stored on remote servers. It was necessary to modificate existing algorithms for this type of obtaining data. This thesis uses several variants of Fagin algorithm, indexing methods using B+ trees and communication via web services.
|
|
|
Ontology mapping and mining with user preference
Maruščák, Dušan ; Vojtáš, Peter (advisor) ; Hoksza, David (referee)
In this diploma thesis we deal with the problem of ontology mining and mapping. Ontology mining is ontology learning from instance. First step to ontology mining is instance mining. We present method for ontology instance mining from web pages that contain structured data records. We use HTML tree of the page to detect data records. We search data records only in relevant branches of HTML tree and we identify also non-contiguous records. Next we present method to identify attributes of record and their mapping into attributes of ontology concepts. We discuss also several alternative methods including OCR usage for processing visual form of web document . Results of experiments on several types of web documents show a right direction of our research.
|
|
|
Interactive Gantt Charts
Skalický, Tomáš ; Barták, Roman (advisor) ; Vojtáš, Peter (referee)
This work deals with problems of interactive rescheduling in Gantt charts. The goal of the work is to design and implement an algorithm which resolves the inconsistencies in a schedule. First existing approaches are studied. Algorithm for solving our inconsistencies in a schedule is the most important contribution of this work. It is introduced there and there is also it's proof of correctness and finiteness. Demonstration of applicability of the algorithm follows. For this reason, program GanttViewer which is a part of this work is used. Finally, this program is described in detail.
|
|
|
Query languages for the Semantic web
Galgonek, Jakub ; Yaghob, Jakub (advisor) ; Vojtáš, Peter (referee)
The idea of the Semantic Web brings new requirements such as to create and store metadata of documents or resources. Also ability to search in such metadata is needed. Existing query languages for the Semantic Web are unfortunately either too weak or have complicated syntax or semantics. The aim of this thesis is to compare existing Semantic Web query languages and to propose new one considering its expression strength. This comparison is done by juxtapositioning of their approaches to various issues in querying. Such issues are, for example, a basic selection of data, an ability to select data with recursively defined structure, creating data, a way of working with blank nodes, etc. On the basis of this comparison, the Tequila language is proposed. The Tequila is based on named pattern and provide general recursion. This thesis also shows the way how to use Tequila language and further, it compares the Tequila with other query languages.
|
guest ::
