|
|
Filter interesting rules in EasyMiner system
Duben, Přemysl Václav ; Vojíř, Stanislav (advisor) ; Zeman, Václav (referee)
Postprocessing is like data preparation one of the most challenging tasks in data mining that users must deal with. It is desirable to simplify it so that the path to results is as fast and efficient as possible. The extension of the EasyMiner research project to filter the association rules by similarity to the knowledge-based rules, should be helped in this respect, which is the subject of this diploma thesis. The objectives were accomplished by a detailed analysis of the default state of EasyMiner in conjunction with a thoroughly thought-out implementation proposal without increasing the demands on the server or user of the application. An analysis of general practices and the author's deep knowledge of Internet application issues served to do this. The future deployment of this extension to the EasyMiner infrastructure will benefit from a clearer and more efficient work with the Knowledge base part, where it will no longer be necessary to evaluate the interest in the same or similar rules and the user will be able to focus directly on the quality of the results. This thesis is divided into chapters as a detailed description of how a similar problem can be approached in any other project that works with a certain form of knowledge base. Initial input analysis with access search for comparison of the various elements passes through a description of the default application state to a specific solution design. This should be a guideline for the implementation itself and for the testing of the proposed and implemented procedures.
|
|
|
Creation of interface for creating apriori association rules
Balhar, Jakub ; Kliegr, Tomáš (advisor) ; Hazucha, Andrej (referee)
This work aims at finding or creating web application, which allows user to easily create and edit constructs similar to association rules. I summarized and compared existing solutions in the first part and decided that none of these solutions meets the requirements of SEWEBAR project. In the second part I focus on the formats, used for communication with world outside the application and for communication betweeen parts of the applications. This is followed by definition of the web application, which I created and in the end of this part I explain in deep the architecture of the application. The resulting application is part of the SEWEBAR project, but it is written in the way, which makes it easy to deploy it to any other web projects, which needs to create or edit constructs similar to association rules. In the work I also cover possible configurations for this deployment.
|
|
|
Application of KDD on the data of plastic surgery clients
Šotlík, Jakub ; Rauch, Jan (advisor) ; Tomášek, David (referee)
The main objective of my thesis is to analyze data about clients of plastic and aesthetic surgery with methods and tools of the Knowledge Discovery in Databases and to find as many useful knowledge as possible from the data's owner view (the knowledge consists of verbal rules expressing relationships between two entities). Found knowledge will be presented in SEWEBAR system. Elaboration of my work is in accordance with CRISP-DM methodology that is used for the Knowledge Discovery in Databases. Analytical questions will be solved by LISp-Miner software that uses analytical procedure 4ft-Miner of the GUHA method. Found relationships will be presented in SEWEBAR system and some interesting relationships will be presented in this work. The main purpose of the thesis is to find useful knowledge of plastic and aesthetic surgery branch from both business and medical view. From medical point of view the work finds knowledge about medical and psychological status of clients. From business point of view the work finds knowledge for management. The thesis is structured to correspond with CRISP-DM methodology where every phase of methodology has one chapter. There is result of every phase described in every chapter together with the description of my work on phase.
|
|
|
Aplikace procedury Ac4ft-Miner na medicínská data
Nekvapil, Viktor ; Rauch, Jan (advisor) ; Šimůnek, Milan (referee)
This bachelor thesis deals with the data mining procedure Ac4ft-Miner, implemented in the LISp-Miner system, which is developed at the Department of Information and Knowledge Engineering at the University of Economics, Prague. The aim of this thesis is firstly to describe the procedure in a simple, understandable way. Secondly, the aim is to apply this procedure on the medical data and present examples of use of this procedure. Further aim is to create methodology of use for doctors from the experience obtained. The aims are reached by using a lot of examples, which demonstrate theoretical concepts on concrete data and by the pursuit of the simple visualisation of tasks (analytical questions) solved by the procedure. The output of this thesis is a coherent text with lot of examples separated from the continuous text; so the reader familiar with a particular topic can skip the examples and proceed to the next issue. Further result of this thesis is an outline of the graphical presentation of analytical questions. Both the examples and the graphical presentation will be used further in the SEWEBAR project of which this thesis is one part. The methodology of use of the procedure for doctors is in the form of advices for use of the tool which should contribute to the further research which is needed. This is because of the high complexity of the procedure, which does not allow formulating general conclusions usable in the methodology. Chapter 1 characterizes the overall process of Knowledge Discovery in Databases represented by the CRISP-DM Methodology. Chapter 2 presents theoretical concepts related to Ac4ft-Miner. Chapter 3 deals with action rules. Chapter 4 addresses possibilities of defining the input and interpretation of the output of the Ac4ft-Miner. Chapter 5 describes the research conducted on the real medical data set ADAMEK, states methodology and examples of the output. Chapter 6 summarises the experience obtained and formulates the methodology of use of Ac4ft-Miner for doctors.
|
|
|
CMS Joomla! and Ontopia Knowledge Suite Integration
Hazucha, Andrej ; Kliegr, Tomáš (advisor) ; Nekvasil, Marek (referee)
The aim of this thesis is to outline issues related to integration of Content Management Systems and Knowledge Bases based on semantic web technologies. The work begins with semantic technologies research and their use cases. The possibilities and proposals of integration of these technologies into CMS and collaborative wikis are discussed. As far as the most of open-source CMS are based on PHP platform tools written in PHP are insisted. CMS Joomla! and Ontopia Knowledge Suite integration is demonstrated in practical the part of the thesis. Possibility to communicate with different systems that allow HTTP requests is presented, too. Joomla! and OKS communication is through RESTful TMRAP protocol implemented in OKS. The query language used in this case is tolog. Communication with SPARQL endpoint or XML database is also demonstrated. Raw XML returned from Knowledge Base data source is transformed by XSLT into (X)HTML fragments. The transformations are user defined. Created demo application is included into SEWEBAR project. This application enables to incorporate results of semantically rich queries into analytical reports of data mining tasks within CMS Joomla! Interface.
|
|
|
Knowledge Processing within the GUHA Method
Šťastný, Daniel ; Rauch, Jan (advisor) ; Kliegr, Tomáš (referee)
This study presents an introduction into the data-mining methodology CRISP-DM (CRoss-Industry Standard Process for Data Mining). It provides a fundamental description of association rules and the GUHA method (General Unary Hypotheses Automaton) with related 4ft-Miner, SD4ft-Miner and Action Rules. The examples are shown on real data. Sequentially the study describes the role of the domain knowledge and the project SEWEBAR (SEmantic WEb and Analytical Reports) held at UEP. The practical output of this work is the XML Schema definition for the markup language BKEF (Background Knowledge Exchange Format) designed within the SEWEBAR and the transformation file programmed in the XSL ensuring visualization of the content of any BKEF file.
|
guest ::
