|
|
Automation of a data mining process in the road accidents data from London by the LISp-Miner system
Soukup, Tomáš ; Rauch, Jan (advisor) ; Vojíř, Stanislav (referee)
This thesis is focused on the area of automated data mining and to describe steps associated with solving analytical questions using the LISp-Miner system in the data with road accident records. Analytical tasks were primarily created based on domene knowledge from road accidents statistics in Great Britain and from previous analysis in my semestral project. The aim of this thesis is creation of an automated data mining process for analyze the input data by applying 4ft-Miner, Ac4ft-Miner a SD4ft-Miner procedures, and looking for a new knowledge for every single year of the analyzed period. The implementation language is the LMCL language that enables usage of the LISp-Miner system's functionality in an automated way. These created scripts could be used for analyses of another dataset with the same structure or with some manual changes in initial parameters for the quite different data.
|
|
|
Use of data mining techniques for open data
Prokůpek, Miroslav ; Rauch, Jan (advisor) ; Chudán, David (referee)
This diploma thesis examines applications of datamining methods to open data. It is realized by solving analytical questions using the LISp-Miner system. Analytical questions are examined in data from The Czech Trade Inspection Authority from the perspective of the data owner. Procedure used to solve analytical questions is 4ft-Miner. There are presented and resolved four analytical questions, which are the results of the work. Work includes a detailed description of the transformation of the relational database into a format suitable for data mining. A detailed description of the data is also included. The theoretical part deals with the GUHA method and CRISP-DM methodology.
|
|
|
Analysis of real data from Alza.cz product department using methods of KDD
Válek, Martin ; Berka, Petr (advisor) ; Kliegr, Tomáš (referee)
This thesis deals with data analysis using methods of knowledge discovery in databases. The goal is to select appropriate methods and tools for implementation of a specific project based on real data from Alza.cz product department. Data analysis is performed by using association rules and decision rules in the Lisp-Miner and decision trees in the RapidMiner. The methodology used is the CRISP-DM. The thesis is divided into three main sections. First section is focused on the theoretical summary of information about KDD. There are defined basic terms and described the types of tasks and methods of KDD. In the second section is introduced the methodology CRISP-DM. The practical part firstly introduces company Alza.cz and its goals for this task. Afterwards, the basic structure of the data and preparation for the next step (data mining) is described. In conclusion, the results are evaluated and the possibility of their use is outlined.
|
|
|
Utilization of System LISp-Miner in the Analysis of the Factors Influencing the Dominance of Cyanobacteria in Phytoplankton
Hlaváčová, Tereza ; Šimůnek, Milan (advisor) ; Potužák, Jan (referee)
The aim of this work is to describe steps associated with solving analytical questions using the LISp-Miner in the data from water-analyzes of 12 ponds in South Bohemia in the period from year 2007 to 2012. Analytical questions are primarily focused on issues of cyanobacteria, based on instructions of data-owner, Povodí Vltavy, státní podnik. Apart from a description of the application of procedures KL-Miner, CF-Miner and 4ft-Miner on data, the work aims to prepare an automating process based on steps made during using procedures. The theoretical part is a summary of the basic concepts and principles associated with association rules and GUHA method. The practical part follows the CRISP-DM methodology. The result is a proposal of automation process by which it is possible to look for interesting rules in the hydrobiological and hydrochemical data. Then there is a set of recommendations for better utilization of database for KDD, with proposals how to modify and prepare the data.
|
|
|
Analýza dát z oblasti kontroly kvality použitím systému LISp-Miner
Štefke, Martin ; Šimůnek, Milan (advisor) ; Srogoňová, Kristína (referee)
Objective of the bachelor thesis is analysis of occurrence of non-conforming products in SEWS Slovakia. There were analyzed production defects from the period January 2013 to October 2014, the analysis was perform from the database in the academic system LISp-Miner. In the initial theoretical part is a summary of the different approaches to the issue of knowledge discovery from databases.The following practical part is described the treatment and processing of data,define the basic analytic issues. At the end there are defined relevant relationship betweendata and analytical methods.
|
|
|
Combining OLAP and data mining for analysis on trainee dataset
Borokshinova, Anastasia ; Chudán, David (advisor) ; Šimůnek, Milan (referee)
The aim of this thesis is to show the possibility of combining two data analyses techniques OLAP and data mining in a certain area. The principal method of achieving the aim will be continuous comparison and check of acquired results using two techniques. A practise dataset on credits provided to physical persons is used for practical application. The data analysis will be performed using Power Pivot MS Excel complement and LISp-Miner system. For work with LISp-System the 4ft Miner procedure will specifically be used, which proceeds according to respected CRISP-DM data mining methodology. The thesis added value consists first of all in presentation of a possibility of OLAP and data mining linkage on the same dataset, thus reducing the number of erroneous conclusions which analysers might arrive at on the basis of one technique. Other benefits consist in presentation of relational data transfer to multi-dimensional structure and practical options of 4ft-Miner system LISp-Miner procedure usage.
|
|
|
Srovnání vybraných nástrojů dobývání znalostí z databází z hlediska implementace asociačních pravidel
Lízler, Robert ; Nekvapil, Viktor (advisor) ; Rauch, Jan (referee)
This bachelor thesis deals with a comparison between two selected data mining software tools, LISp-Miner, developed at the department of information and knowledge engineering at the faculty of informatics and statistics of the University of Economics, Prague, and Rapidminer, a globally popular software suite. The focus of the comparison is mining for association rules. The aim of this work is first to provide a user-oriented evaluation of how the software tools compare in the selected area and second to attempt to discover some interesting differences between the results of how the software tools implement association mining procedures. To reach these goals, the software tools will be tested and evaluated by the author according to a selected set of criteria, grouped into 3 categories: functionality, usability and performance. The work is structured as follows: chapter 1 sets out some theoretical background and introduces the software tools, chapter 2 evaluates the available functionality of the tools for various steps of the overall association mining procedure, chapter 3 rates the software tools based on their usability and user-friendliness, while chapter 4 summarises the results of testing the software tools on a selected data set.
|
|
|
The real application of methods knowledge discovery in databases on practical data
Mansfeldová, Kateřina ; Máša, Petr (advisor) ; Kliegr, Tomáš (referee)
This thesis deals with a complete analysis of real data in free to play multiplayer games. The analysis is based on the methodology CRISP-DM using GUHA method and system LISp-Miner. The goal is defining player churn in pool from Geewa ltd.. Practical part show the whole process of knowledge discovery in databases from theoretical knowledge concerning player churn, definition of player churn, across data understanding, data extraction, modeling and finally getting results of tasks. In thesis are founded hypothesis depending on various factors of the game.
|
|
|
Automation of a data mining process by the LISp-Miner system
Ochodnická, Zuzana ; Šimůnek, Milan (advisor) ; Rauch, Jan (referee)
This thesis is focused on the area of automated data mining. The aim of this thesis is a description of the area of automated data mining, creation of a design of an automated data mining tasks creation process for verification of set domain knowledge and new knowledge search, and also an implementation of verification of set domain knowledge of attribute dependency type influence with search space adjustments. The implementation language is the LMCL language that enables usage of the LISp-Miner system's functionality in an automated way. These data analyses were performed on data from air pollution monitoring. The design and implementation were successful and the created scripts could be used (with some manual changes in initial parameters) for analyses of another dataset as well.
|
|
|
Application of knowledge discovery methods in the field of cardiac surgery
Čech, Bohuslav ; Berka, Petr (advisor) ; Aiglová, Květoslava (referee)
This theses demonstrate practical use of knowledge discovery in the field of cardiac surgery. The tasks of the Department of Cardiac Surgery University Hospital Olomouc are solved through the use of GUHA method and LISp-Miner system. Mitral valve surgery data comes from clinical practice between the years 2002 and 2011. Theoretical part includes chapter on KDD -- type of tasks, methods and methodology and chapter on cardiac surgery -- anatomy and functions of heart, mitral valve disease and diagnostic methods including quantification. Practical part brings solutions of the tasks and whole process is described in the spirit of CRISP-DM.
|
guest ::
