|
|
Implementation of Mining Modules of Data Mining System on NetBeans Platform
Stríž, Rostislav ; Bartík, Vladimír (referee) ; Šebek, Michal (advisor)
Data collecting plays an important role in many aspects of today's businesses and quality information is the key to success. Process called Knowledge Discovery in Databases makes possible to extract hidden information that can be used further in our efforts. Main goal of this thesis is to describe an addition to such Data Mining System. Main objective is to create data mining module for NetBeans application, developed for demonstrational purposes by Faculty of Information Technology. New module is going to be able to mine information from Oracle database server via unusual use of Genetic Algorithm. This thesis describes the whole process of module implementation, begining with theoretical basics through coding details to final testing and summary.
|
|
|
Implementation of Algorithms Based on Decision Trees in C#
Grolig, Lukáš ; Pešek, Martin (referee) ; Stríž, Rostislav (advisor)
This bachelor thesis is focused on selection of data mining algorithms based on decision trees for an analytical system developed under the project System for the Internet security increase based on malware spreading analysis. Selected algorithms are described in greater detais, as well as their implementation in the C# language. These algorithms are then tested with regards to their training speed and classification accuracy. Finally, this thesis presents further conclusions and recommendations based on performed experiments.
|
|
|
Predicting Future Location of a Moving Object
Kebísek, Ján ; Stríž, Rostislav (referee) ; Pešek, Martin (advisor)
This thesis deals with the design and the implementation of the application for predicting future location of a moving object. It describes a method for prediction based on the algorithm WhereNext. This algorithm obtains T-Patterns from a database of trajectories of objects, which represent frequent patterns of movement of objects, and those subsequently uses for prediction. The algorithm was implemented in programming language Java and its functionality was tested on a generated dataset of movement of cars.
|
|
|
Periodic Patterns Mining
Stríž, Rostislav ; Zendulka, Jaroslav (referee) ; Šebek, Michal (advisor)
Data collecting and analysis are commonly used techniques in many sectors of today's business and science. Process called Knowledge Discovery in Databases presents itself as a great tool to find new and interesting information that can be used in a future developement. This thesis deals with basic principles of data mining and temporal data mining as well as with specifics of concrete implementation of chosen algorithms for mining periodic patterns in time series. These algorithms have been developed in a form of managed plug-ins for Microsoft Analysis Services -- service that provides data mining features for Microsoft SQL Server. Finally, we discuss obtained results of performed experiments focused on time complexity of implemented algorithms.
|
|
|
Implementation of Mining Modules of Data Mining System on NetBeans Platform
Stríž, Rostislav ; Bartík, Vladimír (referee) ; Šebek, Michal (advisor)
Data collecting plays an important role in many aspects of today's businesses and quality information is the key to success. Process called Knowledge Discovery in Databases makes possible to extract hidden information that can be used further in our efforts. Main goal of this thesis is to describe an addition to such Data Mining System. Main objective is to create data mining module for NetBeans application, developed for demonstrational purposes by Faculty of Information Technology. New module is going to be able to mine information from Oracle database server via unusual use of Genetic Algorithm. This thesis describes the whole process of module implementation, begining with theoretical basics through coding details to final testing and summary.
|
|
|
Predicting Future Location of a Moving Object
Kebísek, Ján ; Stríž, Rostislav (referee) ; Pešek, Martin (advisor)
This thesis deals with the design and the implementation of the application for predicting future location of a moving object. It describes a method for prediction based on the algorithm WhereNext. This algorithm obtains T-Patterns from a database of trajectories of objects, which represent frequent patterns of movement of objects, and those subsequently uses for prediction. The algorithm was implemented in programming language Java and its functionality was tested on a generated dataset of movement of cars.
|
|
|
Implementation of Algorithms Based on Decision Trees in C#
Grolig, Lukáš ; Pešek, Martin (referee) ; Stríž, Rostislav (advisor)
This bachelor thesis is focused on selection of data mining algorithms based on decision trees for an analytical system developed under the project System for the Internet security increase based on malware spreading analysis. Selected algorithms are described in greater detais, as well as their implementation in the C# language. These algorithms are then tested with regards to their training speed and classification accuracy. Finally, this thesis presents further conclusions and recommendations based on performed experiments.
|
|
|
Periodic Patterns Mining
Stríž, Rostislav ; Zendulka, Jaroslav (referee) ; Šebek, Michal (advisor)
Data collecting and analysis are commonly used techniques in many sectors of today's business and science. Process called Knowledge Discovery in Databases presents itself as a great tool to find new and interesting information that can be used in a future developement. This thesis deals with basic principles of data mining and temporal data mining as well as with specifics of concrete implementation of chosen algorithms for mining periodic patterns in time series. These algorithms have been developed in a form of managed plug-ins for Microsoft Analysis Services -- service that provides data mining features for Microsoft SQL Server. Finally, we discuss obtained results of performed experiments focused on time complexity of implemented algorithms.
|
guest ::
RSS feed.