|
|
Predictive Modelling with Python
Duda, Jan ; Burgetová, Ivana (referee) ; Zendulka, Jaroslav (advisor)
The main goal of this bachelor thesis is get to know with the data mining and its domain, also with the Knowledge discovery in databases process. It shows the most importnant approaches, which are implemented in Python language afterwards. The case study contains the prediction of index S&P 500 describing stock market developments on the US stock exchange. Both classification and regression models are used for the forecasting. Model evaluation is reached by the Monte Carlo experimental method.
|
|
| |
|
|
Classification in Data Streams Using Ensemble Methods
Jarosch, Martin ; Zendulka, Jaroslav (referee) ; Hlosta, Martin (advisor)
This master's thesis deals with knowledge discovery and is focused on data stream classification. Three ensemble classification methods are described here. These methods are implemented in practical part of this thesis and are included in the classification system. Extensive measurements and experimentation were used for method analysis and comparison. Implemented methods were then integrated into Malware analysis system. At the conclusion are presented obtained results.
|
|
|
Information System of a Floorball Team
Zmek, Jakub ; Bartík, Vladimír (referee) ; Zendulka, Jaroslav (advisor)
This bachelor thesis is focused on study of web technologies and the subsequent creation of an information system for floorball team FbC Reative Aligators E for well-aranged statistics and event attendance management. The information systém is programmed as a web aplication with Nette framework support. The system allows logging to events (trainings, matches) and displaying off attendance. The systém automatically extracts data (matches, competition table, player statistics) from Czech floorbal websites and stores them in the database. The downloaded statistics are the publicly avaible in the informaction system.
|
|
|
Information System Supporting Feature-Driven Development
Tichá, Pavlína ; Zendulka, Jaroslav (referee) ; Rychlý, Marek (advisor)
This thesis deals with the Featured Driven Development (FDD) agile methodics. To support this methodics, an information system has been created, providing all team-members with instruments to follow the methodics. This multi-user system is implemented as a web-based application, enabling creation of a feature list, plan a project, support the cooperation among the feature team members and watch the project progress in an illustrative way. To improve the visualization possibilities, a wide range of reports aimed at the company management and the client is provided.
|
|
|
Support for Spatial Data in Oracle
Volf, Tomáš ; Chmelař, Petr (referee) ; Zendulka, Jaroslav (advisor)
This work acquaints with support for working with spatial data and mentions the possibility for spatio-temporal data in the Oracle database server 11g. On the basis of acquaintance with support for spatial data was designed sample application that uses this support. The sample application provides to display spatial data, which are stored in the database, graphically and also displays information about spatial objects. Finally, there are reviewed achievements and the possibilities how to continue in the project.
|
|
|
Migration Framework in SAP System
Hanák, Tomáš ; Bartík, Vladimír (referee) ; Zendulka, Jaroslav (advisor)
The goal of this diploma thesis is to analyze process of migration data within the scope of SAP systems. Based on this analysis suitably desing and implement migration framework that will be used for migration of data between SAP systems. Entire migration framework and migration proces is built on technological platform SAP NetWeaver and is implemented in programming language ABAP. Functionality of the framework is presented by the case study that is represented by proper data set.
|
|
|
Application Frameworks for Web Application Development
Tulka, Tomáš ; Křivka, Zbyněk (referee) ; Zendulka, Jaroslav (advisor)
Application frameworks are tools that enable easier development of web applications and enhance their quality. Because there are so may Java web application frameworks in existence it is difficult at times to choose the correct one to suit a particular application. This thesis examines frameworks from a general point of view. Descriptions of the characteristic functions of frameworks are also covered, along with functions, and the ways in which they differ from each other; and thus it enables the most appropriate framework to be chosen. The thesis also analyses typical representatives of frameworks for certain uses, it demonstrates their activity by means of standardized applications and compares them in terms of practical use.
|
|
|
Object Relational Databases
Franek, Zdenko ; Vrážel, Dušan (referee) ; Zendulka, Jaroslav (advisor)
This bachelor thesis focuses on object-relational database systems. It describes object relational model defined according to standards SQL and utilization of these standards in Oracle 10g product. It also contains information about database analysis, design and implementation of sample application, in which specific aspects of object-relational model of Oracle 10g server would be illustrated. Rational Rose was chosen for database design, because it involves support for object-relational design. This thesis also analyzes, which object-relational extensions are included in implementation tool Oracle Forms 10g and utilization of PL/SQL language for implementation of database application.
|
|
|
Classification of Potentially Malicious File Clusters via Machine Learning
Holop, Patrik ; Zendulka, Jaroslav (referee) ; Bartík, Vladimír (advisor)
Táto práca navrhuje alternatívu súčasných metód klasifikácie malvéru na úrovni súborov, ktoré sú často založené na detekcii špecifických postupností bytov v daných súboroch. Experimentáciou bolo potvrdené, že je možné klasifikovať potenciálnu hrozbu aj na úrovni zoskupení súborov založenej na spoločných vlastnostiach súborov v danom zoskupení. To bolo dosiahnuté dôkladným výberom vlastností troch typov súborov - PE, APK a .NET. Porovnaním niekoľkých metód strojového učenia boli vybraté klasifikátory s najvyššou presnosťou a implementovaná webová služba poskytujúca API pre klasifikáciu, ktoré bolo použité pre integráciu s interným systémom spoločnosti Avast zodpovedného za tvorbu súborových zoskupení. Táto práca taktiež diskutuje možné nedostatky a navrhuje kroky pre zlepšenie dosiahnutej presnosti klasifikácie.
|
guest ::
