|
|
Big Data Processing in Industry 4.0
Stredánsky, Dávid ; Fajčík, Martin (referee) ; Smrž, Pavel (advisor)
Main goal of this thesis is to create application for industrial big data processing. Final application uses bearing vibration data. The application's design is inspired by Lambda architecture for big data processing. The application monitors data recieved from sensors in real time and enables periodic batch processing. Known methods from bearing condition monitoring, such as root mean square, deviation or skewness extraction are used in batch processing. Data prediction method Prophet is tested out in this thesis. Final web appli- cation is written in the Python language with the use of Dash framework and results are stored in MySQL database.
|
|
|
Use of Knowledge Discovery for Data from PDF Files
Dvořáček, Libor ; Burgetová, Ivana (referee) ; Bartík, Vladimír (advisor)
This bachelor thesis deals with the extraction of tables from digitally created pdfs and the subsequent use of the obtained data for data analysis. Methods of dimension reduction and cluster analysis are used. The main content is an analysis of available tools for data extraction in the python language, a description and comparison of the used machine learning methods and implementation of an application that combines all these topics into one functional unit at: http://extraktor.herokuapp.com
|
|
|
Evaluating the performance of mobile networks based on long-term measurements
Rehák, Ondrej ; Miloš, Jiří (referee) ; Slanina, Martin (advisor)
The aim of this thesis is to choose the proper measurement system for evaluating the performance of the LTE mobile networks based on long-term measurements. The thesis describes mobile network LTE, its architecture and introducts the Quality of Service in the LTE. In the next part are studied the known measurement methods and furthermore, there is proposed a solution in the form of long-term measurement. This measurement uses the mobile phone application Open-RMBT, which stores the measurement results into the database on the chosen server. The following part focuses on the issue of choosing a suitable mobile device for the measurement, then it describes a pilot testing and the followed run of the long-term measurements. In the last part is introduced the interractive application to plot graphs. Measurement results are discussed in the conclusion.
|
|
|
Identification of Cryptocurrency Users
Zrnčík, Henrich ; Matoušek, Petr (referee) ; Veselý, Vladimír (advisor)
abstract.en={The 3rd January 2009 is considered to be the beginning of the cryptocurrency era. This work will deal with one of the ways of obtaining information about cryptocurrency users. It will be done by retrieving it from public websites where users often knowingly or unknowingly publish their cryptocurrency's address for different purposes (donation accounts or online payments which include personal data) as a result of which it is possible to link their crypto account with their real identity. The information is obtained through web scrappings. The result is an implemented application capable of automated collecting of data about the identity of cryptocurrency users and its subsequent storage in a structured database.
|
|
|
Activity Alarm for Cryptocurrency Blockchains
Vokráčko, Lukáš ; Grégr, Matěj (referee) ; Veselý, Vladimír (advisor)
Cryptocurrencies are becoming popular and the demand for monitoring transactions inside them increases alongside with it. In this thesis, I describe few of the most widespread cryptocurrencies built on top of a blockchain and how to obtain information of their transactions in order to raise alarms. I discuss existing solutions and describe application Cryptoalarm designed for monitoring transactions involving specific addresses in order to raise alarms. Cryptoalarm scans blockchains of cryptocurrencies such as Bitcoin, Bitcoin Cash, Litecoin, Zcash, Dash, Ethereum and raises alarms about address activities in real-time.
|
|
|
New video coding algorithms
Zach, Ondřej ; Počta,, Peter (referee) ; Fliegel, Karel (referee) ; Slanina, Martin (advisor)
Předložená dizertační práce se zabývá moderními algoritmy pro kódovaní videosekvencí, zejména algoritmem High Efficiency Video Coding, a jeho použítím v prostředí online streamování. Vzhledem k tomu, že chování koncových diváků směřuje ke sledování video obsahu kdykoli a kdekoli, způsob, jakým je obsah doručen k divákovi, se stává stejně důležitým, jakým je samotné kódování. V této práci se zaměřujeme na užití HEVC ve službách založených na HTTP adaptivním streamování, zejména ve službách využívajích DASH. Dále se zabýváme dalšími aspekty, které mají vliv na kvalitu zážitku (Quality of Experience) tak, jak jej vnímá koncový uživatel. Takovými jsou na příklad přítomnost reklamy či další systémové parametry. Abychom mohli sbírat názory uživatelů, pro naše experimenty často používáme crowdsourcing. Z tohoto důvodu je část této práce věnována samotnému crowdsourcingu a tomu, jak jej lze využít pro hodnocení kvality videa.
|
|
|
Use of Knowledge Discovery for Data from PDF Files
Dvořáček, Libor ; Burgetová, Ivana (referee) ; Bartík, Vladimír (advisor)
This bachelor thesis deals with the extraction of tables from digitally created pdfs and the subsequent use of the obtained data for data analysis. Methods of dimension reduction and cluster analysis are used. The main content is an analysis of available tools for data extraction in the python language, a description and comparison of the used machine learning methods and implementation of an application that combines all these topics into one functional unit at: http://extraktor.herokuapp.com
|
|
|
Evaluating the performance of mobile networks based on long-term measurements
Rehák, Ondrej ; Miloš, Jiří (referee) ; Slanina, Martin (advisor)
The aim of this thesis is to choose the proper measurement system for evaluating the performance of the LTE mobile networks based on long-term measurements. The thesis describes mobile network LTE, its architecture and introducts the Quality of Service in the LTE. In the next part are studied the known measurement methods and furthermore, there is proposed a solution in the form of long-term measurement. This measurement uses the mobile phone application Open-RMBT, which stores the measurement results into the database on the chosen server. The following part focuses on the issue of choosing a suitable mobile device for the measurement, then it describes a pilot testing and the followed run of the long-term measurements. In the last part is introduced the interractive application to plot graphs. Measurement results are discussed in the conclusion.
|
|
|
New video coding algorithms
Zach, Ondřej ; Počta,, Peter (referee) ; Fliegel, Karel (referee) ; Slanina, Martin (advisor)
Předložená dizertační práce se zabývá moderními algoritmy pro kódovaní videosekvencí, zejména algoritmem High Efficiency Video Coding, a jeho použítím v prostředí online streamování. Vzhledem k tomu, že chování koncových diváků směřuje ke sledování video obsahu kdykoli a kdekoli, způsob, jakým je obsah doručen k divákovi, se stává stejně důležitým, jakým je samotné kódování. V této práci se zaměřujeme na užití HEVC ve službách založených na HTTP adaptivním streamování, zejména ve službách využívajích DASH. Dále se zabýváme dalšími aspekty, které mají vliv na kvalitu zážitku (Quality of Experience) tak, jak jej vnímá koncový uživatel. Takovými jsou na příklad přítomnost reklamy či další systémové parametry. Abychom mohli sbírat názory uživatelů, pro naše experimenty často používáme crowdsourcing. Z tohoto důvodu je část této práce věnována samotnému crowdsourcingu a tomu, jak jej lze využít pro hodnocení kvality videa.
|
|
|
Identification of Cryptocurrency Users
Zrnčík, Henrich ; Matoušek, Petr (referee) ; Veselý, Vladimír (advisor)
abstract.en={The 3rd January 2009 is considered to be the beginning of the cryptocurrency era. This work will deal with one of the ways of obtaining information about cryptocurrency users. It will be done by retrieving it from public websites where users often knowingly or unknowingly publish their cryptocurrency's address for different purposes (donation accounts or online payments which include personal data) as a result of which it is possible to link their crypto account with their real identity. The information is obtained through web scrappings. The result is an implemented application capable of automated collecting of data about the identity of cryptocurrency users and its subsequent storage in a structured database.
|
guest ::
