|
|
Analysis of Parameters of Packet Classification Rule Sets
Sabo, Jozef ; Orsák, Michal (referee) ; Matoušek, Jiří (advisor)
A theme of bachelor's thesis is an analysis of rules used for packet classification in computer networks. A theoretical part of the thesis introduces packet classification and describes the role of classification rules. This part also presents the format of classification rules utilized in real tools. Based on these information, a tool able to analyze IP 5-tuple classification rules in any format was designed and implemented. Output of the implemented tool is a parameter file containing different statistics and probability distributions of examined rule sets. This parameter file can be used for generating synthetic rule sets using ClassBench and ClassBench-ng tools. The final part of the thesis examines parameter files created by the implemented tool from available real rule sets.
|
|
|
Application of Unsupervised Learning Methods in Graph Similarity Search
Sabo, Jozef ; Burgetová, Ivana (referee) ; Křivka, Zbyněk (advisor)
Goal of this master's thesis was in cooperation with the company Avast to design a system, which can extract knowledge from a database of graphs. Graphs, used for data mining, describe behaviour of computer systems and they are anonymously inserted into the company's database from systems of the company's products users. Each graph in the database can be assigned with one of two labels: clean or malware (malicious) graph. The task of the proposed self-learning system is to find clusters of graphs in the graph database, in which the classes of graphs do not mix. Graph clusters with only one class of graphs can be interpreted as different types of clean or malware graphs and they are a useful source of further analysis on the graphs. To evaluate the quality of the clusters, a custom metric, named as monochromaticity, was designed. The metric evaluates the quality of the clusters based on how much clean and malware graphs are mixed in the clusters. The best results of the metric were obtained when vector representations of graphs were created by a deep learning model (variational graph autoencoder with two relation graph convolution operators) and the parameterless method MeanShift was used for clustering over vectors.
|
|
|
Porovnání bílkovinné stability u bílých vín
Sabo, Jozef
Thesis deals with comparing the protein stability of white wines. The aim of this thesis is to compare the stability of the proteins for seven particular varieties of the white wines using sodium-calcium bentonite Puranit. Size of the batch 150 g / l of the bentonite was used in the research. Theoretical part are briefly described the nitrogen substances, individual factors effect in the condensation of the proteins, the impact of aging of the wine on the soft feces on its protein stability, opportunities of the using the fining enological agent - bentonite, silicic acid salts, gelatin, tannin, isinglass. The thesis are characterized individual in the research applied the varieties of the white wines. In the practical part is detailed described the procedure of the carried out the experiment, the individual results are reported in the table and graphs. Research showed that after application of the bentonite is significantly changed the protein stability of individualt types of the wine.
|
|
|
Odstranění rozmazání pomocí dvou snímků s různou délkou expozice
Sabo, Jozef ; Šroubek, Filip (advisor) ; Horáček, Jan (referee)
In the presented work we study methods of image deblurring using two images of the same scene with different exposure times, focusing on two main approach categories, the so called deconvolution and non-deconvolution methods. We present theoretical backgrounds on both categories and evaluate their limitations and advantages. We dedicate one section to a comparison of both method categories on test data (images) for which we use a MATLAB implementation of the methods. We also compare the effectiveness of said methods against the results of a selected single- image de-noising algorithm. We do not focus at computational efficiency of algorithms and work with grayscale images only.
|
|
|
Odstranění rozmazání pomocí dvou snímků s různou délkou expozice
Sabo, Jozef ; Šroubek, Filip (advisor) ; Horáček, Jan (referee)
In the presented work we study the methods of image deblurring using two images of the same scene with different exposure times, focusing on two main approach categories, so called deconvolution and non-deconvolution methods. We present theoretical backgrounds on both categories and evaluate their limitations and advantages. We dedicate one section to compare both method categories on test data (images) for which we our MATLAB implementation of the methods. We also compare the effectiveness of said methods against the results of a selected single-image de-noising algorithm. We do not focus at computational efficiency of algorithms and work with single-channel images only.
|
|
|
Application of Unsupervised Learning Methods in Graph Similarity Search
Sabo, Jozef ; Burgetová, Ivana (referee) ; Křivka, Zbyněk (advisor)
Goal of this master's thesis was in cooperation with the company Avast to design a system, which can extract knowledge from a database of graphs. Graphs, used for data mining, describe behaviour of computer systems and they are anonymously inserted into the company's database from systems of the company's products users. Each graph in the database can be assigned with one of two labels: clean or malware (malicious) graph. The task of the proposed self-learning system is to find clusters of graphs in the graph database, in which the classes of graphs do not mix. Graph clusters with only one class of graphs can be interpreted as different types of clean or malware graphs and they are a useful source of further analysis on the graphs. To evaluate the quality of the clusters, a custom metric, named as monochromaticity, was designed. The metric evaluates the quality of the clusters based on how much clean and malware graphs are mixed in the clusters. The best results of the metric were obtained when vector representations of graphs were created by a deep learning model (variational graph autoencoder with two relation graph convolution operators) and the parameterless method MeanShift was used for clustering over vectors.
|
|
|
Analysis of Parameters of Packet Classification Rule Sets
Sabo, Jozef ; Orsák, Michal (referee) ; Matoušek, Jiří (advisor)
A theme of bachelor's thesis is an analysis of rules used for packet classification in computer networks. A theoretical part of the thesis introduces packet classification and describes the role of classification rules. This part also presents the format of classification rules utilized in real tools. Based on these information, a tool able to analyze IP 5-tuple classification rules in any format was designed and implemented. Output of the implemented tool is a parameter file containing different statistics and probability distributions of examined rule sets. This parameter file can be used for generating synthetic rule sets using ClassBench and ClassBench-ng tools. The final part of the thesis examines parameter files created by the implemented tool from available real rule sets.
|
|
|
Porovnání bílkovinné stability u bílých vín
Sabo, Jozef
Thesis deals with comparing the protein stability of white wines. The aim of this thesis is to compare the stability of the proteins for seven particular varieties of the white wines using sodium-calcium bentonite Puranit. Size of the batch 150 g / l of the bentonite was used in the research. Theoretical part are briefly described the nitrogen substances, individual factors effect in the condensation of the proteins, the impact of aging of the wine on the soft feces on its protein stability, opportunities of the using the fining enological agent - bentonite, silicic acid salts, gelatin, tannin, isinglass. The thesis are characterized individual in the research applied the varieties of the white wines. In the practical part is detailed described the procedure of the carried out the experiment, the individual results are reported in the table and graphs. Research showed that after application of the bentonite is significantly changed the protein stability of individualt types of the wine.
|
|
|
Odstranění rozmazání pomocí dvou snímků s různou délkou expozice
Sabo, Jozef ; Šroubek, Filip (advisor) ; Horáček, Jan (referee)
In the presented work we study methods of image deblurring using two images of the same scene with different exposure times, focusing on two main approach categories, the so called deconvolution and non-deconvolution methods. We present theoretical backgrounds on both categories and evaluate their limitations and advantages. We dedicate one section to a comparison of both method categories on test data (images) for which we use a MATLAB implementation of the methods. We also compare the effectiveness of said methods against the results of a selected single- image de-noising algorithm. We do not focus at computational efficiency of algorithms and work with grayscale images only.
|
|
|
Odstranění rozmazání pomocí dvou snímků s různou délkou expozice
Sabo, Jozef ; Šroubek, Filip (advisor) ; Horáček, Jan (referee)
In the presented work we study the methods of image deblurring using two images of the same scene with different exposure times, focusing on two main approach categories, so called deconvolution and non-deconvolution methods. We present theoretical backgrounds on both categories and evaluate their limitations and advantages. We dedicate one section to compare both method categories on test data (images) for which we our MATLAB implementation of the methods. We also compare the effectiveness of said methods against the results of a selected single-image de-noising algorithm. We do not focus at computational efficiency of algorithms and work with single-channel images only.
|
guest ::
RSS feed.