|
|
Neural Networks for Video Quality Enhancement
Sirovatka, Matej ; Juránek, Roman (oponent) ; Hradiš, Michal (vedoucí práce)
In this thesis, a new method for video super-resolution is proposed. The method is based on the idea of using deformable convolutional layers together with optical flow to align features from multiple sequential video frames. This novel module is then used in a U-Net-like deep neural network to predict high-resolution frames. The proposed method is evaluated on a dataset containing real-life scenes and compared to other methods. Multiple different configurations of the proposed method are tested and the results are analyzed. The results of the experiments show promising results, with the model outperforming bilinear interpolation, and single-frame methods. Multiple different architectures of the feature alignment module together with the rest of the U-Net architecture are tested, showing that using Vgg19 as the encoder of the U-Net gives the best results.
|
|
|
Intelligent Manager of Fantasy Premier League Game
Vasilišin, Maroš ; Burgetová, Ivana (oponent) ; Hynek, Jiří (vedoucí práce)
Fantasy Premier League online game gives millions of players around the world the chance to become a manager of their club for a while. The results and scores in the game depend on correctly predicting how players will behave in real football matches. If the user had software for predicting and analyzing players' future performance, it would help with making decisions and the outcome of the game could significantly improve. This master's thesis deals with the design and implementation of a prediction model that uses neural networks for time series prediction throughout the game season. Various methods were used to process player and club data for the last 4 seasons. The results are presented in the form of a web application where users can use the created model on their teams. Performance and accuracy of prediction methods were tested on the data from the last season of the Premier League and algorithm predictions were in most of the cases close to reality. If the user used the prediction model's advice 100% in the game, he would score more points than a regular player who does not use any prediction model.
|
|
|
Identification and characterization of malicious behavior in behavioral graphs
Varga, Adam ; Burget, Radim (oponent) ; Hajný, Jan (vedoucí práce)
In recent years, there has been an increase in work involving comprehensive malware detection. It is often useful to use a graph format to capture behavior. This is the case with the Avast antivirus program, whose behavioral shield detects malicious behavior and stores it in the form of graphs. Since this is a proprietary solution and Avast antivirus works with its own set of characterized behavior, it was necessary to design our own detection method that will be built on top of these behavioral graphs. This work analyzes graphs of malware behavior captured by the behavioral shield of the Avast antivirus program for the process of deeper detection of malware. Detection of malicious behavior begins with the analysis and abstraction of patterns from the behavioral graph. Isolated patterns can more effectively identify dynamically changing malware. Behavior graphs are stored in the Neo4j graph database and thousands of them are captured every day. The aim of this work was to design an algorithm to identify the behavior of malicious software with emphasis on tagging speed and uniqueness of identified patterns of behavior. Identification of malicious behavior consists in finding the most important properties of trained classifiers and subsequent extraction of a subgraph consisting only of these important properties of nodes and the relationships between them. Subsequently, a rule for the evaluation of the extracted subgraph is proposed. The diploma thesis took place in cooperation with Avast Software s.r.o.
|
|
|
Identification and characterization of malicious behavior in behavioral graphs
Varga, Adam ; Burget, Radim (oponent) ; Hajný, Jan (vedoucí práce)
In recent years, there has been an increase in work involving comprehensive malware detection. It is often useful to use a graph format to capture behavior. This is the case with the Avast antivirus program, whose behavioral shield detects malicious behavior and stores it in the form of graphs. Since this is a proprietary solution and Avast antivirus works with its own set of characterized behavior, it was necessary to design our own detection method that will be built on top of these behavioral graphs. This work analyzes graphs of malware behavior captured by the behavioral shield of the Avast antivirus program for the process of deeper detection of malware. Detection of malicious behavior begins with the analysis and abstraction of patterns from the behavioral graph. Isolated patterns can more effectively identify dynamically changing malware. Behavior graphs are stored in the Neo4j graph database and thousands of them are captured every day. The aim of this work was to design an algorithm to identify the behavior of malicious software with emphasis on tagging speed and uniqueness of identified patterns of behavior. Identification of malicious behavior consists in finding the most important properties of trained classifiers and subsequent extraction of a subgraph consisting only of these important properties of nodes and the relationships between them. Subsequently, a rule for the evaluation of the extracted subgraph is proposed. The diploma thesis took place in cooperation with Avast Software s.r.o.
|
|
|
Intelligent Manager of Fantasy Premier League Game
Vasilišin, Maroš ; Burgetová, Ivana (oponent) ; Hynek, Jiří (vedoucí práce)
Fantasy Premier League online game gives millions of players around the world the chance to become a manager of their club for a while. The results and scores in the game depend on correctly predicting how players will behave in real football matches. If the user had software for predicting and analyzing players' future performance, it would help with making decisions and the outcome of the game could significantly improve. This master's thesis deals with the design and implementation of a prediction model that uses neural networks for time series prediction throughout the game season. Various methods were used to process player and club data for the last 4 seasons. The results are presented in the form of a web application where users can use the created model on their teams. Performance and accuracy of prediction methods were tested on the data from the last season of the Premier League and algorithm predictions were in most of the cases close to reality. If the user used the prediction model's advice 100% in the game, he would score more points than a regular player who does not use any prediction model.
|
host ::
RSS.