|
|
Neural network utilization for etwork traffic predictions
Pavela, Radek ; Mačák, Jaromír (referee) ; Kacálek, Jan (advisor)
In this master’s thesis are discussed static properties of network traffic trace. There are also addressed the possibility of a predication with a focus on neural networks. Specifically, therefore recurrent neural networks. Training data were downloaded from freely accessible on the internet link. This is the captured packej of traffic of LAN network in 2001. They are not the most actual, but it is possible to use them to achieve the objective results of the work. Input data needed to be processed into acceptable form. In the Visual Studio 2005 was created program to aggregate the intensities of these data. The best combining appeared after 100 ms. This was achieved by the input vector, which was divided according to the needs of network training and testing part. The various types of networks operate with the same input data, thereby to make more objective results. In practical terms, it was necessary to verify the two principles. Principle of training and the principle of generalization. The first of the nominated designs require stoking training and verification training by using gradient and mean square error. The second one represents unknown designs application on neural network. It was monitored the response of network to these input data. It can be said that the best model seemed the Layer recurrent neural network (LRN). So, it was a solution developed in this direction, followed by searching the appropriate option of recurrent network and optimal configuration. Found a variant of topology is 10-10-1. It was used the Matlab 7.6, with an extension of Neural Network toolbox 6. The results are processed in the form of graphs and the final appreciation. All successful models and network topologies are on the enclosed CD. However, Neural Network toolbox reported some problems when importing networks. In creating this work wasn’t import of network functions practically used. The network can be imported, but the majority appear to be non-trannin. Unsuccessful models of networks are not presented in this master’s thesis, because it would be make a deterioration of clarity and orientation.
|
|
|
Audio noise reduction using deep neural networks
Talár, Ondřej ; Galáž, Zoltán (referee) ; Harár, Pavol (advisor)
The thesis focuses on the use of deep recurrent neural network, architecture Long Short-Term Memory for robust denoising of audio signal. LSTM is currently very attractive due to its characteristics to remember previous weights, or edit them not only according to the used algorithms, but also by examining changes in neighboring cells. The work describes the selection of the initial dataset and used noise along with the creation of optimal test data. For network training, the KERAS framework for Python is selected. Candidate networks for possible solutions are explored and described, followed by several experiments to determine the true behavior of the neural network.
|
|
|
Machine Learning Strategies in Electronic Trading
Huf, Petr ; Kolář, Martin (referee) ; Černocký, Jan (advisor)
Úspěšné obchodování na trzích je snem mnoha lidí. Zajímavým odvětvím tohoto byznysu je elektronické obchodování, kde obchodní strategie běží na počítači bez jakéhokoliv zásahu člověka. Tento způsob obchodování poskytuje spoustu volného času a vysoké příjmy. Tato práce je zaměřena na využití neuronových sítí při stavbě takovéto obchodní strategie. Jako základ byla použita již existující rekurentní neuronová síť, která byla postupně modifikována podle potřeb pro obchodování. Výsledkem je neuronová síť předpovídající budoucí pohyby trhu. Obchodní strategie používající tuto neuronovou síť dokáže na burze úspěšně obchodovat.
|
|
|
Usage of Public Business Information for Automatic Trading
Gráca, Martin ; Plchot, Oldřich (referee) ; Černocký, Jan (advisor)
In the era of modern technology and high performance computers, the classical trades model getting insufficient. For successful trading, generating stable profit, it is good to use modern technologies and opportunities. The main goal of this work is to develop a trading system based on modern technologies. This work uses public business data from Edgar database managed by U.S. Securities and Exchange Commission (SEC), historical share´s prices and recurrent neural network to create such model. The final system is able to trade successfully and generate profit.
|
|
|
Prediction of data flow in computer networks
Zvěřina, Lukáš ; Sobek, Jiří (referee) ; Vychodil, Petr (advisor)
The aim of this thesis was to study problems of prediction of data in computer networks. Furthermore, this work deals with network traffic and analyzing its properties. In this study were analyzed the possibilities of network traffic prediction using Farima model, the theory of chaos with Lyapunov exponents and neural networks. Possibilities of prediction with the focus on neural network were discussed in detail here, mainly on recurrent neural networks. Prediction was performed in Matlab development environment in Neural Network Toolbox, where they were created, trained and evaluated neural network to predict specific types of network traffic. For testing were selected Elman network NARX network and general LRN recurrent network. The results were clearly organized into tables and plotted in graphical relationships before and after the use of predictive techniques designed to final evaluation.
|
|
|
Advanced classification of cardiac arrhythmias in ECG
Sláma, Štěpán ; Hejč, Jakub (referee) ; Ronzhina, Marina (advisor)
This work focuses on a theoretical explanation of heart rhythm disorders and the possibility of their automatic detection using deep learning networks. For the purposes of this work, a total of 6884 10-second ECG recordings with measured eight leads were used. Those recordings were divided into 5 groups according to heart rhythm into a group of records with atrial fibrillation, sinus rhythms, supraventricular rhythms, ventricular rhythms, and the last group consisted of the others records. Individual groups were unbalanced represented and more than 85 % of the total number of data are sinus rhythm group records. The used classification methods served effectively as a record detector of the largest group and the most effective of all was a procedure consisting of a 2D convolutional neural network into which data entered in the form of scalalograms (classification procedure number 3). It achieved results of precision of 91%, recall of 96% and F1-score values of 0.93. On the contrary, when classifying all groups at the same time, there were no such quality results for all groups. The most efficient procedure seems to be a variant composed of PCA on eight input signals with the gain of one output signal, which becomes the input of a 1D convolutional neural network (classification procedure number 5). This procedure achieved the following F1-score values: 1) group of records with atrial fibrillation 0.54, 2) group of sinus rhythms 0.91, 3) group of supraventricular rhythms 0.65, 4) group of ventricular rhythms 0.68, 5) others records 0.65.
|
|
|
Nonlinear analysis and prediction of network traffic
Člupek, Vlastimil ; Burget, Radim (referee) ; Vychodil, Petr (advisor)
This thesis deal with an analysis of network traffic and its properties. In this thesis are discussed possibilities of prediction network traffic by FARIMA model, theory of chaos with Lyapunov exponent and by neural networks. The biggest attention was dedicated to prediction network traffic by neural networks. In Matlab with using Neural Network Toolbox were created, trained and tested recurrent networks for prediction specific types of network traffics, which was captured on local network. There were choosed Elman network, LRN and NARX network to test the prediction of network traffic, results were discussed. Thesis also introduce area of application ability prediction of network traffic, there is introduce design of system for dynamic allocation bandwidth with particular description of its prediction part. Thesis also states possible use designed system for dynamic allocation of bandwidth.
|
|
|
Audio noise reduction using deep neural networks
Talár, Ondřej ; Galáž, Zoltán (referee) ; Harár, Pavol (advisor)
The thesis focuses on the use of deep recurrent neural network, architecture Long Short-Term Memory for robust denoising of audio signal. LSTM is currently very attractive due to its characteristics to remember previous weights, or edit them not only according to the used algorithms, but also by examining changes in neighboring cells. The work describes the selection of the initial dataset and used noise along with the creation of optimal test data. For creation of the training network is selected KERAS framework for Python and are explored and discussed possible candidates for viable solutions.
|
|
|
Automatic tagging of musical compositions using machine learning methods
Semela, René ; Galáž, Zoltán (referee) ; Kiska, Tomáš (advisor)
One of the many challenges of machine learning are systems for automatic tagging of music, the complexity of this issue in particular. These systems can be practically used in the content analysis of music or the sorting of music libraries. This thesis deals with the design, training, testing, and evaluation of artificial neural network architectures for automatic tagging of music. In the beginning, attention is paid to the setting of the theoretical foundation of this field. In the practical part of this thesis, 8 architectures of neural networks are designed (4 fully convolutional and 4 convolutional recurrent). These architectures are then trained using the MagnaTagATune Dataset and mel spectrogram. After training, these architectures are tested and evaluated. The best results are achieved by the four-layer convolutional recurrent neural network (CRNN4) with the ROC-AUC = 0.9046 ± 0.0016. As the next step of the practical part of this thesis, a completely new Last.fm Dataset 2020 is created. This dataset uses Last.fm and Spotify API for data acquisition and contains 100 tags and 122877 tracks. The most successful architectures are then trained, tested, and evaluated on this new dataset. The best results on this dataset are achieved by the six-layer fully convolutional neural network (FCNN6) with the ROC-AUC = 0.8590 ± 0.0011. Finally, a simple application is introduced as a concluding point of this thesis. This application is designed for testing individual neural network architectures on a user-inserted audio file. Overall results of this thesis are similar to other papers on the same topic, but this thesis brings several new findings and innovations. In terms of innovations, a significant reduction in the complexity of individual neural network architectures is achieved while maintaining similar results.
|
|
|
Vehicle Classification Using Radar
Gottwald, Vilém ; Zemčík, Pavel (referee) ; Maršík, Lukáš (advisor)
Cílem této práce je rozpoznávání vozidel z radarových mračen bodů. Radar poskytuje informace o vzdálenosti a úhlu každého detekovaného cíle. Tyto informace lze převést do kartézského souřadnicového systému a získat tak 3D reprezentaci scény ve formě mračna bodů. V této práci jsou představeny stávající přístupy k rozpoznávání objektů v mračnech bodů. Metoda zvolená pro tuto práci spočívá v detekci objektů pomocí shlukování bodů a následné klasifikaci pomocí rekurentní neuronové sítě. Shluky bodů reprezentující objekty jsou vytvářeny z mračen bodů pomocí modifikovaného algoritmu DBSCAN. Z jednotlivých objektů jsou extrahovány příznaky, které jsou využity pro klasifikaci na různé typy vozidel pomocí neuronové sítě s dlouhodobou krátkodobou pamětí (LSTM). Pro trénování a vyhodnocení modelu byla vytvořena datová sada obsahující 57 345 anotovaných objektů. Vyvinutý model dosáhl na těchto datech 83% přesnosti metriky F1-skóre.
|
guest ::
