|
|
Financial market analysis using deep learning algorithm
Nimrichter, Adam ; Burget, Radim (referee) ; Mašek, Jan (advisor)
The thesis deals with methods for analysis of financial markets, focused on cryptocurrencies. The theoretical part, in a context of virtual currencies, describes block-chain technology, financial indicators and neural networks with recurrent architectures. Main goal is to create a system for giving a recommendation either for buy, or sell the currency. The system consists of designed financial strategy and predicted value of the currency, for which is used financial indicators and LSTM neural network. Tests were performed on Bitcoin, Litecoin and Ethereum historical data from year 2017.
|
|
|
Design of the application for the camera control and machine learning
Lukaszczyk, Jakub ; Richter, Miloslav (referee) ; Bilík, Šimon (advisor)
This bachelor thesis deals with the design of a program for controlling industrial cameras. The first part deals with current applications, their design and shortcomings. In the practical part, a similar application is then developed using Python. Compared to currently available applications, the developed application provides a modular and open design and can therefore be further extended and modified. The application is further complemented with a link to the Tensorflow library to enable image classification and training of artificial neural network models. The application has been tested and appears to be functional. The thesis concludes by evaluating the results and outlining possibilities for further development.
|
|
|
Machine learning applied to simulations of material mechanical behavior
Raisinger, Jan ; Novák, Lukáš (referee) ; Eliáš, Jan (advisor)
The thesis explores the possibility of using machine learning models to predict effective macroscopic material parameters of multiphase materials. The asymptotic expansion homogenization method is used together with the finite element method to create software in Python, which is used to calculate effective macroscale mechanical parameters of sets of heterogeneous arrangements. These sets are generated using several methods, e.g. as a realization of a discretized random field. The sets are used to train neural networks built using the Keras library. The accuracy of the networks and the quality of training data are assessed. The advantages and disadvantages of the networks compared to the FEM solver are demonstrated on their application in an optimization problem.
|
|
|
Detection of printing defects
Boček, Václav ; Boštík, Ondřej (referee) ; Honec, Peter (advisor)
This thesis deals with the design and subsequent implementation of a unit inspecting a printed logos on the pen surface. A line-scan camera is used to capture the object. Whole the unit including acquited data processing is controlled by Raspberry Pi 4 platform extended by perifery board. The control of the hardware parts is implemented in C++, the detection algorithms in Python using OpenCV and TensorFlow libraries. The unit has a graphical user interface for control of the inspection process. In the end of the thesis test of the unit reliability is shown.
|
|
|
Deep Learning for Text Classification
Kolařík, Martin ; Harár, Pavol (referee) ; Povoda, Lukáš (advisor)
Thesis focuses on analysis of contemporary machine learning methods used for text classification based on emotion and testing several deep neural nework architectures. Outcome of this thesis is a neural network architecture, which is tuned for using with text data and which had the best result of 79,94 percent. Proposed method is language independent and it doesn’t require as precisely classified training datasets as current methods. Training and testing datasets were consisted of short amateur movie reviews in Czech and in English. Thesis contains also overview of theoretical basics for convolutional neural networks and history of neural networks and language processing Scripts were written in Python, neural networks were simulated using Keras library and Theano framework. We used CUDA for better performance.
|
|
|
Classification of arteries and veins in retinal image data
Černohorská, Lucie ; Jakubíček, Roman (referee) ; Kolář, Radim (advisor)
This master's thesis deals with the classification of the retinal blood vessels in retinal image data. The thesis contains a description of anatomy of the human eye with focus on the blood circulation, and imaging and diagnostic methods of the retina are briefly mentioned further. The thesis also summarizes methods of the blood circulation classification with emphasis on the deep learning. The practical section was implemented in Python programming language and describes the pre-processing of the data with determination of AV ratio. Based on a literature search, the U-net architecture was chosen for the classification of the retinal blood vessels. The architecture was modified using the open-source Keras library and tested on images from the experimental video-ophthalmoscope. The modified architecture was initially used for classification of vessels into the corresponding classes and because of unsatisfying results was modified another architecture segmenting retinal vessels, arteries or veins and a proposition of a method of the blood vessels classification.
|
|
|
Blood vessel segmentation in retinal images using deep learning approaches
Serečunová, Stanislava ; Vičar, Tomáš (referee) ; Kolář, Radim (advisor)
This diploma thesis deals with the application of deep neural networks with focus on image segmentation. The theoretical part contains a description of deep neural networks and a summary of widely used convolutional architectures for segmentation of objects from the image. Practical part of the work was devoted to testing of an existing network architectures. For this purpose, an open-source software library Tensorflow, implemented in Python programming language, was used. A frequent problem incorporating the use of convolutional neural networks is the requirement on large amount of input data. In order to overcome this obstacle a new data set, consisting of a combination of five freely available databases was created. The selected U-net network architecture was tested by first modification of the newly created data set. Based on the test results, the chosen network architecture has been modified. By these means a new network has been created achieving better performance in comparison to the original network. The modified architecture is then trained on a newly created data set, that contains images of different types taken with various fundus cameras. As a result, the trained network is more robust and allows segmentation of retina blood vessels from images with different parameters. The modified architecture was tested on the STARE, CHASE, and HRF databases. Results were compared with published segmentation methods from literature, which are based on convolutional neural networks, as well as classical segmentation methods. The created network shows a high success rate of retina blood vessels segmentation comparable to state-of-the-art methods.
|
|
|
Neural network for style transfer
Kadlec, Filip ; Matoušek, Radomil (referee) ; Hůlka, Tomáš (advisor)
In this bachelor’s thesis we describe machine learning, types of artificial neural networks and internal processes of neural networks, such as feedforward data processing and training neural networks. We are also pursuing comparison and description of libraries (such as TensorFlow and Keras), which are suitable for neural networks implementation. In the practical part of thesis, we are dealing with problem called artistic style transfer with convolutional neural network.
|
|
|
Detection of significant events in systems baased on phase OTDR
Makówka, David ; Petyovský, Petr (referee) ; Valach, Soběslav (advisor)
This diploma thesis concerns the design, implementation and testing of a system that classifies events captured using optic fiber along a perimeter of guarded objects. A theoretical part introduces physical principles, main structures of measuring systems, methods of measuring, data format, pre-processing options and classification using convolutional neural networks. A practical part describes implementation of a software for convolutional neural networks training and testing, process of samples extraction from measured data, its annotation and conversion to format required by neural networks. Results of measured data analysis and results of achieved classification accuracy using convolutional neural networks for both post processing of measured data and for deployment of neural network into real time processing system are presented.
|
|
|
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.
|
guest ::
