|
|
Essays on Data-driven, Non-parametric Modelling of Time-series
Hanus, Luboš ; Vácha, Lukáš (advisor) ; Witzany, Jiří (referee) ; Ellington, Michael (referee) ; Trimborn, Simon (referee)
This thesis consists of four contributions to the literature on data-driven and non-parametric modelling of time series. In the first paper, we study the synchronisation of business cycles and propose a multivariate co-movement measure based on time-frequency cohesion. We suggest that economic inte- gration may lead to increased co-movement of business cycles, which may reflect the benefits of convergence and coordination of economic policies. The second paper presents a new methodology for identifying persistence in macroeconomic variables. Using time-varying frequency response func- tions, we identify heterogeneous persistence effects in US macroeconomic variables. The third and fourth papers propose data-driven techniques for probabilistic forecasting of time series using deep learning. We introduce a multi-output neural network that selects the most appropriate distribution for the data. The distributional neural network is valuable for modelling data with non-linear, non-Gaussian and asymmetric structures. The third paper demonstrates the usefulness of the method by estimating information-rich macroeconomic fan charts and distributional forecasts of asset returns. In the last paper, we present the distributional neural network to obtain the proba- bility distribution of electricity price...
|
|
|
Intracranial hemorrhage localization in axial slices of head CT images
Kopečný, Kryštof ; Chmelík, Jiří (referee) ; Nemček, Jakub (advisor)
This thesis is focused on detection of intracranial hemorrhage in CT images using both one-stage and two-stage object detectors based on convolutional neural networks. The fundamentals of intracranial hemorrhage pathology and CT imaging as well as essential insight into computer vision and object detection are listed in this work. The knowledge of these fields of studies is a starting point for the implemenation of hemorrhage detector. The use of open-source CT image datasets is also discussed. The final part of this thesis is a model evaluation on a test dataset and results examination.
|
|
|
Utilization of artificial intelligence in vibrodiagnostics
Dočekalová, Petra ; Huzlík, Rostislav (referee) ; Zuth, Daniel (advisor)
The diploma thesis deals with machine learning, expert systems, fuzzy logic, genetic algorithms, neural networks and chaos theory, which fall into the category of artificial intelligence. The aim of this work is to describe and implement three different classification methods, according to which the data set will be processed. The GNU Octave software environment was chosen for the data application for licensing reasons. Further evaluate the success of data classification, including visualization. Three different classification methods are used for comparison, so that we can compare the processed data with each other.
|
|
|
open source artificial intelligence options
Ostrý, Lubomír ; Kumpán, Pavel (referee) ; Appel, Martin (advisor)
This thesis focuses on open source tools and resources in the field of artificial intelligence, particularly in machine learning. The aim is to analyze current state, possibilities and limitations of work with a set of open source artificial intelligence programs. The first part describes and explains basic terms regarding machine learning, mainly neural networks, their training and use. Following section describes a set of machine learning tools, specifically their main characteristics, compatibility and use. Available sources of open source datasets for neural network training is a topic of another chapter. Lastly an application was created using a selection of described tools displaying their possibilities and use.
|
|
|
Playing Games Using Neural Networks
Buchal, Petr ; Kolář, Martin (referee) ; Hradiš, Michal (advisor)
The aim of this bachelor thesis is to teach a neural network solving classic control theory problems and playing the turn-based game 2048 and several Atari games. It is about the process of the reinforcement learning. I used the Deep Q-learning reinforcement learning algorithm which uses a neural networks. In order to improve a learning efficiency, I enriched the algorithm with several improvements. The enhancements include the addition of a target network, DDQN, dueling neural network architecture and priority experience replay memory. The experiments with classic control theory problems found out that the learning efficiency is most increased by adding a target network. In the game environments, the Deep Q-learning has achieved several times better results than a random player. The results and their analysis can be used for an insight to reinforcement learning algorithms using neural networks and to improve the used techniques.
|
|
|
Description of Relation between Flow and Suspended Sediment Load in a Hydromertic Profiles of a Selected Rivers
Bobková, Dominika ; Janál,, Petr (referee) ; Marton, Daniel (advisor)
The issue of the relationship between water discharge and the suspended sediment loads is a globally highly addressed topic. Knowing the suspended sediment loads in the streams avoids problems with over-filling of water cannons and thus prevents insufficient capacity of water reservoirs. This thesis is partly a follow-up to the bachelor thesis, which extends and introduces new procedures. Neural networks, more specifically multilayer perceptron neural networks, are used to analyse the relationship between water discharge and suspended sediment loads. The results of the networks are then processed in Excel into graphs and evaluated using the coefficient of determination, Nash-Sutcliffe coefficient and RMSE coefficient. The practical application is solved on two profiles - the profile Podhradí nad Dyjí and the profile Židlochovice. Each profile is examined in a different period.
|
|
|
A convolutional neural network for image segmentation
Mitrenga, Michal ; Petyovský, Petr (referee) ; Jirsík, Václav (advisor)
The aim of the bachelor thesis is to learn more about the problem of convolutional neural networks and to realize image segmentation. This theme includes the field of computer vision, which is used in systems of artificial intelligence. Special Attention is paid to the image segmentation process. Furthermore, the thesis deals with the basic principles of artificial neural networks, the structure of convolutional neural networks and especially with the description of individual semantic segmentation architectures. The chosen SegNet architecture is used in a practical application along with a pre-learned network. Part of the work is a database of CamVid images, which is used for training. For testing, a custom image database is created. Practical part is focused on CNN training and searching for unsuitable parameters for network learning using SW Matlab.
|
|
|
Recognizing Faces within Image
Svoboda, Pavel ; Žák, Pavel (referee) ; Švub, Miroslav (advisor)
The essence of face recognition within the image is generally computer vision, which provides methods and algorithms for the implementation. Some of them are described just in this work. Whole process is split in to three main phases. These are detection, aligning of detected faces and finally its recognition. Algorithms which are used to applied in given issue and which are still in progress from todays view are mentioned in every phase. Implementation is build up on three main algorithms, AdaBoost to obtain the classifier for detection, method of aligning face by principal features and method of Eigenfaces for recognizing. There are theoretically described except already mentioned algorithms neural networks for detection, ASM - Active Shape Models algorithm for aligning and AAM - Active Appearance Model for recognition. In the end there are tables of data retrieved by implemented system, which evaluated the main implementation.
|
|
|
Vehicle Control via Reinforcement Learning
Maslowski, Petr ; Uhlíř, Václav (referee) ; Šůstek, Martin (advisor)
The goal of this thesis is a creation of an autonomous agent that can control a vehicle. The agent utilizes reinforcement learning that uses neural networks. The agent interprets images from the front vehicle camera and selects appropriate actions to control the vehicle. I designed and created reward functions and then experimented with hyperparameters setup. Trained agent simulate driving on the road. The result of this thesis shows a possible approach to control an autonomous vehicle agent using machine learning method in CARLA simulator.
|
|
|
Traffic Signs Detection and Recognition
Číp, Pavel ; Honec, Peter (referee) ; Horák, Karel (advisor)
The thesis deals with traffic sign detection and recongnition in the urban environment and outside the town. A precondition for implementation of the system is built-in camera, usually in a car rear-view mirror. The camera scans the scene before the vehicle. The image data are transfered to the connected PC, where the data are transformation to information and evalutations. If the sign was detected the system is visually warned the driver. For a successful goal is divided into four separate blocks. The first part is the preparing of the image data. There are color segmentation with knowledge of color combination traffic signs in Czech Republic. Second part is deals with shape detection in segmentation image. Part number three is deals with recognition of inner pictogram and its finding in the image database. The final part is the visual output of displaying founded traffic signs. The thesis has been prepader so as to ensure detection of all relevant traffic signs in three basic color combinations according to existing by Decree of Ministry of Transport of Czech Republic. The result is the source code for the program MATLAB. .
|
guest ::
