National Repository of Grey Literature 22 records found  beginprevious13 - 22  jump to record: Search took 0.00 seconds. 
Extreme learning machines for time series prediction
Zmeškal, Jiří ; Rajnoha, Martin (referee) ; Burget, Radim (advisor)
Thesis is aimed at the possibility of utilization of extreme learning machines and echo state networks for time series forecasting with possibility of utilizing GPU acceleration. Such predictions are part of nearly everyone’s daily lives through utilization in weather forecasting, prediction of regular and stock market, power consumption predictions and many more. Thesis is meant to familiarize reader firstly with theoretical basis of extreme learning machines and echo state networks, taking advantage of randomly generating majority of neural networks parameters and avoiding iterative processes. Secondly thesis demonstrates use of programing tools, such as ND4J and CUDA toolkit, to create very own programs. Finally, prediction capability and convenience of GPU acceleration is tested.
Handwritten text recognition using a sliding window
Ďuriš, Denis ; Povoda, Lukáš (referee) ; Rajnoha, Martin (advisor)
This bachelor thesis deals with optical character recognition. It focuses on recognizing hand-written text. The theoretical introduction describes the methods used for optical character recognition and selected machine learning methods. Subsequently, the work describes two methods for making cutouts of characters, using a sliding window. Cutouts are used in training and testing datasets of machine learning models. The document includes methods to improve the accuracy of character recognition. The accuracy of the models is evaluated in conclusion. Charcters in cutouts are clasified by an automated recognition program.
Machine Understanding for Text Messages Used in Aviation
Lieskovský, Pavol ; Rajnoha, Martin (referee) ; Povoda, Lukáš (advisor)
This work deals with problems of NOTAM in text format, which is used in aeronautics. It documents the difference between text and digital format of NOTAM, special types of NOTAM messages and items from which the NOTAM consist of. It describes syntax and the functions of program, which was made within the frame of this thesis. The program is fully capable of correct parsing and processing of the NOTAM. The program can display each area of processed NOTAM messages in map and also provides detection of collision between these areas and flight plan
Detection of moving objects in video
Hanek, Petr ; Přinosil, Jiří (referee) ; Rajnoha, Martin (advisor)
This bachelor thesis focuses on OpenCV library and it’s methods. Created application is able to detect moving objects from static camera video thanks to background subtraction methods. This application can be used different modes: detection in area which is calculated by BFS algorithm and two slightly different modes for crossing line detection. The application is multi thread because of graphical user interface demands on processor performance. This application also has implemented Kalman filter for multi target tracking and Hungarian method which solves assignment problem.
Image annotation using deep learning
Zarapina, Natalya ; Rajnoha, Martin (referee) ; Burget, Radim (advisor)
This semester thesis describes the design and implementation of the client-server program for classification and localization of certain elements which are present in provided images. This program loads a set of images and use deep learning, especially deep convolution neural network perform a classification. First part describes the architecture, basic principles of operations in convolution network and chosen machine learning algorithms for classification. Second part contains a description of created program.
Online interest point detector
Přibyl, Jakub ; Rajnoha, Martin (referee) ; Mašek, Jan (advisor)
This thesis focuses on online learning detector for long-term tracking of object in video sequence. The object is defined by a bounding box. The text describes different parts of the detector: object tracking, object detection and online learning detector. The main contribution of this work is creating extension of the OpenTLD program for parallel detection and tracking of multiple objects. The parallelization is then compared on two practical examples and the processor's impact on detection is compared. The best results were achieved with parallelization, where all objects were detected. The most accurate detection was in the case of sufficiently learned objects with the smallest shape change.
Convolution neural networks on the Windows platform
Kapusta, Martin ; Rajnoha, Martin (referee) ; Přinosil, Jiří (advisor)
The aim of the bachelor thesis is the latest knowledge of convolution neural networks and their application. The thesis describes the history, biological neuron and analogous mathematical model of a neuron. It also deals with the areas where neural networks are used, as well as the areas in which they expand gradually, the ways of learning and training, the differences between convolution neural networks and classical neural networks and their architecture. The thesis consists of two parts. The first part is the selection of the framework for working with convolution neural networks, which is suitable for implementation in the Windows operating system, the installation of the framework and its troubleshooting. The second part is aimed at creating an automated installation tool for the Windows 7 and Windows 10 operating system, created in JavaFX.
Analysis of the communication path attributes for IP geolocation
Rajnoha, Martin ; Komosný, Dan (referee) ; Balej, Jiří (advisor)
The aim of this thesis was to study current resources to find location of stations in the network Internet, mainly active methods that are based on delay measurements. Describe origin of the delay and its parts. Next create an application that is able remotely measure the delay between stations and convert this delay to distance. Aplication calculate geographic position of station on based this distances. For measurement was used experimental network PlanetLab.
Warehouse modeling using graphical user interface
Rajnoha, Martin ; Mašek, Jan (referee) ; Burget, Radim (advisor)
Master’s thesis proposes a new algorithm which enables efficient conversion of graphical representation of warehouse into graph theory representation and consequently accelerates estimation for route costs. The proposed algorithm computes route distances between any places in warehouse based on Breadth first search, image processing „skeletonization“ and Dijkstra algorithm. Using the proposed algorithm it is possible to search routes in a warehouse effectively and fast using precomputed routing table. Searching time is less then milisecond using routing table and even size of warehouse doesn’t affect it significantly instead of using Dijkstra algorithm.
Phenomenon of Emergence in Complex Information Systems
Rajnoha, Martin ; Bruckner, Tomáš (advisor) ; Svatoš, Oleg (referee)
The aim of this diplomma thesis is to build a platform of the phenomenon of emergence in complex information systems. To our best knowledge, there has not been provided any similar concept in either internetional or domestic academic literature. The necessity to create a concept of the phenomenon of emergence in the enviroment of information systems stems from the observation of the fragmented knowledge about the emergence concept in the pool of scientific papers where the link between emergence and information systems is missing. As a result, the platform created in this work is the reaction to the lack of the above mentioned link, while the ambition is to provide a cornerstone for potential emergence's utilization in information systems. In this work, we provide a construct that describes and analyzes the characteristics, technics and methodologies in connection with the phenomenon of emergence, placing a great deal on the specifics of the emergence in complex information sytems. Special attention is paid to eNetworks that we consider to be the best enviroment for examining the characteristics of emergent behavior in regards to the concept of complexity. This enviroment shows suitable conditions for the analysis of information spreading and dynamic interactions, which is primarily connected with generating of emergent characteristic. In order to understand the causality of specific emergence's demonstrations, we take a closer look at two approaches: Holonistic multi-agemt systems and iterative simulation process.

National Repository of Grey Literature : 22 records found   beginprevious13 - 22  jump to record:
See also: similar author names
1 Rajnoha, Milan