National Repository of Grey Literature 171 records found  1 - 10nextend  jump to record: Search took 0.00 seconds. 
Interactive GUI for Parish Records Rewritting
Zatloukal, Tomáš ; Žák, Marek (referee) ; Rozman, Jaroslav (advisor)
This thesis deals with the efficiency of transcription of matrices into computers. The goal is to create mechanisms that will improve the orientation in a larger number of form inputs. These mechanisms should also smartly complement the input field and check for errors.
Image Segmentation with Deep Neural Network
Pazderka, Radek ; Šůstek, Martin (referee) ; Rozman, Jaroslav (advisor)
This master's thesis is focused on segmentation of the scene from traffic environment. The solution to this problem is segmentation neural networks, which enables classification of every pixel in the image. In this thesis is created segmentation neural network, that has reached better results than present state-of-the-art architectures. This work is also focused on the segmentation of the top view of the road, as there are no freely available annotated datasets. For this purpose, there was created automatic tool for generation of synthetic datasets by using PC game Grand Theft Auto V. The work compares the networks, that have been trained solely on synthetic data and the networks that have been trained on both real and synthetic data. Experiments prove, that the synthetic data can be used for segmentation of the data from the real environment. There has been implemented a system, that enables work with segmentation neural networks.
RSS Reader for iOS
Bogdanchikov, Iaroslav ; Rozman, Jaroslav (referee) ; Hrubý, Martin (advisor)
The aim of this work is to create a mobile application for iOS operating system for easy following, reading and storing/archiving of stories from news sites and blogs accessed through web feeds in RSS format. The application is implemented in Swift programming language. Apple's Core Data application framework was used for data persistence. The work consists of theoretical and practical parts. The theoretical part describes the RSS format and principles of programming an application for iOS operating system. The practical part contains description of design, implementation and testing of the application. The resulting application provides user with a simple instrument to work with RSS channels and stories, and by following the Apple Human Interface Guidelines the application fits naturally in iOS ecosystem.
Comparison of Databases Systems for the Registers Digitalization
Rešovský, Martin ; Rozman, Jaroslav (referee) ; Kočí, Radek (advisor)
This paper presents comparative analysis of relational and object-based database systems over firmly specified data set gathered by registers digitalization of wedding and death records. Data were processed by chosen representants of theirs categories Db4o and PostgreSQL. Data model was created and described for both databases. Evaluation was made on the base of comparison of theoretical foundations, implementation and results of performance tests of the databases on test dataset equivalent to original sample. By carried out research, we found out, that relational model has stronger theoretical foundations, much better support and administration, and is more efficient. On the other hand, object-based approach models database much more naturally and preced construction complications. Main result is, that relational database model appears to be more efficient and preferable, and therefore, with gained knowledge, we can state, that it has better preconditions for effective processing of death and wedding historic records.
Program for Interactive Family-Tree Making
Navrátilová, Eva ; Zbořil, František (referee) ; Rozman, Jaroslav (advisor)
This thesis describes the design and implementation of an application for interactive family-tree making. The application supports importing and exporting data in GEDCOM format, further editing of the data, visualizing the data in family charts and their export. The design of the program is modular. It is implemented using C++ and Qt. The program was released for testing amongst the group of Czech and Slovak genealogists and their opinions on the program were obtained and analysed.
Intelligent Word Completing in GUI for Parish Records Rewriting
Postulka, Aleš ; Žák, Marek (referee) ; Rozman, Jaroslav (advisor)
This thesis is about creation of an intelligent word completion system for parish records rewriting. System is implemented as a part of graphical user interface of web application DEMOS. Main task of this system is displaying word suggestions for an individual record items, intelligent populating parts of parish record, displaying data suggestions for individual people of record and displaying suggestions which contains data suitable to populate the whole parish record.
Semi-Automatic Word Normalization in Parish Records
Hříbek, David ; Zbořil, František (referee) ; Rozman, Jaroslav (advisor)
This work deals with the extension of DEMoS web application for the management of parish records by the possibility of normalization (assignment of a normalized form of writing to individual words) of names, surnames, occupations, domiciles and other types of words occurring in parish records. In the solution, a duplicate record detection process was used, which allowed sorting of the records from parish records into clusters of similar words. As a result of the clustering, it was possible to share normalized word variants within these clusters. Thus, DEMoS suggests normalized variants for words entered by users, used not only for the same words, but also for similar words. In this work, automatic testing of word clustering was proposed. In total, 640 different combinations of clustering parameters were tested for each word type. Subsequently, the best clustering parameters were selected for each word type. By normalizing words, DEMoS application significantly increases the efficiency of searching in parish records. Records are also easier to read.
Comparison of Relation and Document Database Systems
Pakes, Marek ; Rozman, Jaroslav (referee) ; Kočí, Radek (advisor)
The purpose of this thesis is to compare relational and document-oriented database systems for use in genealogy field. PostgreSQL and MongoDB database systems were used in pursuance of the comparison. The systems are compared according to vital records of marriage and death certificates. Testing data set is generated and filled in the databases by an own implementation of a Node.js script.
Evolutionary Algorithms for Neural Networks Learning
Vosol, David ; Rozman, Jaroslav (referee) ; Zbořil, František (advisor)
Main point of this thesis is to find and compare posibilities of cooperation between evolutionary algorithms and neural network learning and their comparison with classical learning technique called backpropagation. This comparison is demonstrated with deep feed-forward neural network which is used for classification tasks. The process of optimalization is via search of optimal values of weights and biases within neural network with fixed topology. We chose three evolutionary approaches. Genetic algorithm, differential evolution and particle swarm optimization algorithm. These three approaches are also compared between each other. The demonstrating program is implemented in Python3 programming language without usage of any third parties libraries focused on deep learning.
Record Linkage in Genealogical Data
Šorm, Jan ; Rozman, Jaroslav (referee) ; Zbořil, František (advisor)
The main aim of this thesis is to study genealogical data, to find out possible problems in their merging and to implement methods for this data merging. In this thesis, it will be studied the problem of classifying similar names into common classes. This problem will be studied mainly because people's names and surnames play the most important role in every registry entry. In this thesis, it will be analyzed several metrics for calculating the distance between two strings. In addition, several experiments will be done for these metrics to classify names into classes with as few errors as possible. Based on these results, experiments for record linkage will be performed.

National Repository of Grey Literature : 171 records found   1 - 10nextend  jump to record:
See also: similar author names
5 Rozman, Jiří
Interested in being notified about new results for this query?
Subscribe to the RSS feed.