|
|
Programming of drivers of external devices and data evaluation in C++
Kaščák, Kamil ; Kodyš, Peter (advisor) ; Lokoč, Jakub (referee)
In the present work we study current status of drivers for external devices in clean room in Institute of Particle and Nuclear Physics. In this work we analyse existing software and create a new driver for communication through RS232 port. Work studies various possibilities of serial communication in Windows and Linux and creates possible design for driver, which is based on creating universal layer for supplying communication between user programs and external devices. Work describes important steps of implementation in both operating systems. Next part consists of user documentation for created software. This documentation focuses on di erences of usage in Windows and Linux. At the end work shows report from testing software with real devices and gives advices, which should programmer follows when creating similar software solution.
|
|
|
Object detection for video surveillance using the SSD approach
Dobranský, Marek ; Lokoč, Jakub (advisor) ; Božovský, Petr (referee)
The surveillance cameras serve various purposes ranging from security to traffic monitoring and marketing. However, with the increasing quantity of utilized cameras, manual video monitoring has become too laborious. In re- cent years, a lot of development in artificial intelligence has been focused on processing the video data automatically and then outputting the desired no- tifications and statistics. This thesis studies the state-of-the-art deep learning models for object detection in a surveillance video and takes an in-depth look at SSD architecture. We aim to enhance the performance of SSD by updating its underlying feature extraction network. We propose to replace the initially used VGG model by a selection of modern ResNet, Xception and NASNet classifica- tion networks. The experiments show that the ResNet50 model offers the best trade-off between speed and precision, while significantly outperforming VGG. With a series of modifications, we improved the Xception model to match the ResNet performance. On top of the architecture-based improvements, we ana- lyze the relationship between SSD and a number of detected classes and their selection. We also designed and implemented a new detector with the use of temporal context provided by the video frames. This detector delivers enhanced precision while...
|
|
|
Hybrid databases
Hušek, Radek ; Mareš, Martin (advisor) ; Lokoč, Jakub (referee)
This thesis presents design and implementation of a data structure, which tries to combine advantages of both databases and regular data structures. Main advantages of databases we try to retain are data persistence through storing data on a hard disk and working with data using transactions which allows us parallel access without danger of inconsistency. From data structures we borrow the implementation as a library of functions and the aim on simplicity and storing data in memory. Our implementation is built around the concept of (software) transactional memory; all data are stored on hard drive as log of operations. 1
|
|
|
The Support of XML Technologies in Oracle DB, IBM DB2 and Microsoft SQL Server
Hazaran, Elina ; Holubová, Irena (advisor) ; Lokoč, Jakub (referee)
The aim of this thesis is to perform an all-round comparison analysis of XML technologies support in three database systems: Oracle DB, IBM DB2 and SQL Server. It includes a theoretical technologies description and their comparison analysis, along with implemented software which is designed to run experiments by querying XML data using XQuery, SQL/XML technologies and XMark benchmark. It provides the comparison of database performances based on different storage methods, create time comparison statistics, export results to a text file and store the history of previous results. The main part of the work is the demonstration of several experiments run and a detailed analysis of the database performances based on the obtained results.
|
|
|
Communication with external devices in laboratory
Vachna, Michal ; Kodyš, Peter (advisor) ; Lokoč, Jakub (referee)
In the present work the goal is to map present circumstances of computer infrastructure in the physical laboratory, examine the demands and problems at work in the laboratory such as data backup, remote control, disk space sharing, access organization of processes to external devices, version control of measuring application development, running processes on remote hosts. Assess existing solutions, consider the possibility of improvements and propose new solutions appropriate to the needs of the laboratory. As far as possible, in regard to the current operations of the laboratory, implement solutions to selected problems and requirements. The work has to be methodical material and guide for further development of the laboratory in the coming years.
|
|
|
Using Metric Indexes For Effective and Efficient Multimedia Exploration
Čech, Přemysl ; Lokoč, Jakub (advisor) ; Skopal, Tomáš (referee)
The exponential growth of multimedia data challenges effectiveness and efficiency of the state-of-the- art retrieval techniques. In this thesis, we focus on browsing of large datasets using exploration approaches where query cannot be particularly expressed or where the need of some general notion of the dataset is required. More specifically, we study exploration scenarios utilizing the metric access method PM-Tree which natively creates a hierarchy of nested metric regions. We enhance the PM- Tree for the exploration purposes and define different traversing and querying strategies. Further, we investigate range multi-query (range query defined by multiple objects) approaches. We propose new effective and efficient cut-region range query and compare the new query with other approaches for efficient multi-query processing. Finally, we implemented all new methods and strategies for the PM- Tree into multimedia exploration framework and tested browsing algorithms on a game-like demo application.
|
|
|
IS for organizaton's production monitoring
Dzurenko, Tomáš ; Hoksza, David (advisor) ; Lokoč, Jakub (referee)
Storing and processing data is a prerequisite to succesful functioning of every organisation. This work deals with implementation of easily accessible and user friendly application which would provide tools for simple data in- put and subsequent displaying of these data in a predefined reports. Reports can be displayed for any time period and with different level of grouping. Important feature of this application is comparing inserted data with prede- fined plans. Application is built using ASP.NET and C# technology. Data are stored using Microsoft SQL Server 2005. 1
|
|
|
Multi-model Approach For Effective Multimedia Exploration
Grošup, Tomáš ; Lokoč, Jakub (advisor) ; Somol, Petr (referee)
This work is focusing on exploration of multimedia collections. It describes the problematic of exploration and proposes new approaches to it, two based on the data structure M-Index and two utilizing multiple similarity models at once. Those approaches were compared using an extensive user study. Part of this work is also devoted to analysis of a new exploration system, design of its architecture, system implementation and its deployment. This exploration system was used in several applications, which are also shown and described in this thesis.
|
|
|
Visualisation of Text Retrieval Algorithms
Remiš, Daniel ; Kopecký, Michal (advisor) ; Lokoč, Jakub (referee)
The work deals with design and implementation of the program, which is used to clarify the operation of algorithms for searching through text using a graphical view of their structures. The work also includes some analyzis of already existing, interesting visualization tools designed to address other areas.
|
|
|
Using Neural Networks in the Hierachical Routing
Straka, Martin ; Štanclová, Jana (advisor) ; Lokoč, Jakub (referee)
The objective of the diploma thesis is to show possible utilization of the neural networks for the partitioning needs of the hierarchical routing algorithm. The work proposes a hierarchical approach, which can be useful for the optimal path searching process. We focus on the application of several neural network models to extract hierarchical information from the transportation network data. Introduced models are based on the energy minimization principle and we demonstrate an employment of the deterministic annealing methods (MFA) as quite ambitious in the partitioning process. The experimental part of this work makes use of our findings and propose several suggestions on the proper parametrization of employed neural network models. In the experimental tests, we demonstrate capabilities of the MFA to provide a partitioning task also in case of lack of the global information.
|
guest ::
