National Repository of Grey Literature 22 records found  previous11 - 20next  jump to record: Search took 0.00 seconds. 
Parking Spot Recognition by Artificial Intelligence
Sicha, Marek ; Koudelka, Vlastimil (referee) ; Kadlec, Petr (advisor)
This thesis deals with the recognition of parking spots in images using artificial intelligence. The goal of the work was to study neural networks and select a suitable network to solve the problem. Python programming language was chosen for implementation and Mask R-CNN convolutional network was selected as a suitable neural network. To train the neural network, a custom dataset was created which contains images captured from street cameras. The trained network was then implemented in a program that easily provides information about available parking spaces in a particular area. The program analyzes images from cameras in parking lots and on streets, identifies the number of available parking spaces, and displays this information on a map.
Spatio-Spectral EEG Patterns in the Source-Reconstructed Space and Relation to Resting-State Networks: An EEG-fMRI Study
Jiříček, Stanislav ; Koudelka, V. ; Mantini, D. ; Mareček, R. ; Hlinka, Jaroslav
In this work, we present and evaluate a novel EEG-fMRI integration approach combining a spatio-spectral decomposition method and a reliable source localization technique. On the large 72 subjects resting- state hdEEG-fMRI data set we tested the stability of the proposed method in terms of both extracted spatio-spectral patterns(SSPs) as well as their correspondence to the BOLD signal. We also compared the proposed method with the spatio-spectral decomposition in the electrode space as well as well-known occipital alpha correlate in terms of the explained variance of BOLD signal. We showed that the proposed method is stable in terms of extracted patterns and where they correlate with the BOLD signal. Furthermore, we show that the proposed method explains a very similar level of the BOLD signal with the other methods and that the BOLD signal in areas of typical BOLD functional networks is explained significantly more than by a chance. Nevertheless, we didn’t observe a significant relation between our source-space SSPs and the BOLD ICs when spatio-temporally comparing them. Finally, we report several the most stable source space EEG-fMRI patterns together with their interpretation and comparison to the electrode space patterns.
Kindergarten FUTURUM
Koudelka, Vojtěch ; Erben, Adam (referee) ; Pavlovský, Tomáš (advisor) ; Kolář, Radim (advisor)
The goal of this bachleor thesis was to create a modern nursery with the capacity of two classes for children of mainly preschool age. The nursery will be a part of the scholastic partnership in the Brno Masaryk district. The building on the southwest part of the area has a similar footprint to the already existing school. It consists of two floors. The facility is designed to complement the surroundings in terms of space and vista. The construction is visually similar to the present buildings in the area due to carefully chosen facades and colours.The terraces are constructed from three fields, one a little higher than the other, the buidling system is copying the terraces. A significant element of the facade is the brick porches created from plaster and slanting console. They define an entrace to the building. The structural wall system consists of a masonry unit and cast-in-place concrete. The roof of the construction is formed by prestressed slabs. Furthermore, children need a large enough grassy area to play outside, and so, to compensate for all lost parts of the terrain, there will be an eco-friendly roof. The replacement of buited-up surface of grass made by a green roof is a reaction of heavily tree fitted part of the city.
Semantic personalization
Koudelka, Václav ; Zavoral, Filip (advisor) ; Eckhardt, Alan (referee)
The aim of this work is to design and implement a tool in form of framework, which is destined for web architects and should enable methods of personalization within the scope of arbitrary web application. Framework will obtain information on functioning of web application, it will try to determine, how is application used by users and based on this knowledge it will attempt to make using of application more efficient by means of environmental adaptations. During framework designing emphasis will be put on easiness of using within common web application, to its work it should use only means commonly available within any standard webhosting. For every user will be application environment personalized on the basis of his behaviour. Part of framework will be intelligent precision mechanism, whose input will be data about web application usage and data retrieved from user. Output will be set of recommendations for application modification. Part of thesis is also sample web application, in which framework potential is demonstrated.
Microstates analysis in EEG data of sleep-deprived subjects
Křápková, Monika ; Koudelka, Vlastimil (referee) ; Lamoš, Martin (advisor)
This bachelor’s thesis deals with the processing and analysis of EEG data in sleep deprived subjects. In the theoretical part, the electroencephalography method is presented first. Further, there are possibilities of preprocessing and analysis of EEG data, introduction to statistics, and the last one is a research on the influence of sleep deprivation on human electrophysiology. The practical part consists of the preprocessing of EEG data, EEG microstates analysis and statistical evaluation of the results from the study of sleep deprivation. Finally, the results of this part are discussed in a separate chapter.
Neural Modeling of Electromagnetic Fields in Cars
Kotol, Martin ; Škvor, Zbyněk (referee) ; Koudelka, Vlastimil (referee) ; Raida, Zbyněk (advisor)
Disertační práce se věnuje využití umělých neuronových sítí pro modelování elektromagnetických polí uvnitř automobilů. První část práce je zaměřena na analytický popis šíření elektromagnetických vlny interiérem pomocí Nortonovy povrchové vlny. Následující část práce se věnuje praktickému měření a ověření analytických modelů. Praktická měření byla zdrojem trénovacích a verifikačních dat pro neuronové sítě. Práce se zaměřuje na kmitočtová pásma 3 až 11 GHz a 55 až 65 GHz.
Modeling the brain of a rat
Kuřátko, David ; Koudelka, Vlastimil (referee) ; Raida, Zbyněk (advisor)
This master’s thesis deals with creation and modification of several numerical rat’s brain models which are subsequently used in electromagnetic software CST Studio Suite 2014. The first part of the thesis is focused to insertion of exciting source to the model which depends on the used approach. These sources produce signals on the surface of the rat’s brain model which are then analysed. The experimental part of the thesis dealt with three different procedures of cooking agar jelly, which were used for creation of five plate capacitors, which subsequently served for measure electric properties of phantom. The conclusion of this master’s thesis is focused on comparison between results from simulations and experimental parts with a subsequent analysis of the deviations of results and their possible causes.
Human brain and its modeling
Zelenka, Pavel ; Koudelka, Vlastimil (referee) ; Raida, Zbyněk (advisor)
The project deals with the development of a computer model of human brain. The model is used in the simulation program CST STUDIO SUITE 2015 to show the distribution of electromagnetic waves. The outputs of simulations should help us with a better understanding of electromagnetic field behavior inside the brain. In real life, the model will be used for the verification of methods localizing source currents in the brain.
Semantic personalization
Koudelka, Václav ; Eckhardt, Alan (referee) ; Zavoral, Filip (advisor)
The aim of this work is to design and implement a tool in form of framework, which is destined for web architects and should enable methods of personalization within the scope of arbitrary web application. Framework will obtain information on functioning of web application, it will try to determine, how is application used by users and based on this knowledge it will attempt to make using of application more efficient by means of environmental adaptations. During framework designing emphasis will be put on easiness of using within common web application, to its work it should use only means commonly available within any standard webhosting. For every user will be application environment personalized on the basis of his behaviour. Part of framework will be intelligent precision mechanism, whose input will be data about web application usage and data retrieved from user. Output will be set of recommendations for application modification. Part of thesis is also sample web application, in which framework potential is demonstrated.
Advanced microwave filter analyses and design
Čáslavský, Jan ; Urbanec, Tomáš (referee) ; Koudelka, Vlastimil (advisor)
his thesis investigates the design methodology of microstrip filters. The work deals with important steps in microwave filter design. Namely, the selection of approximate function and suitable representation of ideal filter elements are investigated. The basic design approach is demonstrated on the simple examples of microwave filters. These designed filters are analyzed in the program Ansoft Designer.

National Repository of Grey Literature : 22 records found   previous11 - 20next  jump to record:
See also: similar author names
4 Koudelka, Vlastimil
3 Koudelka, Vojtěch
3 Koudelka, Václav
Interested in being notified about new results for this query?
Subscribe to the RSS feed.