National Repository of Grey Literature 139 records found  1 - 10nextend  jump to record: Search took 0.00 seconds. 
Cephalopod jaws from the Bohemian Cretaceous Basin - taxonomy and stratigraphic implications
Kozlová, Zuzana ; Košťák, Martin (advisor) ; Vašíček, Zdeněk (referee)
This work is focused on systematic research of cephalopod jaws from the Late Cretaceous. Samples of 147 newly recorded nautiloid rhyncholites from the Bohemian Cretacoeus Basin and one new ammonite rhyncholite from Řepov village were systematically analyzed. The new collection of lower ammonite jaws (aptychi) consists of 32 specimens. Nautiloid rhyncholites from localities Turkaňk, Úpohlavy, and Dreisen were determined as Nautilorhynchus simplex. Conchorhynchs from locality Vinary u Vysokého Mýta belong to the species Conchorhynchus cretaceous, which is associated with the commonmost species Eutrephoceras sublaevigatum. Ammonite rhyncholite is left in the open nomenclature due to its uncertain systematic position and it is not assigned to any ammonite species. Records of aptychi from the locality of Úpohlavy and Pecínov represent mainly species of heteromorphic ammonites - baculitids (Baculites, Sciponoceras). The total diversity of species from both localities reaches 20 ammonite species. The two jaw morphotypes (2 species of aptychi) are reported from the Bohemian Cretaceous Basin for the first time herein. Of the high importance, it is a record of ammonite Prionocyclus germari from Úpohlavy with associated lower jaws in situ within the body chamber. Aptychus of this taxon has never been...
Automatic Chord Recognition Using Deep Neural Networks
Nodžák, Petr ; Bidlo, Michal (referee) ; Vašíček, Zdeněk (advisor)
This work deals with automatic chord recognition using neural networks. The problem was separated into two subproblems. The first subproblem aims to experimental finding of most suitable solution for a acoustic model and the second one aims to experimental finding of most suitable solution for a language model. The problem was solved by iterative method. First a suboptimal solution of the first subproblem was found and then the second one. A total of 19 acoustic and 12 language models were made. Ten training datasets was created for acoustic models and three for language models. In total, over 200 models were trained. The best results were achieved on acoustic models represented by convolutional networks together with language models represented by recurent networks with LSTM modules.
Application of Neural Accelerators on Rapsberry PI
Barna, Kristian ; Sekanina, Lukáš (referee) ; Vašíček, Zdeněk (advisor)
The presented bachelor thesis deals with the statistical evaluation of performance for hardward accelerator of deep neural networks. Describes convolutional neural networks along with mathematical calculations. Explains their acceleration and conversion to a format suitable for the Intel Movidius NCS accelerator. 8 hardware platforms and 22 neural network difficulties were compared experimentally. Up to 105-fold improvement  was demonstrated in isolated inference of the MobileNetV2 network for the Raspber Pi platform using an accelerator. Performance between the tested platforms was also evaluated from an energy point of view. The application of facial identity demonstrated the conditions during real use. Possible limits of CNN acceleration on power-limited devices (Raspberry Pi) have been uncovered, especially due to improper selection of input image resolution. All measurements were evaluated by statistical procedures.
Application of Approximate Computing in Image Processing
Hruda, Petr ; Vašíček, Zdeněk (referee) ; Bidlo, Michal (advisor)
This master thesis focuses on approximate computing applied to image processing. Specifically, the approximation is applied to adaptive thresholding. Two approaches were used, the design of a new system using approximated components and the approximation of an existing algorithm. The resulting effect on thresholding quality was investigated. Experimental evaluation of the first approach shows quality improvements of thresholding with usage of aproximated components. Also, area of found aproximated solutions is smaller. Evaluation of the second approach shows worse quality of thresholding with usage of aproximated components. The second approach is then declared inappropriate.
Quality Monitoring Device for Electrical Power Networks
Bartoň, Jan ; Šimek, Václav (referee) ; Vašíček, Zdeněk (advisor)
The diploma thesis deals with the parameters of electricity quality. The aim of this work is to design and implement a prototype device that will allow remote measurement of power quality. The proposed system uses NB-IoT technology for data transmission. The system enables remote measurement of important parameters of electrical energy, such as the magnitude of the supply voltage or the frequency of the electric network. The device can measure electric current, average voltage values and detect dip / swell voltage events. The device reads a sampled electrical signal suitable for harmonic analysis. The device has started to meet the requirements for measuring device of class S according to EN 61000-3-40.
Optimizations Methods for Freight Transportation
Gabonay, Michal ; Vašíček, Zdeněk (referee) ; Bidlo, Michal (advisor)
The following work concerns the study of the evolutionary algorithm, which optimizes freight transport planning. The demand for freight transport is constantly increasing nowadays and with creating, implementing and using proper route planning we are able to significantly reduce transportation costs. However, it is preferably to implement it in companies with large numbers of served customers and with a sufficiently large fleet of vehicles.   The study starts by defining what fright transport planning problem is and by characterizing its existing specifications and variants. My work proceeds to give a background of the possible solutions to the multifaceted aspects of the problem. The specific subproblem I choose to focus on is the Vehicle routing problem with Pickup and Delivery for which I apply the optimization solution. In the main body of my thesis, I will elaborate on the chosen optimization solution which encompasses the genetic algorithm and evolutionary strategy. The aim of the study is to measure the suitability of the algorithms and techniques used, for which reason the final part of my work will deal with the analysis and evaluation of the experiments.
Evolutionary Design of Convolutional Neural Networks
Piňos, Michal ; Vašíček, Zdeněk (referee) ; Sekanina, Lukáš (advisor)
The aim of this work is to design and implement a program for automated design of convolutional neural networks (CNN) with the use of evolutionary computing techniques. From a practical point of view, this approach reduces the requirements for the human factor in the design of CNN architectures, and thus eliminates the tedious and laborious process of manual design. This work utilizes a special form of genetic programming, called Cartesian genetic programming, which uses a graph representation for candidate solution encoding.This technique enables the user to parameterize the CNN search process and focus on architectures, that are interesting from the view of used computational units, accuracy or number of parameters. The proposed approach was tested on the standardized CIFAR-10dataset, which is often used by researchers to compare the performance of their CNNs. The performed experiments showed, that this approach has both research and practical potential and the implemented program opens up new possibilities in automated CNN design.
Access System Controller Supporting More Types of Identification
Havlíček, Lukáš ; Bidlo, Michal (referee) ; Vašíček, Zdeněk (advisor)
This thesis deals with design and implementation of access system control unit supporting more types of identification. Designed system supports identification using access cards MIFARE and detection of Bluetooth Low Energy devices. Device is realised using the ESP32 development board. The display of passage history and system configuration is solved using a web interface, which is provided by a web server running on this device.
Smart Home Security System
Dragúň, Peter ; Bidlo, Michal (referee) ; Vašíček, Zdeněk (advisor)
This thesis deals with the security of flats and houses using Bluetooth Low Energy (BLE) technology. The aim of the thesis is to develop an electronic security system for access and intrusion control exploiting the possibilities of Bluetooth Low Energy technology for improved user experience. The thesis describes security systems, BLE technology and ESP32 microcontroller. The creation of a mobile application that is used to set up the system and its management is included, as well. The thesis also describes the design, construction of a prototype and its implementation. The last part is the verification of functionality, testing and suggestions of possibilities for further improvement of the created prototype.
Simple Video Game Based on Reconfigurable FPGA Platform
Kuba, Adam ; Vašíček, Zdeněk (referee) ; Šimek, Václav (advisor)
The aim of this thesis is to create video game. The target platfrom in this thesis is educational kit Minerva, which is equiped by microcontroller Kinetis K60 and Field-programmable gate array Spartan 6 by company Xilinx. The video game includes graphics output via HDMI, using the TFP410 circuit, which takes care of image generation. User input is realized using a keyboard connected to the pins of the kit. The video game is intended to serve as a sample application for a educational kit.

National Repository of Grey Literature : 139 records found   1 - 10nextend  jump to record:
See also: similar author names
1 Vašíček, Z.
Interested in being notified about new results for this query?
Subscribe to the RSS feed.