This paper discusses design and implementation of classifying system for recognition of musical instruments from audio records with use of Musical Information Retrieval techniques. In the first part, paper describes parameters used for instrument classification, calculation of said parameters from records and reduction of feature vector. Next part is devoted to tuning and implementation of various classifiers with focus on neural networks. These classifiers ar further tested on records from IRMAS dataset wchich contain 11 musical instruments playing solo or with other instruments. Results of classifiers tested on different parameters and different numbers of instruments are discussed in the last part.

This thesis is focused on cybercrime, acquisition of evidence and development of a platform for retrieval, analysis and archiving web site data. The goal is to satisfy the investigators and security experts of the Czech police. The aim is to provide an open source platform that will be freely disseminable and in compliance with the requirements of legal institutions. The output of the thesis is two platform versions - full-fledged, fulfilling all the requirements set out in the diploma thesis and a light version for the police investigators of the Czech Republic.

The goal of this thesis is to create control software for stand-alone payment machines. The purpose of this software is minimize maintenance cost and usability as much as possible. Description of technologies and protocols used in implementation are in the text. Next, there is process of work beginning with analysis, continues with design, construction, testing and installation manual. Projekt status and product utilization at the end of project is in chapter about evaluation.

The aim of the graduation thesis is to evaluate the current development in the field of SDN and the possibility of programmability of SDN elements using the application programming interface. The first theoretical chapter describes the following: the basic architecture of SDN, the traffic within SDN between its individual layers, the communication protocols Southbound interface and Northbound interface. The second chapter of the thesis deals with the programmability of SDN elements with the help of API. The third theoretical chapter describes the current development in the field of SDN. The practical part of the thesis is devoted to creation of two laboratory tasks dealing with the programming of the SDN API. Laboratory tasks include BIG-IP programming from F5 Network and routers from Arista Network. Programming is done using Python via REST API for BIG-IP, or eAPI for Arista EOS. The Ansible setup tool is also used for the same purpose.

This diploma thesis deals with the kidney tumor segmentation in CT data. First kidney anatomy and pathology is discussed. Following topics are the conventional segmentation techniques and segmentation techniques using machine learning. In the final part, the convolutional neural network is discussed as its algoritm was used for segmentation in the practical part, in which algoritm for segmentation was designed in Python programming language. This algoritm was tested and evaluated using databaze KiTS19.

The thesis is about industrial automatic CIP protocol, which belongs to SCADA systems. The first part is focused on basic principles of CIP protocol and on analysis of two protocols (EtherNET/IP and DeviceNet), which are based on CIP protocol. The second part deals with designing scenarios for a simulation. The simulation of one-way communication, two-way communication with help of reads from the console and two-way real time communication between Raspberries PI 3B+. The third part deals with a realization of the simulation, a start-up and a function of predefined scenarios and graphic interface. The fourth part deals with analysis network communication in situations, which occur during a protocol EtherNet/IP simulation.

This thesis deals with description and implementation of AAS module. This thesis describes the selection of individual components of device. This module will be a part of the testbed Barman project. This project is implemented in accordance with Industry 4.0 trends. Device will be work as reader of information and ingredients from NFC tags placed on a glass. With this information, parent cell can make decision which action will be done with glass. In this thesis, software for hardware operation with AAS module will be created and described. This program will further communicate with the parent program controlling the functionality of the cell itself.

The main goal of the master thesis is design and implementation of information system for monitoring purposes. The implemented monitoring system will be able to automatically monitor devices of a certain company. This goal is preceded by strategic analysis using PEST and 7S methods for examination of current state of the company. Another part is the analysis of the efficiency of service processes using the HOS method together with the selection of a suitable monitoring system. An enhancement of service processes is designed by the Lewin model. Finally, the selected information system for monitoring was designed, implemented and tested. A deployment of the system should provide simplification of devices supervision, to save costs as well as to speed-up the response-time to unexpected situations.

This diploma thesis deals with robotic automation of selected business process using RPA technology. Robotic automation tools are compared with each other and two are subsequently selected for development of the automation – the UiPath software and the AiVIRO library. Realized automations are compared and evaluated in conclusion.

This diploma thesis deals with the use of freely available data sets to estimate the signal strength in localities where measurements are missing. This work aimed to use interpolation and regression methods to estimate as accurately as possible the possible signal coverage in a given locality. First, data sets were analyzed, based on results, a test model for various methods has been created. The methods with the best results have been implemented on real data sets containing thousands of measurements. At the end of the work, accurate estimates are commented and circumstances to reduce the deviation of the measured and calculated values are specified.