|
|
Very Low Bit-Rate Speech Coding Based on Neural Networks
Jochman, Stanislav ; Malenovský, Vladimír (referee) ; Černocký, Jan (advisor)
Vrámci tejto práce sme skúmali možnosti zlepšenia kvality zvuku produkovaným pomocou neurónovej siete LPCNet. Analyzovali sme vplyv použitia dátových setov zameraných na cieľový jazyk a ich vplyv na kvalitu výsledného zvuku. Pre meranie kvality kódovania reči sme využili hodnotiaci systém WARP-Q. Cieľom našej práce bolo navrhnúť vylepšenie trénovacieho dátového setu a použitie postfilterov pre zlepšenie kvality zvuku. Naše výsledky ukazujú merateľné zlepšenia s využitím malého slovenského dátového setu. Rovnako sme zaznamenali, že využitie dolnopriepustného filteru a filtra zlepšujúceho formanty zlepšilo kvalitu výsledného zvuku.
|
|
|
Health assessment using smart devices
Vargová, Enikö ; Filipenská, Marina (referee) ; Němcová, Andrea (advisor)
This thesis deals with the possibilities of non-invasive determination of blood glucose from photoplethysmographic signals. Elevated blood sugar is often associated with disease called diabetes mellitus. Diabetes is one of the world’s major chronic diseases. Untreated diabetes is often a cause of death. The aim of the work is to propose methods for glycemic classification and prediction. Two datasets have been created by recording the PPG signals using two smart devices (a smart wristband and a smartphone), along with their blood glucose levels measured in an invasive way. The PPG signals were preprocessed, and suitable features were extracted from them. Various machine-learning models for glycemic classification and prediction were created.
|
|
|
Temperature Profile in Reflow Soldering and Influence of Different PCBś and ComponentsThermal Capacities
Procházka, Martin ; Špinka, Jiří (referee) ; Starý, Jiří (advisor)
This thesis mainly deals with the prediction of temperature on the components and the PCB during reflow soldering. The theoretical part describes the particular solder reflow process, types of heat transfer and temperature profiles. The practical part is divided into forecasting temperatures if the conveyor is stopped and the temperature predictions when the conveyor is in motion. In both parts of the measured temperature is compared with the predicted temperatures, which show the success rate of prediction. The last part of this work is part of the simulation, which helps in proper understanding of the issues discussed.
|
|
|
Risk Management of Bank Credit System and Decision Making Process
Skovajsa, Radek ; Kryštof, Zdeněk (referee) ; Čižinská, Romana (advisor)
The theoretical part of this thesis describes the development of Czech banking sector, especially with emphasis on post-revolutionary rebirth within the new conditions of market economy. The following part demonstrates the decision-making credit account process of a bank on a particular case study based on the methodics and procedures leading up to maximal elimination of credit risk. At the same time, the author presents a partially modified internal opinion on a decision of particular business transaction. It is accented that every decision of a bank must comply with the regulations of CNB. The conclusion of the thesis affirms the maximal efforts of domestic banks to minimalize risks within their decision-making credit account processes, which is mirrored in current stability in the development of Czech banking sector.
|
|
|
Optimization of the Bank Loan Application
Skovajsa, Radek ; Kořínková, Martina (referee) ; Čižinská, Romana (advisor)
The work is based both on theoretical basis and practical working processes of banks for assessing client's financial standing in Czech market environment. Basic preconditions for successful credit allocation to a business entity will be set along with evaluation of the importance of information from a credit requisition form's compulsory enclosure. A detailed analysis of the client's economy from a bank perspective will be succeeded by identification of critical risks and positives of an applicant's financial position.
|
|
|
Prediction of Selected Parameters of Rotational Kinematics Pairs of Machine Tools
Marek, Tomáš ; Šooš, Ĺubomír (referee) ; Kolář, Petr (referee) ; Blecha, Petr (advisor)
The dissertation thesis is used as a methodology for prediction of selected parameters of rotational kinematic pairs of machine tools. The motivation for its writing has been continually increasing requirements for parameters (performance, accuracy, static and dynamic stiffness) of machine tools. The methodology takes into account the availability of suitable measuring devices and description of the design of rotary kinematic pairs. It will be useable for predicting the behavior of rotational kinematic pairs, even at the design stage by applying results to the machine design. The work is processed so that first is used a system approach to suggest methodology for prediction of the behavior of rotary kinematic pair in CNC machine tools, planning measurement strategy and verifying the results, including applications for specific kinematic chain of the selected machine. Based on this system approach and the resulting methodology, the measurement of the rotary kinematic pair was performed. The results of the system approach and measurement are generalized in the form of recommendations for designers of machining centers, allowing to increase the accuracy of the rotational kinematic pair.
|
|
| |
|
|
Algorithmic Trading Using Twitter Data
Kříž, Jakub ; Plchot, Oldřich (referee) ; Szőke, Igor (advisor)
This master's thesis describes creation of prediction system. This system predicts future market development based on stock exchange data and twitter messages analysis. Tweets from two different sources are analysed by mood dictionaries or via recurrent neural networks. This analysis results and technical analysis of stock exchange data results are used in multilayer neural network for prediction. A business strategy is created and tested based on results of this prediction. Design and implementation of prediction system is described in this thesis. This system achieved revenue increase more than 25 % of some business strategies by tweets analysis. However this improvement applies for certain data and timeframe.
|
|
|
Optimization of Run Configurations of k-Wave Jobs
Sasák, Tomáš ; Jaroš, Marta (referee) ; Jaroš, Jiří (advisor)
This thesis focuses on scheduling, i.e. correct approximation of configurations used to run k-Wave simulations on supercomputers from the IT4Innovations infrastructure. Especially, for clusters Salomon and Anselm. A single work is composed of a set which contains many simulations. Every simulation is executed by some code from the k-Wave toolbox. To calculate the simulation, it is necesarry to select a suitable configuration, which means the amount of supercomputer resources (number of nodes, i.e. cores), and the duration of the rental. Creation of an ideal configuration is complicated and is even harder for an inexperienced user. The approximation is made based on the empiric data, obtained from multiple executions of different sets of simulations on given clusters. This data is stored and used by a set of approximators, which performs the actual approximation by methods of interpolation and regression. The text describes the implementation of the final scheduler. By experimenting, the most efficient methods for this problem has found out to be Akima spline, PCHIP interpolation and cubic spline. The main contribution of this work is creation of a tool which can find suitable configuration for k-Wave simulation without knowing the code or having lots of experience with its usage.
|
|
|
Prediction of gravity quantities values based on the terrestrial measurements and digital elevation model
Letko, Ivan ; Doudová, Lenka (referee) ; Machotka, Radovan (advisor)
The main objective of this master thesis is random equipartition concentration of measured gravimetric points in the area of interest pursuant by digital terrain model. Remove-Compute-Restore method was used for this purpose. In this thesis normal acceleration of gravity, topographic effect and Faye anomaly were subtracted from measured gravity. The result is Bouguer anomaly with general topographic effect which is interpolated for concentration points. We obtained predicated values of gravity after the restoration of subtracted effects. The main result of the thesis is the map of real gravity and precision evaluation of used method. Furthermore, the reductions of gravity, interpolation methods in programme ArcGIS, Remove-Compute-Restore method and the term of digital terrain model are explained in the thesis.
|
guest ::
