|
|
Inter turn short-circuit detection in vector controlled PMS motor using AI
Zezula, Lukáš ; Kozovský, Matúš (referee) ; Blaha, Petr (advisor)
This thesis deals with the diagnostics of inter turn faults in a vector controlled synchronous motor with permanent magnets. Inter turn faults are detected by the pretrained convolution neural network GoogLeNet from adequately preprocessed signals of phase currents, inverter voltages and electrical angular velocity. Signal preprocesing includes, but is not limited to digital filtration, resampling and Wavelet transform. For the purpose of network training a drive system model is created, capable of simulating inter turn faults. The network is then trained on the simulated data and later validated with data measured on a real drive system, capable of emulating faults. The results of the diagnostics, together with the main problems are presented in the conclusion.
|
|
|
Detection of QRS complexes in ECG signals
Zhorný, Lukáš ; Ronzhina, Marina (referee) ; Kozumplík, Jiří (advisor)
This thesis deals with the detection of QRS complexes from electrocardiograms using time-frequency analysis. Detection procedures are based on wavelet and Stockwell transform. The theoretical part describes the basics of electrocardiography, then introduces common approaches to time-frequency analysis, such as short-time Fourier transform (STFT), wavelet transform and Stockwell transform. These algorithms were tested on a set of electrograms from the MIT-BIH and CSE-MO1 arrhythmia database. For the CSE database worked best the method based on the wavelet transform with the filter bank Symlet4, with the resulting value of sensitivity 100 % and positive predictivity 99.86%. For the MIT database had the best performance the detector using the Stockwell transform with values of sensitivity 99.54% and positive predictivity 99.68%. The results were compared with the values of other authors mentioned in the text.
|
|
|
Modernization of evaluation of the stored in-flight data
Koníček, Roman ; Hrabina, Martin (referee) ; Sigmund, Milan (advisor)
The thesis deals with the types of on-board registrars and on-board tape recorders used in the Air Force of the Czech Republic. Short research deals with the history of their development in the army. Above all, it focuses on acquiring and processing data from the current on-board P-503B deck. There are described the methods of single channel cleaning of acquired audio signal by nonlinear spectral subtraction and wavelet transform. The quality of filtered recordings was evaluated by subjective method. Further on, a speech detector working on the principle of spectral distance measurement is described. The last chapter deals with the solution of time synchronization of flight data and voice recording. Finally, the possibilities and use of the proposed program are assessed.
|
|
|
Practical examples of signal processing
Hanzálek, Pavel ; Smékal, Zdeněk (referee) ; Mekyska, Jiří (advisor)
The thesis focuses on the issue of signal processing. Using practical examples, it tries to show the use of individual signal processing operations from a practical point of view. For each of the selected signal processing operations, an application is created in MATLAB, including a graphical interface for easier operation. The division of the thesis is such that each chapter is first analyzed from a theoretical point of view, then it is shown using a practical demonstration of what the operation is used in practice. Individual applications are described here, mainly in terms of how they are handled and their possible results. The results of the practical part are presented in the attachment of the thesis.
|
|
|
ECG quality estimation
Pospíšil, Jan ; Smíšek, Radovan (referee) ; Smital, Lukáš (advisor)
This bachelor thesis deals with the question of estimation of the quality of the ECG signals, which is a key parameter for determining the diagnosis. The theoretical part deals with the basic knowledge concerning cardiac physiology, electrocardiography and finally the types of interferences that can occur during the measurement. The following practical part will deal with the published methods and the proposal of methods for estimating signal quality and their testing on artificial and real data.
|
|
|
ECG quality estimation
Pospíšil, Jan ; Smíšek, Radovan (referee) ; Smital, Lukáš (advisor)
This bachelor thesis deals with the question of estimation of the quality of the ECG signals, which is a key parameter for determining the diagnosis. The theoretical part deals with the basic knowledge concerning cardiac physiology, electrocardiography and finally the types of interferences that can occur during the measurement. The following practical part will deal with the published methods and the proposal of methods for estimating signal quality and their testing on artificial and real data.
|
|
|
Detection of ventricular premature beats in long-term ECG
Šagát, Martin ; Kozumplík, Jiří (referee) ; Maršánová, Lucie (advisor)
The thesis deals with problems of premature ventricular complexes and ways of their detection. Heart’s basic physiological activities and the principle of their measurement are described in the theoretical part of the thesis. It deals specifically with the appearance and manifestations of ventricular extrasystoles in the ECG. The thesis also discusses various ways of detecting premature ventricular complexes. In this thesis, detection based on morphological features, wavelet transform and signal energy was used. All methods were implemented using Matlab and tested on all signals of the MIT-BIH Arrhythmia database.
|
|
|
Sympatovagal balance analysis
Rusz, Jakub ; Ronzhina, Marina (referee) ; Janoušek, Oto (advisor)
The main focus of this work is to describe and implement a method to analyze sympathovagal balance. The theoretical part begins with electrocardiogram origin and measurement followed by heart rate variability explanation and a method of tachogram creation. The chapter is finished by description of wavelet transform as a means for tachogram processing and obtaining the sympato-vagal balance coeficient. Practical part of work focuses on developing a solution in Matlab for this problem. The R detector, tachogram creation and wavelet transform processing scripts with sympato-vagal balance assesment are fully described along with an example of their outputs. The work is finished with a conclusion of the findings and the assessment of sympato-vagal balance form them, which is unfortunately not so simple.
|
|
|
Optimal detection of the Twave end in ECG signals
Lorenc, Patrik ; Kozumplík, Jiří (referee) ; Vítek, Martin (advisor)
This work deals with the optimal detection of the T wave end in ECG signals, which uses the method of wavelet transform. Method of wavelet transform is now used quite a lot, because in practice it achieves good results. The aim of this work is a general introduction to ECG signal, wavelet transforms, and also with the method and realization of the T wave end detection.
|
|
|
Wiener Wavelet Filtering of ECG Signals
Sizov, Vasily ; Vítek, Martin (referee) ; Kozumplík, Jiří (advisor)
Tato práce se zabývá možností využití vlnkové transformace v aplikacích, které se zabývají potlačením šumu. Především se jedná o oblast filtrace signálu EKG. Úkolem je zhodnotit vliv různých parametrů nastavení samotné filtrace a zjistit jaký vliv má různé nastavení prahování wavelet koeficientů. Výsledkem práce je také stanovení hodnot prahů, stanovení nejlepšího způsobu rozkladu signálu a volba rekonstrukčních bank filtrů. Text obsahuje výsledky Wienerovy filtrace, při které byly testovány různé banky rozkladových a rekonstrukčních filtrů.Všechny popsané filtrační metody byly testovány na reálných záznamech EKG s aditivním myopotenciálním šumem. Algoritmy byly realizovány v prostředí MATLAB.
|
guest ::
