National Repository of Grey Literature 111 records found  1 - 10nextend  jump to record: Search took 0.00 seconds. 
Liveness Detection on Touchless Fingerprint Scanner
Fořtová, Kateřina ; Kanich, Ondřej (referee) ; Heidari, Mona (advisor)
This Bachelor's Thesis is focused on liveness detection of fingerprints with using touchless sensor. Work summarizes theoretical introduction to biometrics, fingerprint processing and some of present researches for liveness detection. The new approach is introduced with using Local Binary Pattern algorithm, Sobel and Laplacian operator and Wavelet transform. Artificial Neural Networks, Support Vector Machines and Decision Trees were used for final classification. Several experiments with dataset illuminated by lights with various wavelengths were realized. It was discovered, that fingerprints illuminated by red light reached the best accuracy 90.1% compared to other considered wavelenghts of visible light. The classification with vector based on Local Binary Pattern achieved average accuracy 89.8%, accuracy with vector based on Sobel and Laplacian operator was 91.5%. Several Wavelet families were used for Wavelet transform during experiments. The best accuracy achieved wavelets of Biorthogonal spline wavelet family (85.1%) and wavelets from Reverse biorthogonal spline wavelet family (86.6%).
Finding The Fault Inception Time Using Wavelet Transform
Bukvisova, Zuzana
This paper deals with the transient detection method utilizing the wavelet transform, which proved to be more suitable for this purpose than the Fourier transform. The aim of this work is to analyze data, obtained from the power network model created in PSCAD software, and to determine the time of the fault inception. This calculated time is then compared with the actual fault inception time set in the model. The results show that the wavelet analysis can successfully detect all tested faults.
Comparison Of Heart Activity Sensing Devices
Babicová, Martina
The goal of this work is comparison of heart activity sensing devices. ECG record cannot be evaluated in the presence of large amounts of muscle noise. Removing this noise is one of the needs for devices success. The discrete wavelet transform is used to separate the useful and noise component. The result is an estimate of SNR for four devices: CorScience, Faros, BiosignalPlux, CardioSignal and a comparison between them. Quality measurement and evaluation indicates that Faros device is the most reliable.
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.
Comparison of heart activity sensing devices
Babicová, Martina ; Smital, Lukáš (referee) ; Smíšek, Radovan (advisor)
The goal of this work is comparison of heart activity sensing devices. However, an ECG record cannot be evaluated with the presence of muscle interference. Removing this noise is one of the needs for device success. The theoretical part represents electrophysiology of the heart, electrocardiography, various interferences types, theoretical basis for recording of biosignals including used devices and methods signal quality estimation. The practical part is SNR (signal-to-noise ratio) calculation. The Wavelet filter and Wiener filter-based wavelet domain are used to separate the useful and noise component.
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.

National Repository of Grey Literature : 111 records found   1 - 10nextend  jump to record:
Interested in being notified about new results for this query?
Subscribe to the RSS feed.