|
| |
|
|
Sleep scoring using artificial neural networks
Vašíčková, Zuzana ; Mézl, Martin (referee) ; Králík, Martin (advisor)
Hlavným cieľom semestrálnej práce je vytvorenie umelej neurónovej siete, ktorá bude schopná roztriediť spánok do spánkových epoch. Na začiatku je uvedené zhrnutie informácií o spánku a spánkových epochách. V ďalších kapitolách sa nachádza dôkladnejší prehľad metod na spracovávanie signálov a na klasifikáciu. Po zhrnutí teoretických znalostí potrebných na uskutočnenie praktickej časti práce boli na základe tohto rozboru vypočítané zo signálov potrebné znaky. Tieto znaky boli podrobené štatistickej analýze a na jej základe boli vybrané niektoré znaky, ktoré boli vhodné ako vstup do neurónovej siete, ktorá je po naučení schopná triediť spánkové epochy do príslušných fáz.
|
|
|
Obstructive sleep apnea detection using polysomnography
Smrčková, Markéta ; Mézl, Martin (referee) ; Králík, Martin (advisor)
This thesis attempts to find an alternative method for automatic detection of sleep apnea using polysomnographic data. The first part is focused on introduction to lungs anatomy and physiology of breathing, sleeping and cardiac system. The second part describes the process of sleep examination and particular components of polysomnographic data. The third part is focused on realization of specific method for sleep apnoea detection, application on real data and results evalutation.
|
|
|
Analysis of intracardiac electrogram of heart arrthytmias in the spectral domain
Karlíková, Adéla ; Králík, Martin (referee) ; Mézl, Martin (advisor)
The most important aspect of successful ablation and destruction of arrhythmia is to find the place where arrhythmia spreads. The site of initial activation can be found by conventional or complex techniques. This thesis describes a new conventional method that can also be applied in practice. It was found that the closer is catheter to the place of the initial activation the more dominant frequency shifts to the higher values. We will use this fact in creating an algorithm which will compare frequency values in the frequency spectrum. This algorithm will also assess how far is the catheter located from the site of the origin of the arrhythmia. In the conclusion of the thesis is an evaluation of the measured clinical data and a comparison of the effectiveness of the method.
|
|
|
Multichannel EMG signal processing for gesture recognition
Brázdil, Štěpán ; Králík, Martin (referee) ; Harabiš, Vratislav (advisor)
This work deals with the complex solution of the problem concerning the design and implementation of the system for the collection, classification and visualization of EMG signal. The thesis is designed with respect to possible future applications like implementation of a real limb model controlled by the proposed system. In the introductory part the theoretical knowledge of EMG signal generation and sensing possibilities, including the anatomical structure of the upper limb, are revealed. In the other parts, the possible realization of measurements using the BITalino system and the use of data processing and classification using the Matlab program are discussed. The output of this work is a functional program code that allows visualization of upper limb gestures in the graphical user interface.
|
|
| |
|
|
Analysis of Secondary School Pupils' Knowledge and the Interpretation of Evolutionary Biology by Teachers in the Czech Republic, England and Scotland
Hlaváčová, Lucie ; Teodoridis, Vasilis (advisor) ; Králík, Miroslav (referee) ; Švecová, Milada (referee)
An evolution is considered the single greatest unifying theory in biology. Therefore, evolution is a crucial topic from the perspective of didactics of biology because it reaches contemporary paradigm of science education. These doctoral thesis deals with the educative aspects in the field of evolutionary biology. Given the fact that educational content and understanding of causal patterns in science may be influenced by the sociocultural background, the whole research is carried out in comparison with Great Britain. The main aim of the thesis is carried out three successive analyzes. First, the occurrence and the content of definitions of evolutionary terms in Czech and British science or biology textbooks have been compared (16 Czech and 16 British textbooks). Data were evaluated using content analysis and hierarchical cluster analysis. Subsequently, a comparison of teaching evolution has been made using a questionnaire survey (350 Czech and 122 British teachers) and interviews (10 Czech and 7 British teachers). Finally, a comparison of the Czech and British pupils' knowledge and opinions on specific evolutionary topics were obtained via a questionnaire (964 Czech and 97 British pupils). Statistically significant differences between Czech and British respondents were verified by Chi-square test...
|
|
|
Heart rate variability analysis from sleep ECG
Lepková, Kamila ; Kozumplík, Jiří (referee) ; Králík, Martin (advisor)
This bachelor thesis deals with an analysis of heart rate variability from sleep ECG. The thesis is divided into two parts, the first one is theoretical part and describes the physiology of heart and respiratory system, ECG curve, sleeping phases, apnea, and above all analysis of heart rate variability of ECG. In the practical part, using MATLAB software, was developed an algorithm of the analysis. The algorithm was tested on real signals from a publicly accessible database. The difference between the physiological ECG and the ECG with apnea is statistically evaluated using sing parameters from the time and frequency domain. Kruskal-Wallis statistic test confirms that there is a significant difference between the physiological signal and the apnea signal.
|
|
|
Sleep stage classification
Lacinová, Michaela ; Smital, Lukáš (referee) ; Králík, Martin (advisor)
This bachelor thesis deals with analysis of polysomnography and its methods of measurement in electroencephalography, electromyography and electrooculography in the first part. It comprises an analysis of sleep stages recommended by the AASM. Polysomnographic data are further analysed in the domains of time and frequency, which are evaluated separately. In the second part the data are classified into particular classes using methods of decision trees and k-nearest neighbours in the MATLAB programming environment. These data are evaluated and compared with available literature.
|
|
|
Heart Sounds Detector
Hlaváčová, Kristýna ; Králík, Martin (referee) ; Kozumplík, Jiří (advisor)
In this thesis deals with detection of heart sounds in signal. In first half of thesis is discussed anatomy, physiology of cardiovascular system and issue of heart sounds. Afterwards, devices for evalution phonocardigram signals and their analysis are described. Thereafter the work focuseson the algorithm for detection of the first and second heart sound, which was implemented in the MATLAB R2014a environment. In conclusion, there is a summary of the proposed method and statistic evaluation.
|
guest ::
RSS feed.