|
|
Multi-channel Methods of Speech Enhancement
Zitka, Adam ; Balík, Miroslav (referee) ; Smékal, Zdeněk (advisor)
This thesis deals with multi-channel methods of speech enhancement. Multichannel methods of speech enhancement use a few microphones for recording signals. From mixtures of signals, for example, individual speakers can be separated, noise should be reduced etc. with using neural networks. The task of separating speakers is known as a cocktail-party effect. The main method of solving this problem is called independent component analysis. At first there are described its theoretical foundation and presented conditions and requirements for its application. Methods of ICA try to separate the mixtures with help of searching the minimal gaussian properties of signals. For the analysis of independent components are used different mathematical properties of signals such as kurtosis and entropy. Signals, which were mixed artificially on a computer, can be relatively well separated using, for example, FastICA algorithm or ICA gradient ascent. However, difficult is situation, if we want to separate the signals created in the real recording enviroment, because the separation of speech people speaking at the same time in the real environment affects other various factors such as acoustic properties of the room, noise, delays, reflections from the walls, the position or the type of microphones, etc. Work presents aproach of independent component analysis in the frequency domain, which can successfully separate also recordings made in the real environment.
|
|
|
The use of EEG in assessing the emotional state of a person
Strakoš, Libor ; Mézl, Martin (referee) ; Potočňák, Tomáš (advisor)
This thesis is focused on EEG processing and emotion classification within two-dimensional emotion space. First part consists of theoretical research about emotional responses of human subjects on sound, image and video stimuli. Emotions are examined from aspect of physiology and psychology. Furthermore technical overview of measurement, analysis and emotion classification within two-dimensional emotional space is discussed. Based on gathered knowledge measurement setup with audiovisual stimuli was designed and measured with two independent instruments – EGI GES400MR in laboratory conditions and Emotiv EPOC device in non-laboratory conditions. Signals were processed and emotions were classified based on chosen features. Performance of classifiers in multiple feature selection setups was evaluated.
|
|
|
Noise and artifact suppression in fMRI data based on multi-echo data and independent component analysis
Pospíšil, Jan ; Gajdoš, Martin (referee) ; Mikl, Michal (advisor)
The main task of this work is to design an algorithm for suppressing unwanted noise and artifacts in fMRI data using the analysis of independent components and multi-echo data. The theoretical part deals with the basic principles of magnetic resonance, including construction and image data processing. The practical part presents a pilot design of a method inspired by a professional publication in the Matlab software environment, where this design is subsequently tested on real fMRI data provided by the Laboratory of Multimodal and Functional Imaging, CEITEC MU.
|
|
|
Face Detection and Identification
Konôpková, Júlia ; Drahanský, Martin (referee) ; Váňa, Jan (advisor)
This work is focused on the problematic of face detection and identification in photography. The introduction is devoted to the most popular methods with briefly descriptions of their principles and rules. Within the practical part of this work we implement and test on free available databases the several of these methods. In the conclusion we evaluate the results and addition of this whole work.
|
|
|
Time Frequency Analysis of ERP Signals
Bartůšek, Jan ; Provazník, Ivo (referee) ; Černocký, Jan (advisor)
Tato práce se zabývá vylepšením algoritmu pro sdružování (clustering) ERP signálů pomocí analýzy časových a prostorových vlastností pseudo-signálů získaných za pomocí metody analýzy nezávislých komponent (Independent Component Analysis). Naším zájmem je nalezení nových vlastností, které by zlepšily stávající výsledky. Tato práce se zabývá použitím Fourierovy transformace (Fourier Transform), FIR filtru a krátkodobé Fourierovy transformace ke zkvalitnění informace pro sdružovací algoritmy. Princip a použitelnost metody jsou popsány a demonstrovány ukázkovým algoritmem. Výsledky ukázaly, že pomocí dané metody je možné získat ze vstupních dat zajímavé informace, které mohou být úspěšně použity ke zlepšení výsledků.
|
|
|
Person Identification
Ťapuška, Tomáš ; Zuzaňák, Jiří (referee) ; Hradiš, Michal (advisor)
This master's thesis is about the most known methods for face recognition. There are described their advantages and disadvantages. This work is specialized at holistic methods for face recognition, which are working with 2D pictures of people. I implemented the automatic system for face recognition according to digital picture of face. There was, in this system, implemented these methods: KNN (K nearest neighbour), PCA (Principal component analysis) and LDP (Linear doscriminant projection). There was done some tests to compare implemented methods. The tests was done on the pictures from dataset FERET. In the conclusion of this text are considered implemented approaches and is marked the best method for face recognition from implemented.
|
|
|
Methods and algorithms for face recognition
Soukup, Jiří ; Heriban, Pavel (referee) ; Šťastný, Jiří (advisor)
This work is describing basic methods of face recognition. The methods PCA, LDA, ICA, trace tranfsorm, elastic bunch graph map, genetic algorithm and neural network are described. In practical part, the PCA, PCA + RBF neural network and genetic algorithms are implemented. The RBF neural network is used in the way of clasificator and genetic algorithm is used for RBF NN training in one case and for selecting eigenvectors from PCA method in the other case. This method, PCA + GA, called EPCA, outperform other methods tested in this work on the ORL testing database.
|
|
|
Human Sleep EEG Analysis
Sadovský, Petr ; Rozman, Jiří (advisor)
This thesis deals with analysis and processing of the Sleep Electroencephalogram (EEG) signals. The scope of this thesis can be split into several areas. The first area is application of the Independent Component Analysis (ICA) method for EEG signal analysis. A model of EEG signal formation is proposed and conditions under which this model is valid are examined. It is shown that ICA can be used to remove non-deterministic artifacts contained in the EEG signals. The second area of interest is analysis of stationarity of the Sleep EEG signal. Methods to identify stationary signal segments and to analyze statistical properties of these stationary segments are presented. The third area of interest focuses on spectral analysis of the Sleep EEG signals. Analyses are performed that shows the processes that form particular parts of EEG signals spectrum. Also, random signals that are an integral part of the EEG signals analysis are performed. The last area of interest focuses on elimination of the transition processes that are caused by the filtering of the short EEG signal segments.
|
|
|
Visualization and export outputs from functional magnetic resonance imaging
Přibyl, Jakub ; Gajdoš, Martin (referee) ; Slavíček, Tomáš (advisor)
Thesis discusses the principles and methodology for measuring functional magnetic resonance imaging (fMRI), basically the origin and use of BOLD signal types used experiments. Further attention is paid fMRI data processing and statistical analysis. Subsequent chapters are devoted to a brief description of the most common software tools used to analyze data from fMRI. The main section was to create a program in MATLAB with a detailed graphic user interface for easy visualization and export output from analyzes of fMRI data. The second half is devoted to describing the program developer and graphic user interface, including key functionality. The final section describes the application program with real data from clinical studies of dynamic connectivity and use in an international project APGem.
|
|
|
Reference signals in intracranial EEG: implementation and analysis
Uher, Daniel ; Hejč, Jakub (referee) ; Ronzhina, Marina (advisor)
The idea of a artifact-free brain activity recording has been circling around the scientific world for a few decades. Parasitic phenomenons and unwanted components may significatntly complicate the analysis of intracranial electroencephalographic (iEEG) recordings. However, with the rise of modern technology, new methods for precise removal of noise artifacts started to emerge. Here we use the concept of virtual reference signals for the elimination of such unwanted components. In this work, the algorithms for reference signal estimation using common average based method as well as more recent methods based on independent component analysis (ICA) were realized and evaluated on a variety of iEEG data. It was found that the ICA-based algorithms allow obtaining more accurate estimation of the reference signal as compared to the average-based one. Finally, all the methods were implemented into a open-source Python package đť‘źđť‘’đť‘“đť‘ đť‘–đť‘”, which is publicly available, easy to install and ready to use.
|
guest ::
