|
|
Evolutionary Optimization of the EEG Classifier Feature Extractor
Ovesná, Anna ; Hurta, Martin (referee) ; Mrázek, Vojtěch (advisor)
This work focuses on the optimisation of EEG signal classification of alcoholics and control subjects using evolutionary algorithms with a multi-objective approach. The main goal is to maximise the accuracy, sensitivity and specificity of the classification algorithm and minimise the number of features used. Four different classifiers are used, namely Support Vector Machine, k-nearest neighbors, Naive Bayes and AdaBoost. The selection of the best features is optimised using three different evolutionary approaches, two of which convert multi-objective optimisation to single-objective using weighted summation or restricting the maximum number of features. The Pareto optimal solutions are found by the NSGA-II algorithm. Results show that the evolutionary algorithms, combined with appropriate classifiers, reliably distinguish a person with a tendency to alcoholism from one with a healthy relationship towards alcohol.
|
|
|
General use of EEG sensors for mind controlled devices
Blažej, Svätopluk ; Sekora, Jiří (referee) ; Marcoň, Petr (advisor)
This bachelor thesis deals with various types of sensors for collection of EEG data and their application in mind-controlled devices. This work also deals with the issue of EEG signal measurement and its further analysis, how to choose the right sensor, and right design and construction of the device for data collection, amplification and filtration of the signal obtained by the selected sensor. Further, this project aims to develop software for translation (transformation) of the obtained data in order to enable communication and control of external devices.
|
|
|
The influence of deep brain stimulation on the brain connectivity
Horváthová, Ľubica ; Výtvarová, Eva (referee) ; Klimeš, Petr (advisor)
Hĺbková mozgová stimulácia (DBS) predstavuje účinnú liečbu pre pacientov s Parkinsonovou chorobou (PD) alebo farmakorezistentnou epilepsiou. Avšak mechanizmy, ktorými znižuje počet záchvatov a zlepšuje pohyb, zostávajú ešte do značnej miery neznáme. Pre lepšie pochopenie a určenie, v ktorých frekvenčných pásmach je zmena najdôležitejšia, boli urobené porovnania medzi vypnutou a zapnutou DBS pomocou korelačnej metódy a indexu fázového posunu. Jedenásť pacientov s PD a naimplantovanými neurostimulátormi z firiem Medtronic a St.Jude Medical bolo predmetom nahraných dát použitých v tejto práci. Výsledky dokazujú, že zmena konektivity počas DBS nastane a zároveň, že najviac ovplyvňuje najvyššie frekvencie ako beta, nízka gama a vysoká gama. Zmeny v týchto frekvenciách, zodpovedné za motorickú aktivitu, sústredenie a spracovanie informácií, sú v súlade s klinickou teóriou o PD. Počas tejto choroby je patologická beta aktivita hypersynchronizovaná a gama aktivita je znížená práve v motorických oblastiach. Ak sa gama aktivita počas zapnutej stimulácie zvyšuje, fyziologický stav pacientov sa čiastočne znovuobnovuje a tým zlepšuje ich hybnosť. Metódy a výsledky tejto práce budú použité pre ďalší výskum pacientov s PD a epilepsiou.
|
|
|
Sleep stages classification
Nováková, Kateřina ; Ronzhina, Marina (referee) ; Potočňák, Tomáš (advisor)
This work deals with the basic description of polysomnography, sleep morphology and sleep stages. Furtherly, some methods to process electroencephalographic signals are mentioned. Those processing methods are mainly focused on sleep stage classification. The practical part deals with the realization of three classification algorithms using artificial neural networks and verifying the functionality of these methods. All algorithms are designed in Matlab. Feature vectors for individual methods are obtained using energy values, Welch's spectral analysis and Hilbert-Huang Transform. For classification three types of artificial neural networks were used - layer recurrent network, feedforward network and pattern recognition network. On the basis of feature vectors, the sleep is divided into three stages - wakefulness (W), sleep without rapid eye movements (NREM) and sleep with rapid eye movements (REM).
|
|
|
EEG Signal Processing and Analysis
Uhliarik, Michal ; Drahanský, Martin (referee) ; Kupková, Karolína (advisor)
Tato práce se zabývá oblastí elektroencefalografie, zpracováním EEG signálů a jejich analýzou. Jsou vysvětleny základní principy vzniku biologických signálů v mozku, charakteristické mozkové vlny a jejich klasifikace. Dále práce ilustruje základní metodologie měření a záznamu těchto signálů, chyby měření, vliv a zdroje signálových artefaktů. Následně je rozebrána problematika předzpracování signálu, nejrozšířenější metodologie, jejich primární určení a teoretické podklady. Zároveň je obsažen i přehled metod pro analýzu EEG signálu v časové, frekvenční a časově-frekvenční oblasti. Jádrem práce jsou metody analýzy EEG signálu ve frekvenční oblasti, jsou uvedeny jejich teoretické podklady, omezení, odchylky a zaměření, jako i vhodné matematické aparáty pro kompenzaci uvedených nedostatků. Praktická část popisuje architekturu a implementaci aplikace Easy EEG Player, která vznikla jako součást téhle práce. Jsou popsány metody reprezentace, zpracováni a analýzy EEG dat za použití zvolených metodologií.
|
|
|
Electrical Activity Brain Mapping
Dobeš, Petr ; Drahanský, Martin (referee) ; Kupková, Karolína (advisor)
Electrical activity of human brain is one of the most significant signals of biological origin. In order to understand and interpret electroencephalogram (EEG signal) correctly, it is often necessary to perform its visualization. This bachelor thesis deals with EEG signal and its visualization using topographic mapping. The work includes the basics of theory and processing of EEG signal. Moreover, this work consists of design proposal and implementation of an application for topographic mapping of EEG signal obtained using Emotiv Epoc Headset device. Visualization is performed in real time (at the time of measurement). Visualized quantities are amplitude and frequency domain with the possibility to select frequency bands. Implemented application represents an alternative to the procedure when EEG signal has to be recorded and stored in order to perform its visualization.
|
|
| |
|
|
EEG signal measurement using acquisition PC card
Polák, Radek ; Kolářová, Jana (referee) ; Kolář, Radim (advisor)
The build preamplifier and the EEG Signal Measure Virtual Machine is the aim of this project. The abstract of actual clinical electroencefalography, the ways of measurement and processing of brain signals by clinical machines, and introducing my way of measure signal are placed in this work. The preamplifier has been designed for amplification of the brain signal, LabView virtual machine for maesurement and processing amplified signal.This project includes the measure output, the description of virtual machine, and the advice using of this product.
|
|
|
EEG signal measurement using acquisition PC card
Polák, Radek ; Sekora, Jiří (referee) ; Kolář, Radim (advisor)
This work deals with the design of the EEG amplifier and recording of the EEG signal using LabView and data acquisition card. The first art of theses describes the properties of the EEG signal and its origin. In the next part, the design of the 4 stage amplifier is described and simulated and measured frequency characteristics are presented. The last part describes the virtual instruments for EEG signal acquisition using LabView and data acquisition card PCI-NI6221.
|
|
|
Joint EEG-fMRI analysis based on heuristic model
Janeček, David ; Kremláček, Jan (referee) ; Labounek, René (advisor)
The master thesis deals with the joint EEG-fMRI analysis based on a heuristic model that describes the relationship between changes in blood flow in active brain areas and in the electrical activity of neurons. This work also discusses various methods of extracting of useful information from the EEG and their influence on the final result of joined analysis. There were tested averaging methods of electrodes interest, decomposition by principal components analysis and decomposition by independent component analysis. Methods of averaging and decomposition by PCA give similar results, but information about a stimulus vector can not be extracted. Using ICA decomposition, we are able to obtain information relating to the certain stimulation, but there is the problem in the final interpretation and selection of the right components in a blind search for variability coupled with the experiment. It was found out that although components calculated from the time sequence EEG are independent for each to other, their spectrum shifts are correlated. This spectral dependence was eliminated by PCA / ICA decomposition from vectors of spectrum shifts. For this method, each component brings new information about brain activity. The results of the heuristic approach were compared with the results of the joined analysis based on the relative and absolute power approach from frequency bands of interest. And the similarity between activation maps was founded, especially for the heuristic model and the relative power from the gamma band (20-40Hz).
|
guest ::
