|
|
Evolutionary Design of EEG Data Classifier
Kuželová, Simona ; Jawed, Soyiba (referee) ; Mrázek, Vojtěch (advisor)
Tato diplomová práce se zaměřuje na vývoj efektivního klasifikátoru pro klasifikaci kandidátů na základě extrahovaných vlastností z elektroencefalografického (EEG) signálu. K dosažení tohoto cíle byl použit genetický algoritmus pro výběr příznaků a optimalizaci klasifikátorů na základě pěti kritérií: minimalizace počtu příznaků, minimalizace doby inference a maximalizace klasifikační senzitivity, specificity a přesnosti. Pro extrakci příznaků s cílem klasifikovat kandidáty jako trpící MDD, nebo jako zdravé, byla použita EEG data s otevřenýma očima 31 kandidátů trpících depresivní poruchou (MDD) a 28 zdravých kandidátů. Byly otestovány dva algoritmy, NSGA-II a NSGA-III. Navržený algoritmus pracoval se třemi kritérii, ale byly přidány dvě další kritéria - senzitivita a specificita. NSGA-III byl v tomto případě účinnější a byl použit v následujících experimentech. Byla zavedena omezení pro zlepšení parametrů a byly vyzkoušeny různé hodnoty pro pravděpodobnost mutace a křížení. Vygenerované klasifikátory dosáhly průměrné přesnosti 91.36 \%, senzitivity 91.82 \% a specificity 90.84 \%. V závěrečných experimentech byly nejčastěji používány kanály F3 a C3 a nejčastěji využívaným vlnovým pásmem byla gama frekvence. Výsledkem této práce jsou efektivní klasifikátory, které byly získány pomocí navrženého algoritmu, jenž využívá genetický algoritmus pro optimalizaci parametrů.
|
|
|
Artefacts Removal from Brain EEG Signals Using Adaptive Algorithms
Hatala, Juraj ; Jawed, Soyiba (referee) ; Shakil, Sadia (advisor)
Tato práce se zabývá problémem artefaktů ve záznamech elektroencefalografie (EEG) a metodami jejich odstranění s důrazem na adaptivní filtrace. Artefakty jsou neodmys- litelnou součástí metody EEG a negativně ovlivňují analýzu výsledků tím, že překrývají zájmové mozkové signály. Adaptivní filtrace je všestrannou metodou, kterou lze použít pro odstranění těchto artefaktů, pokud je k dispozici referenční signál korelovaný s arte- faktem. Hlavním cílem této práce je návrh a implementace frameworku, který umožní aplikaci metod adaptivní filtrace na EEG data. Druhotným cílem je posouzení účinnosti nového algoritmu Q-LMS při odstraňování artefaktů z EEG, protože dosud nebyl v tomto scénáři použit. Práce představuje knihovnu v prostředí Python pro adaptivní filtrace EEG a ukazuje a hodnotí experimenty pro scénáře odstraňování artefaktů s použitím Q-LMS fil- tru implementovaného v navržené knihovně. V této knihovně je uživatel schopen vytvářet přizpůsobitelné filtrační pipeliny. Knihovna nabízí různé adaptivní filtry a metody vytváření referenčního signálu s důrazem na zpracování neurologických dat ve formátu BIDS. Uži- vatel však může sdílet vlastní filtry s frameworkem a také používat vlastní vstupní data a referenční signály. Experimenty s Q-LMS algoritmem ukázaly, že se jedná o dobře fun- gující adaptivní algoritmus, avšak výsledky filtrace byly průměrný ve srovnání s výsledky dosaženými jinými standardními adaptivními algoritmy
|
|
|
EEG Classification Model for Emotion Detection Using Python
Vengerová, Veronika ; Zaheer, Muhammad Asad (referee) ; Jawed, Soyiba (advisor)
Táto práca sa zaoberá rozoznávaním emócií z elektroencefalogramu (EEG). Dva modely na binárnu klasifikáciu emócií, kde jeden model klasifikuje neutrálnu emóciu alebo strach a druhý šťastie a smútok. Počas práce boli vyskúšané mnohé rôzne architektúry, pričom najlepšie výsledky boli dosiahnuté modelom pozostávajúcim z dvoch vetiev KNN-LSTM spojenými pred výstupnou vrstvou. Výsledná presnosť bola 87.309% na klasifikáciu šťastia a smútku a 84.865% na klasifikáciu neutrálnej emócie a strachu.
|
|
|
Implementation of new method to machine learning model for epileptogenic zone localization in pharmacoresistant epilepsy patients
Pivnička, Martin ; Mívalt, Filip (referee) ; Filipenská, Marina (advisor)
The bachelor thesis describes the issue of the epileptogenic tissue localization considering pacients with drug-resistant epilepsy. The first half of the theoretical part discusses the matter of epilepsy and its treatment. It describes the principle of electroencephalographic measurement and its contribution to epileptology as well as multiple foci localization approaches. The second theoretical part shows machine learning basics and its use for epilepsy treatment. The practical part starts with the description of steps needed to create the gamma method. It continues with the statistical analysis of the method. This analysis contains both gamma method alone and as a part of existing machine learning algorithm. It has been shown that the gamma method is a valuable specific parameter for localizing epileptic foci. Its addition to the machine learning model did not lead to a significant improvement in the performance of the model.
|
|
|
Toolbox for automatic EEG data quality assessment
Meloun, Jan ; Gajdoš, Martin (referee) ; Lamoš, Martin (advisor)
This thesis deals with the design of a tool for the automatic evaluation of EEG data quality. The theoretical part of the thesis contains a description of the formation and propagation of the action potential through the nervous system. Furthermore, a theoretical description of the EEG recording and its artifacts. The following is a description of the methods used to detect artifacts. In the practical part of the thesis, there is a description of the design of the tool for automatic EEG quality assessment, including a discussion of the results based on the provided data.
|
|
|
The influence of morphometric changes of gray and white matter on brain functional connectivity in schizophrenia
Görnerová, Natálie ; Horáček, Jiří (advisor) ; Zach, Petr (referee) ; Filip, Pavel (referee)
More than a century has passed since a clear definition for schizophrenia was established, yet, the etiology, neuropathological and pathophysiological mechanisms of this psychiatric disorder still, to a large extent, remain to be elucidated. In the theoretical part of this dissertation, we review current classification and pathophysiology of schizophrenia, paying a particular attention to the findings from structural and functional imaging techniques. These techniques demonstrate that patients with schizophrenia tend to have reduced volume of grey matter, reduced integrity of white matter and a disrupted inter-regional functional connectivity (FC). The temporal association between structural changes, already detectable on imaging before symptoms appear, and development of disrupted FC remains to be uncovered. At the same time, current knowledge does not fully explain the link between disrupted FC and disturbed experience of self-awareness, a core symptom of schizophrenia. In addition, it is necessary to develop novel effective methods to prevent relapse and prevent the progression of neurobiological changes in the brain. In the practical part of this dissertation, we designed a study with three different groups of subjects aiming to fulfil three key aims that would help us to fill the gaps in...
|
|
|
Neurofeedback and effectiveness of its therapeutic application
VOSPĚLOVÁ, Tereza
This theoretical bachelor thesis introduces neurofeedback, development of its research and its associated areas. It also deals with assessment of effectiveness of therapeutic use in the area of ADHD, epilepsy, specific learning difficulties, Autism Spectrum Disorders, anxiety disorders, OCD, depressive disorders, sleeping disorders, post-traumatic stress disorder and improving the performance. The assessment altogether involves 27 studies and 2 meta-analysis from several databases such as PubMed, Google Scholar, EBSCO, Sciencedirect, PsycNet and ResearchGate. Randomized controlled trials consisting of primal empiric data (except for 2 meta-analysis), which were published in English, Czech or Slovak language or their publishing is about to be done, were incorporated. According to the available results, it wasn't possible to affirm the highest level of the effectiveness, and the treatment using the neurofeedback is characterised as probably efficacious. The work summarizes many methodological imperfections found in examined sources and stresses the importance of their elimination for the future research, so it might be possible to find and prove specific influencing factors.
|
|
|
ERP correlates of valence in affective priming
MEŠKANOVÁ, Michaela
The bachelor thesis, ERP (event-related potentials) correlates of the valence in affective priming, deals with the affective priming from the point of view of the event related potentials processing by electroencephalography, when it is used experimental presentations with different valence and arousal levels. The aim of this thesis is the approaching of the auditory priming effect on the visual processing impulse. This bachelor thesis is divided into theoretical and practical part, where the theoretical part deals with the general principles of the affective priming, emotions and electroencephalography method, including ERP component. The empirical part deals with the experiment, whose aim was description of the auditory priming effect on the affective processing target by the ERP components. Twenty six respondents took part in the experiment. They saw a presentation made in OpenSesame programme in the total length of sixty minutes. The neural data were scanned from the head scalp by the device Biosemi ActiveTwo with 64 electrodes. In the final processing there were 19 measured samples. After the final processing, I analysed 8 graphs displaying ERP curved lines of the relevant electrodes both the high-arousal and low-arousal processing target level. In the comparison with the studies not including affective auditory priming, all given hypothesis were approved. The final discussion summarizes all possible restrictions that could influence acceptance of the alternative hypothesis.
|
|
|
EEG correlates of egocentric and allocentric distance estimates in virtual environment in humans
Kalinová, Jana ; Vlček, Kamil (advisor) ; Telenský, Petr (referee)
Cognitive processes associated with spatial orientation can use different reference frames: egocentric, centered on observer and allocentric, centered on objects in the environment. In this thesis, we use EEG to investigate the dynamics of brain processes accompanying spatial orientation based on these reference frames. Participants were instructed to estimate distances between objects or themselves and objects located in a virtual circular arena; this task was presented in both 2D and 3D displays. Task-related EEG changes were analyzed using a time-frequency analysis and event-related potential analysis of 128-channel EEG recordings. Through time-frequency analysis we found significant power differences in delta, theta, alpha, beta and gamma bands amongst the control, egocentric and allocentric testing conditions. We noted a decrease in alpha power in occipital and parietal regions, while a significantly stronger decrease was observed for the allocentric condition compared to both egocentric and control conditions. A similar pattern was also detectable for the beta band. We also report an increase in theta and delta power in temporal, fronto-temporal and lateral frontal regions that was significantly stronger for the egocentric condition compared to control and, in some electrodes, even...
|
|
|
Controlling a Virtual Robot Using a Hybrid Brain-Computer Interface with Visual and Auditory Cues
Prášil, Matěj ; Hrubý, Martin (referee) ; Tinka, Jan (advisor)
This work deals with the control of a virtual robot using a hybrid interface between the brain and a computer in response to visual and auditory evoked potentials, EEG signal analysis and processing. OpenBCI hardware is used for scanning. I studied the methods needed for signal processing and designed applications. The output is two applications, one for controlling a virtual robot and the other for signal processing and classification. The average accuracy of signal classification on real data is low, only 22.35%
|
guest ::
