|
|
Neural networks used in autonomous vehicles
Ryšavý, Jan ; Píštěk, Václav (referee) ; Kučera, Pavel (advisor)
This bachelor thesis deals with the use of neural networks in autonomous vehicles. The first part of the thesis presents the basic principles of neural networks and learning methods that are used in autonomous vehicles. Then the thesis describes the architecture and functions of neural networks. The second part of the thesis also describes the different types of autonomous vehicles, their classifications and an overview of the sensors used by autonomous vehicles. The last part of the thesis deals with the implementation of neural networks in ECUs using programming languages and libraries, and applications such as object detection and marker recognition.
|
|
|
DEEP LEARNING FOR SINGLE-VOXEL AND MULTIDIMENSIONAL MR-SPECTROSCOPIC SIGNAL QUANTIFICATION, AND ITS COMPARISON WITH NONLINEAR LEAST-SQUARES FITTING
Shamaei, Amirmohammad ; Latta,, Peter (referee) ; Kozubek, Michal (referee) ; Jiřík, Radovan (advisor)
Pro získání koncentrace metabolitů ve vyšetřované tkáni ze signálů magnetické rezonanční spektroskopie (MRS) je nezbytné provézt předzpracování, analýzu a kvantifikaci MRS signálu. Rychlý, přesný a účinný proces zpracování (předzpracování, analýza a kvantifikace) MRS dat je však náročný. Tato práce představuje nové přístupy pro předzpracování, analýzu a kvantifikaci MRS dat založené na hlubokém učení (DL). Navržené metody potvrdily schopnost použití DL pro robustní předzpracování dat, rychlou a efektivní kvantifikaci MR spekter, odhad koncentrací metabolitů in vivo a odhad nejistoty kvantifikace. Navržené přístupy výrazně zlepšily rychlost předzpracování a kvantifikace MRS signálu a prokázaly možnost použití DL bez učitele. Z hlediska přesnosti byly získány výsledky srovnatelné s tradičními metodami. Dále byl zaveden standardní formát dat, který usnadňuje sdílení dat mezi výzkumnými skupinami pro aplikace umělé inteligence. Výsledky této studie naznačují, že navrhované přístupy založené na DL mají potenciál zlepšit přesnost a efektivitu zpracování MRS dat pro lékařskou diagnostiku. Disertační práce je rozdělena do čtyř částí: úvodu, přehledu současného stavu výzkumu, shrnutí cílů a úkolů a souboru publikací, které představují autorův přínos v oblasti aplikací DL v MRS.
|
|
|
Segmentation of Electrocardiographic Signals Using Deep Learning Methods
Hejč, Jakub ; Černý, Martin (referee) ; Halámek, Josef (referee) ; Kolářová, Jana (advisor)
The thesis deals with deep learning methods for the segmentation of surface and intracardiac electrocardiographic recording with focus on atrial activity. The theoretical part introduces current segmentation aproaches of electrocardiographic signals. Issues related to the development of deep learning models in context of standard ECG databases were also discussed. We proposed a pipeling for processing multimodal electrophysiology data from interventional procedures in order to build reliable training datasets. A deep model for segmentation of intracardiac recordings based on a modified residual architecture was proposed. A series of experiments was conducted to evaluate the effect of both model and dataset properties on segmentation quality. The annotation methodology of recordings with atrial fibrillation proved to be a crucial factor. Properties of loss function and type of data augmentation were revealed as secondary important parameters. A novel P wave segmentation method for incomplete references was proposed in the thesis. The approach was inspired by the deep contrast learning. It was modified to distinguish local segments of signals at different levels of abstraction of the extracted feature maps. Results were analyzed using standard quality metrics and post-hoc visual analysis. In some cases, a statistical comparison of experiments for different settings was performed. The results of the work showed that it is possible to use intracardiac signals for embedding a vector representation of local atrial activation into deep models.
|
|
|
Automatic diagnosis of the 12-lead ECG using deep learning
Blaude, Ondřej ; Smital, Lukáš (referee) ; Provazník, Valentine (advisor)
The aim of this diploma thesis is to investigate the problematics of automatic ECG diagnostics, namely on twelve-lead recordings. In the first chapter the heart and its electrical activity measurement is described shortly. In addition to that, the abnormalities which are going to be classified in this thesis are also briefly described. In the second chapter, it is described how the ECG was diagnosed earlier, by classical methods that preceded deep learning. Some of the shortcomings that the classical methods have compared to deep learning are also described here. The third part already pays attention to deep learning itself, and its contribution and advantages compared to classical methods. Convolutional neural networks and their individual blocks are also described here, later attention is paid to selected architectures that were used in some studies. The fourth chapter already focuses on the practical part, in which the data used from the PhysioNet database, the proposed algorithm and its implementation are described in more detail. In the fifth chapter the results are discussed and compared to the corresponding publications.
|
|
|
Deep Learning for Image Stitching
Šilling, Petr ; Beran, Vítězslav (referee) ; Španěl, Michal (advisor)
Sešívání obrázků je klíčovou technikou pro rekonstrukci objemů biologických vzorků z překrývajících se snímků z elektronové mikroskopie (EM). Současné metody zpracování snímků z EM k sešívání zpravidla využívají ručně definované příznaky, produkované například technikou SIFT. Nedávný vývoj však ukazuje, že konvoluční neuronové sítě dokáží zlepšit přesnost sešívání tím, že se naučí diskriminativní příznaky přímo z trénovacích obrázků. S ohledem na potenciál konvolučních neuronových sítí tato práce navrhuje sešívací nástroj DEMIS, který staví na pozornostní síti LoFTR pro hledání shodných příznaků mezi páry obrázků. Dále práce navrhuje novou datovou sadu generovanou dělením obrázků z EM s vysokým rozlišením na pole překrývajících se dlaždic. Výsledná datová sada je použita pro dotrénování sítě LoFTR a k vyhodnocení nástroje DEMIS. Experimenty na dané datové sadě ukazují, že nástroj je schopen nalézt přesnější shody mezi příznaky než SIFT. Navazující experimenty na obrázcích s vysokým rozlišením a malými překryvy mezi dlaždicemi dále poukazují na výrazně vyšší robustnost oproti metodě SIFT. Dosažené výsledky celkově naznačují, že hluboké učení může vést k prospěšným změnám v oblasti EM, například k umožnění menších překryvů mezi snímanými obrázky.
|
|
|
Advanced sleep quality estimation
Benáček, Petr ; Ředina, Richard (referee) ; Filipenská, Marina (advisor)
This thesis deals with the assessment of sleep quality using modern deep learning methods. The thesis describes metrics for automatic classification of sleep stages. A selected database of sleep data is discussed. Due to the low number of data in the wakefulness phase, different methods of data augmentation are described and implemented. Models based on 1D convolutional networks are the basis for the classification. As a result, models for binary classification and classification of 3 and 4 sleep phases are prepared. Finally, sleep quality metrics are calculated using these models and the results are compared with the literature.
|
|
|
Deep Learning in Historical Geography
Vynikal, Jakub ; Pacina, Jan
In relation to the rapid development of artificial intelligence, the possibilities of automatic processing of spatial data are increasing. Scanned topographical maps are a valued source of historical information. Neural networks allow us to extract information quickly and efficiently from such data, eliminating the difficult and repetitive work that would otherwise have to be done by a human. The article presents two case studies exploring the possibilities of using deep learning in historical geography. The first one is concerned with detecting and extracting swamps from topographic maps, while the second one attempts to automatically vectorize contours from the State Map 1 : 5 000
|
|
|
Detection of cells in confocal microscopy images
Hubálek, Michal ; Štursa, Dominik (referee) ; Škrabánek, Pavel (advisor)
The goal of the thesis was to create an application that automatically detects healthy cardiomyocytes from images captured by a confocal microscope. The thesis was created based on the specific needs of researchers from the Slovak Academy of Sciences.The application will facilitate and increase the efficiency of their research,because until now they have to evaluate the images and search for suitable cells manually. The RetinaNet convolutional neural network is used for detection and has been implemented in a user-friendly desktop application. The application also automatically records and stores coordinates of detected cells which can be used for capturing cells in higher image quality. Another advantage of the developed application is its versatility, which allows to train detection on other data, making it applicable to other projects. The result of this work is a functional, standalone and intuitive application that is ready to be used by researchers.
|
|
|
A convolutional neural network for image segmentation
Mitrenga, Michal ; Petyovský, Petr (referee) ; Jirsík, Václav (advisor)
The aim of the bachelor thesis is to learn more about the problem of convolutional neural networks and to realize image segmentation. This theme includes the field of computer vision, which is used in systems of artificial intelligence. Special Attention is paid to the image segmentation process. Furthermore, the thesis deals with the basic principles of artificial neural networks, the structure of convolutional neural networks and especially with the description of individual semantic segmentation architectures. The chosen SegNet architecture is used in a practical application along with a pre-learned network. Part of the work is a database of CamVid images, which is used for training. For testing, a custom image database is created. Practical part is focused on CNN training and searching for unsuitable parameters for network learning using SW Matlab.
|
|
|
Advanced scoring of sleep data
Jagošová, Petra ; Novotná, Petra (referee) ; Ronzhina, Marina (advisor)
The master´s thesis is focused on advanced scoring of sleep data, which was performed using deep neural network. Heart rate data and the movement information were used for scoring measured using an Apple Watch smartwatch. After appropriate pre-processing, this data serves as input parameters to the designed networks. The goal of the LSTM network was to classify data into either two groups for sleep and wake or into three groups for wake, Non-REM and REM. The best results were achieved by network doing classification of sleep vs. wake using the accelerometer. The statistical evaluation of this best-designed network reached the values of sensitivity 71,06 %, specificity 57,05 %, accuracy 70,01 % and F1 score 81,42 %.
|
guest ::
