National Repository of Grey Literature 459 records found  1 - 10nextend  jump to record: Search took 0.00 seconds. 
Visual experince as example and pattern in relation to the expansion and influence into human life
Nohejl, Jiří ; Wittlich, Filip (referee)
The main theme of this dissertation is to define an image as a visual experience. The human interaction is described by the author himself as a perception of the image, which serves as an information unit that could be presented as a possibility, example and pattern for the individual. There is an emphasis on the process of perception itself and on the way of interaction of an individual emphasizing the context of social learning and imitation in this text. The analysis of the principles of this interaction leading into introduction of the partial interactive models covering these processes is formed by the essential plane. The structure of the thesis is divided into ten main chapters in which the author tries to introduce a category of perception, a definition of the image and imitation as a tool of cultural transmission, presentation of the units of this transmission, the process of the interaction itself and analogous example of the fundamental role that a person in this interaction holds. There are also three analogies of these roles, which refer to the anthropological universal interaction describing the man as a gatherer and hunter. Their main purpose is to illustrate the form of a human experience better. Finally, there are reflections on the topic above. The possibilities and results, which...
Evaluation of forest vegetation based on time series of remote sensing data
Laštovička, Josef ; Štych, Přemysl (advisor) ; Brom, Jakub (referee) ; Bucha, Tomáš (referee)
Příloha k disertační práci: Abstrakt v AJ (Mgr. Josef Laštovička) Abstract This dissertation thesis deals with the study of forest ecosystems in the central Europe with the time series of multispectral optical satellite data. These forest ecosystems have been influenced by biotic and abiotic disturbances for the last decade. The time series of the satellite data with high spatial resolution allow the detection and analysis of forest disturbances. This thesis is mainly focused primally on free available Landsat and Sentinel-2 data, these two data types were compared. From methods, the difference time series analyses / algorithms were used. The whole thesis can be divided into two main parts. The first one analyses usability of classifiers for detection of forest ecosystems with per-pixel and sub-pixel methods. Specifically, the Neural Network, the Support Vector Machine and the Maximum Likelihood per-pixel classifiers were used and compared for different types of data (for data with high spatial resolution - Landsat or Sentinel-2; very high spatial resolution - WorldView-2) and for classification of protected forest areas. The Support Vector Machine were selected as the most suitable method for forest classifications (with most accurate outputs) from the list of selected per-pixel classifiers. Also, Spectral...
Segmentation and classification of LIDAR data
Dušek, Dominik ; Šorel, Michal (advisor) ; Obdržálek, David (referee)
The goal of this work was to design fast and simple methods for processing point-cloud-data of urban areas for virtual reality applications. For the visualization of methods, we developed a simple renderer written in C++ and HLSL. The renderer is based on DirectX 11. For point-cloud processing, we designed a method based on height-histograms for filtering ground points out of point cloud. We also proposed a parallel method for point cloud segmentation based on the region growing algorithm. The individual segments are then tested by simple rules to check if it is or it is not corresponding to a predefined object.
Deep Learning for MRI data
Karella, Tomáš ; Pilát, Martin (advisor) ; Blažek, Jan (referee)
The aim of the thesis is the classification of magnetic resonance images by Deep Learning models. The goal was to predict Alzheimer's disease on the dataset created by Alzheimer's Disease Neuroimaging Initiative (ADNI). To prepare the dataset, we built two processing pipelines, which align, normalise and remove irrelevant features from brain scans. We used the processed scans for a 2D and 3D dataset. We designed a few models based on convolutional and previously proposed architectures. Although, many studies published astonishing results on ADNI classification, the results of our experiments do not support previous research in this area. Contrary to what was previously thought, we found that the accuracy strongly depends on the dataset splitting. If we split the dataset by patients, not by scans, the accuracy drops significantly. We presented an overview of several previously published architectures and our experiments showing results of these architectures on the datasets generated by random splitting or subject-based splitting. We also pointed out how the dataset splitting choice changes the performance of our models. The work is a natural extension of study [Fung et al., 2019]. 1
Deep Neural Networks in Image Processing
Ihnatchenko, Luka ; Mrázová, Iveta (advisor) ; Pilát, Martin (referee)
The goal of this master thesis was to propose a suitable strategy to detect and classify objects of interest in mammogram images. A part of this goal was to implement an experimentation framework, that will be used for data preparation, model training and comparison. Patch and full-image versions of the dataset were used in the analysis. Initialisation with weights that were pretrained on the images from other domain improved classifier performance. ResNet-34 had better AUC scores on the test set that ResNet-18. Semi-supervised training using entropy minimisation has no significant improvement over the supervised one. The thesis includes the visualisation of the network predictions and the analysis of the knowledge representation of the classier. The achieved results for a patch version of the dataset are comparable to the results of another article that utilised the same test set. For a full-image dataset the results of the training were suboptimal. 1
Deep learning for tree line ecotone mapping from remote sensing data
Dvořák, Jakub ; Potůčková, Markéta (advisor) ; Lefèvre, Sébastien (referee)
Deep learning is growing in popularity in the remote sensing community, especially as a classification algorithm. First part of this thesis describes deep neural networks commonly used for remote sensing classification and their various applications. Capabilities of selected geospatial software suites in relation to deep models are also discussed in this part. Theoretical findings from the first part of the thesis are validated using two deep convolutional Encoder-Decoder networks - U-Net and its proposed adaptation called KrakonosNet. They are used to perform a sematic segmentation of spruce trees and dwarf pine shrubs in the tree line ecotone of the Krkonoše Mountains, Czechia. A normalised digital surface model is employed for creation of sufficiently large amount of training data, while the classification itself is performed using only optical imagery with very high spatial resolution. Resulting classification is compared to a set of traditional remote sensing classifiers, namely Maximum Likelihood, Random Forest, and a Support Vector Machine. Both U-Net and KrakonosNet significantly outperform the other classifiers on this dataset and will be consequently used in a related research project. Key words deep learning, U-Net, Krkonoše mountains, classification, vegetation mapping, picea abies,...
Blocky accumulation mapping from RPAS LiDAR and image data
Kolář, Michal ; Potůčková, Markéta (advisor) ; Dušánek, Petr (referee)
With merit of constant development in measuring technology it is possible to obtain data of high resolution and accuracy describing Earth's surface. During the project "Vegetation and Krkonoše tundra change detection method development by analyzing data from multispectral, hyperspectral and LiDAR UAV sensors" high quality data were acquired, with point density reaching up to 800 points/m2 and orthophoto of GSD 0.02 m. Data are capturing cryoplanation terraces in NE parth of Luční hora in three time periods: June, July and August 2019. The aim of this work is to devise a methodology of blocky accumulation mapping and evaluating detail of data. Key words: blocky accumulation, laser scanning, UAV, point cloud, orthophoto, segmentation
Classification of Czech sign language alphabet letters using cnn – preliminary study
Krejsa, Jiří ; Věchet, Stanislav
Abstract: The paper deals with the classification of Czech sign language single hand alphabet letters from static images using convolutional neural network (CNN). Proposed CNN architecture exhibits about 71% successful rate of classifying the letters signed by the person not included in the training data set.
Classification of Music Files Using Machine Learning
Sládek, Matyáš ; Smrčka, Aleš (referee) ; Janoušek, Vladimír (advisor)
This thesis is focused on classification of music files using machine learning algorithms. Seven classifiers were compared in this thesis, based on classification accuracy and speed. Two feature extraction methods, two feature selection methods and two parameter optimization methods were used. The best classifier proved to be XGBClassifier, which had reached accuracy of 87.56 % on dataset Extended Ballroom Dataset, 64.56 % on dataset FMA: A Dataset For Music Analysis and 83.50 % on dataset GTZAN. This model could be used for playlist creation or music database categorization.
Machine learning models for quantifying phenotypic signatures of cancer cells based on transcriptomic and epigenomic data
Koban, Martin ; PhD, Florian Halbritter, (referee) ; Mehnen, Lars (advisor)
S rozvojom techník pre efektívnu akvizíciu genomických dát sa jednou z kľúčových vedeckých výziev stala interpretácia výsledkov týchto experimentov v zmysluplnom biologickom kontexte. Táto práca sa zameriava na využitie informácií ukrytých v dobre charakterizovaných transkriptomických a epigenomických dátach z verejne dostupných zdrojov pre účely takejto interpretácie. Najskôr je vytvorený integrovaný súbor dát generovaných metódami DNase-seq a ATAC-seq, ktoré kvantifikujú chromatínovú dostupnosť. Tieto údaje sú doplnené verejne dostupnými výsledkami techniky RNA-seq pre kvantitatívne hodnotenie génovej expresie a vhodne predspracované pre ďalšiu analýzu. Pripravené dáta sú následne použité na trénovanie modelov strojového učenia (klasifikátorov) s dvomi základnými cieľmi. Po prvé za účelom augmentácie metadát prislúchajúcich k jednotlivým biologickým vzorkám v trénovacom dátovom súbore pomocou predikcie nedefinovaných anotácií. Po druhé pre anotáciu zle charakterizovaných testovacích dát (nepoužitých v trénovacej fáze) za účelom overenia generalizačnej schopnosti zostavených modelov. Dosiahnuté výsledky ukazujú, že natrénované klasifikátory sú schopné zachytiť biologicky relevantné informácie, zatiaľ čo vplyv technických artefaktov je minimalizovaný. Navrhnutý prístup je preto schopný prispieť k lepšiemu pochopeniu komplexných transkriptomických a epigenomických dát, predovšetkým v oblasti onkologického výskumu.

National Repository of Grey Literature : 459 records found   1 - 10nextend  jump to record:
Interested in being notified about new results for this query?
Subscribe to the RSS feed.