|
|
Data Analysis and Clasification from the Brain Activity Detector
Ullrich, Petr ; Šůstek, Martin (referee) ; Szőke, Igor (advisor)
This thesis deals with the issue of recording brain activity, implementation of its processing, analysis and classification. The OpenBCI hardware is used for recording. I have studied and described necessary information about recording brain activity and OpenBCI project. Design for data set, data processing and thoughts classification was created. Created system allows classification based on recorded brain activity. The neural network was used for classfication, but the success of the recognition of designed classes was not high.
|
|
|
Analysis of Data to Solve Problems with Humidity in Buildings
Nečasová, Klára ; Korček, Pavol (referee) ; Kořenek, Jan (advisor)
The aim of this work was to solve problems with excessive humidity in buildings using data analysis. The theoretical part of the work deals with impacts of excessive humidity on the health of building occupants and also the condition of the building structure. Data mining methods including classification, prediction, and clustering are described together with model evaluation and selection. The practical part focuses on hardware platform description and measurement scenarios. Key parameters affecting indoor relative humidity are indoor and outdoor temperature and outdoor relative humidity. The long-term measurement of the mentioned parameters was performed using the set of sensors and BeeeOn system. Measured data was used to design a system for event detection related to a humidity change. The approach to air change regulation in the room was based on natural ventilation.
|
|
|
Material Artefact Generation
Rončka, Martin ; Španěl, Michal (referee) ; Kodym, Oldřich (advisor)
Ne vždy je jednoduché získání dostatečně velké a kvalitní datové sady s obrázky zřetelných artefaktů, ať už kvůli nedostatku ze strany zdroje dat nebo složitosti tvorby anotací. To platí například pro radiologii, nebo také strojírenství. Abychom mohli využít moderní uznávané metody strojového učení které se využívají pro klasifikaci, segmentaci a detekci defektů, je potřeba aby byla datová sada dostatečně velká a vyvážená. Pro malé datové sady čelíme problémům jako je přeučení a slabost dat, které způsobují nesprávnou klasifikaci na úkor málo reprezentovaných tříd. Tato práce se zabývá prozkoumáváním využití generativních sítí pro rozšíření a vyvážení datové sady o nové vygenerované obrázky. Za použití sítí typu Conditional Generative Adversarial Networks (CGAN) a heuristického generátoru anotací jsme schopni generovat velké množství nových snímků součástek s defekty. Pro experimenty s generováním byla použita datová sada závitů. Dále byly použity dvě další datové sady keramiky a snímků z MRI (BraTS). Nad těmito dvěma datovými sadami je provedeno zhodnocení vlivu generovaných dat na učení a zhodnocení přínosu pro zlepšení klasifikace a segmentace.
|
|
|
Classification of selected agricultural crops from time series of Sentinel-2 and PlanetScope imagery in Kutnohorsko model area
Kuthan, Tomáš ; Kupková, Lucie (advisor) ; Potůčková, Markéta (referee)
Classification of selected agricultural crops from time series of Sentinel-2 and PlanetScope imagery in Kutnohorsko model area Abstract The thesis is focused on the analysis of spectral characteristics of selected agricultural crops druring agriculutural season from time series of Sentinel -2 (A and B) and PlanetScope sensors in the model area situated around the settlements of Kolín and Kutná Hora. It is based on the assumption that the use of multiple dates of image data acquired crops in different phenological phases of the crops allows better identification of crop species (Lu et al., 2004). The aim of the thesis was to analyse the characteristics of the seasonal course of spectral features of selected agricultural crops (sugar beet, spring barley, winter barley, maize, spring wheat, winter wheat, winter rape) and to determine the period of the year suitable for the differentiation of individual crops. Another aim of the thesis was to classify these crops in the model area from time series of two above-mentioned sensors and to compare the accuracy of the pixel and object-oriented classification approach for multitemporal composites and the accuracy for monotemporal image from the term when the individual crops are clearly distinguishable. The training and validation datasets and the classification mask...
|
|
|
The application of atmospheric circulation classifications in the interpretation of climate model outputs
Stryhal, Jan ; Huth, Radan (advisor) ; Halenka, Tomáš (referee) ; Beranová, Romana (referee)
The application of atmospheric circulation classifications in the interpretation of climate model outputs Mgr. Jan Stryhal Automated (computer-assisted) classifications of atmospheric circulation patterns (circulation classifications, for short) constitute a tool widely used in synoptic and dynamic climatology to study atmospheric circulation and its link to various atmospheric, environmental, and societal phenomena. The application of circulation classifications to output of dynamical models of the atmosphere has developed considerably since the pioneering studies about three decades ago, reflecting rapid development in statistics, computing technology, and-naturally-climatological research, increasingly more and more dependent on simulations of the atmosphere, facing the paradigm of anthropogenic climate change. An uncoordinated use of various statistical approaches to analyzing output of global climate models (GCM) or their various ensembles, and an arbitrary selection of circulation variables, spatial and temporal domains, and reference datasets, have contributed to a need for a comparative study, which would shed some light on the sensitivity of studies dealing with an intercomparison of circulation classifications in two datasets to subjective choices. The present thesis responds to this need...
|
|
|
Introductoryprocessof formative assessment in elementaryschool EDUCAnet
Buršíková, Hana ; Mazáčová, Nataša (advisor) ; Sak, Petr (referee)
My Diploma Thesis "Process of the implementation of a formative assessment at the primary school EDUCAnet" deals with the possibilities of the school assessment and offers examples of the gradual change from the classical system to the formative evaluation. The theoretical part is aimed at the explanation of the basic terms connected with the assessment. It demonstrates different assessment methods and gradually specifies possibilities of the formative assessment. Practical part introduces assessment methods used at the primary school EDUCAnet. Final research summarizes EDUCAnet's students attitude to the assessment. To collect the data I used a questionnaire method, which is afterwards evaluated in graphs as well as in comments. The goal of my research is a detection of the formative assessment method, which is preferred by the students. In this context I am also interested in the motivation of the students and their understanding of the role of mistake in their education.
|
|
|
Tree species classification using sentinel-2 and Landsat 8 data
Havelka, Ondřej ; Štych, Přemysl (advisor) ; Kupková, Lucie (referee)
The main objectives of this master thesis are to evaluate and compare chosen classification algorithm for the tree species classification. With usage of satellite imagery Sentinel-2 and Landsat 8 is examined whether the better spatial resolution affects the quality of the resulted classification. According to past case studies and literature was chosen supervised algorithms Support Vector Machine, Neural Network and Maximum Likelihood. To achieve the best possible results of classification is necessary to find a suitable choice of parameters and rules. Based on literate was applied different settings which were subsequently evaluated by cross validation. All results are accompanied by tables, charts and maps which comprehensively and clearly summarize the answers to the main objectives of the thesis.
|
|
|
Neighborhood components analysis and machine learning
Hanousek, Jan ; Antoch, Jaromír (advisor) ; Maciak, Matúš (referee)
In this thesis we focus on the NCA algorithm, which is a modification of k-nearest neighbors algorithm. Following a brief introduction into classification algorithms we overview KNN algorithm, its strengths and flaws and what lead to the creation of the NCA. Then we discuss two of the most widely used mod- ifications of NCA called Fast NCA and Kernel (fast) NCA, which implements the so-called kernel trick. Integral part of this thesis is also a proposed algo- rithm based on KNN (/NCA) and Linear discriminant analysis titled TSKNN (/TSNCA), respectively. We conclude this thesis with a detailed study of two real life financial problems and compare all the algorithms introduced in this thesis based on the performance in these tasks. 1
|
|
|
Klasifikace na množinách bodů v 3D
Střelský, Jakub ; Mráz, František (advisor) ; Šikudová, Elena (referee)
Increasing interest for classification of 3D geometrical data has led to discov- ery of PointNet, which is a neural network architecture capable of processing un- ordered point sets. This thesis explores several methods of utilizing conventional point features within PointNet and their impact on classification. Classification performance of the presented methods was experimentally evaluated and com- pared with a baseline PointNet model on four different datasets. The results of the experiments suggest that some of the considered features can improve clas- sification effectiveness of PointNet on difficult datasets with objects that are not aligned into canonical orientation. In particular, the well known spin image rep- resentations can be employed successfully and reliably within PointNet. Further- more, a feature-based alternative to spatial transformer, which is a sub-network of PointNet responsible for aligning misaligned objects into canonical orientation, have been introduced. Additional experiments demonstrate that the alternative might be competitive with spatial transformer on challenging datasets. 1
|
|
|
Artificial neural networks for macroeconomic data analysis
Padrón Peňa, Ildefonso ; Mrázová, Iveta (advisor) ; Kuboň, David (referee)
The analysis and prediction of macroeconomic time-series is a factor of great interest to national policymakers. However, economic analysis and forecast- ing are not simple tasks due to the lack of a precise model for the economy and the influence of external factors, such as weather changes or political decisions. Our research is focused on Spanish speaking countries. In this thesis, we study dif- ferent types of neural networks and their applicability for various analysis tasks, including GDP prediction as well as assessing major trends in the development of the countries. The studied models include multilayered neural networks, recur- sive neural networks, and Kohonen maps. Historical macroeconomic data across 17 Spanish speaking countries, together with France and Germany, over the time period of 1980-2015 is analyzed. This work then compares the performances of various algorithms for training neural networks, and demonstrates the revealed changes in the state of the countries' economies. Further, we provide possible reasons that explain the found trends in the data.
|
guest ::
