Land cover classification using artificial neural networks Abstract This Diploma thesis deals with automatic classification of the satellite high spatial resolution image in the field of land cover. The first half of the work contains the theoretical information about remote sensing and classification methods. The biggest attention is given to the artificial neural networks. In practical part of Diploma thesis are these methods used for the classification of SPOT satellite image. Keywords: remote sensing, image classification, artificial neural networks, SPOT

Classification of airborne laser scanning data using information about intensity and width of the recorded signal Abstract One of the basic tasks in analysing airborne laser scanning (ALS) data is filtration of mass 3D point cloud with purpose to create digital terrain model and digital surface model. New scanner generation (so called Full-waveform LiDAR) allows analysing the whole recorded signal. The recorded value of amplitude and signal width accordant with reflectance of different objects differs according to geometry of the objects. Objective of this thesis is to create a methodology for classification of ALS data in settled areas. This methodology will be based on number of reflections, amplitude of reflected signal, recorded signal width and on spatial attributes. At the same time it will be analysed how the parameters of amplitude and signal width are affected by characteristics of estate surface. It means which radiometrical characteristics (e.g. different roof materials) and geometrical characteristics (e.g. different roof inclination) belong to which amplitude and signal width. Basic question of this thesis is if amplitude and signal width are good attributes to improve the quality of filtration of mass 3D point cloud in chosen area and if so, how. Key words: classification, segmentation, LiDAR,...

Title of thesis: Inclusion on the ground fighting techniques in the system of close combat in the Army of the Czech Republic. Aim of thesis: The aim of this study is to evaluate the effectiveness of termination, the risk of injury and severity of selected techniques of fighting on the ground in order to create a theoretical model for the incorporation of new techniques into close combat training in the Army of the Czech Republic. Methods: This thesis is processed by multivariate preferences. IAC group of senior mentors and close combat instructors evaluated using a printed questionnaire completion efficiency, risk of injury and severity of the performance of six combat techniques on the ground in design with no weapon and then in the version with weapons (assault with a knife during the implementation techniques) marks 1 "worst" to 3 "best". To summarize the evaluation I used tables showing the frequency of individual signs and then multiply the resulting frequency value equal to the value of the mark, below which the frequency is. The data obtained from the product of the frequency and the added values allowed us to compare techniques between themselves and determine their mutual order. Results: Despite the chosen criteria evaluated for divergence of selected techniques and access to the results...

Title: Construction of classifiers suitable for segmentation of clients Author: Bc. Jana Hricová Department: Department of Probability and Mathematical Statistics Supervisor: prof. RNDr. Jaromír Antoch, CSc., Department of Probability and Mathematical Statistics Abstract: The master thesis discusses methods that are a part of the data analy- sis, called classification. In the thesis are presented classification methods used to construct tree like classifiers suitable for customer segmentation. Core methodo- logy that is discussed in our thesis is CART (Classification and Regression Trees) and then methodologies around ensemble models that use historical data to cons- truct classification and regression forests, namely Bagging, Boosting, Arcing and Random Forest. Here described methods were applied to real data from the field of customer segmentation and also to simulated data, both processed with RStudio software. Keywords: classification, tree like classifiers, random forests

Titel: Evolution and current state of combatives systems in Prague Goals: The purpose of this work is to present current state of combatives systems in Prague (Prague 4, 5, 6), to focus on data collecting of selected devisions, to create a list of these devisions together with the map of their locations. To process statistically all obtained data and to answer research hypotesis and questions. To delineate shortly the current state of works out comes on same purpose, which were processed in Moravia. Methods: Literature and electronic sources studying. Data collecting by questionnaires sent to heads of devisions. Answering the questions during phone calls or meetings. Informations are written up by scientific software program Microsoft Excel. Results: The list and map of combatives systems , which have the office or the gym in city parts Prague 4, 5, 6, was created after processing all available sources (questionnaires, internet, meetings). Statistical data processsing of the amount of exercisers according to age and sex, focus of the devisions, legal form, training places, way of advertisement of the devisions, completed with the short description of those devisions, which are led by people, who were willing to give the informations for the aim of this work. Keys words: martial systems,...

Many views to facial expression recognition exist. This work presents one of approaches. Existing methods of human face representation by model are discussed. The AAM method, where final appearance model is created from model of shape and model of texture is proposed. Model of shape and model of texture is created by statistic analysis. Using this representation, an effective method is achieved that is complexity of information for searched face in static image. Choice and combination of suitable features for classification of facial expression is principle for facial expression recognition based on AAM. Two approaches of facial expression classification are compared. Classification based on LDA and classification based on SVM. These methods with necessary face localization using AdaBoost form an automated face recognizer in image.

This thesis is concentrated on the labor market in the past five years in region Karvinsko. The aim of thesis is to explore the ways in which is solved the imbalance of labor market in this region and to analyze effectiveness of spending money on active employment policy. The deman and supply sides of the labour market are detailly invastigated due to their great influence on the economic development. The thesis deals the efficiency of active employment policy in region Karvinsko, especially community services, retraining and socially useful jobs. Other part of my thesis is evaluation of the case study among the unemployed who are in evidence of the Job centre in Karvina.

This diploma thesis focuses its point on automatization of stopwords generation as one method of pre-processing a textual documents. It analyses an influence of stopwords removal to a result of data mining tasks (classification and clustering). First the text mining techniques and frequently used algorithms are described. Methods of creating domain specific lists of stopwords are described to detail. In the end the results of large collections of text files testing and implementation methods are presented and discussed.

The aim of this thesis is the draft of risk management model applicable in construction companies providing the service "turnkey". The first part focuses on project management and risk management in general. The second part is the whole issue applied to construction companies providing the service "turnkey". First, the identification of bearing assets of businesses is performed, and their risks are then defined. Load-bearing assets and their risks are sought in the internal and external environment using PESTE analysis and Porter's model of competitive forces. Afterwards, the most serious-risks are selected. Selected risks are supplied with the amount of potential damage and the probability of its occurrence is determined. The significance of selected risk is captured in the risk matrix. The results of the thesis are proposals for strategies "4 T" Risk Management for management of companies.

The aim of the thesis was to derive complex information of the current vegetation cover in the alpine treeline ecotone in Praděd Reserve by using remote sensing. Particularly thesis focuses on an area and expansion of dwarf pine (Pinus mugo Turra) at site above the alpine treeline ecotone around the peak Praděd. Two types of aerial photograph from 2000 and 2012 and satellite images from Landsat 7 (yaer 2000) and Landsat 8 (year 2013) were used for mapping vegetation. Supervised and unsupervised classification accesses and also "per-pixel" and objected classification methods were used in image processing. All the classifications confirmed expansion of dwarf pine stands in the alpine treeline vegetation. Most precise method was based on supervised objected classification.