|
| |
|
|
ADVANCED REGRESSION MODELS
Rosecký, Martin ; Popela, Pavel (referee) ; Bednář, Josef (advisor)
This thesis summarizes latest findings about municipal solid waste (MSW) modelling. These are used to solve multivariable version of inverse prediction problem. It is not possible to solve such problem analytically, so heuristic framework using regression models and data reconciliation was developed. As a side product, models for MSW modelling using PCA (Principal Component Analysis) and LM (Linear Model) were created. These were compared with heuristic model called RF (Random Forest). Both of these models were also used for per capita MSW modelling. Theoretical parts about generalized linear models, data reconciliation and nonlinear programming are also included.
|
|
|
System for Acquisition and Analysis of Real Estate Data from WWW
Karpíšek, Miroslav ; Hynek, Jiří (referee) ; Burget, Radek (advisor)
This project is focused on designing a system for automatic extraction of real estate data from real estate servers. In the theoretical part, this work is first placed in the context of data engineering. Subsequently, the used technologies and system components that were used in the project are described, same as their importance within the framework of the created platform intended for real estate investors for the purpose of renting them. The work also includes an evaluation of the basic methods used to predict the rent amount, which is used to calculate the return of investment.
|
|
|
Secure web application for surface temperature monitoring based on machine learning methods
Hejna, Jan ; Bubniak, Milan (referee) ; Musil, Petr (advisor)
The bachelor thesis is focused on the exploration of the influence of solar radiation on the measured temperature by temperature sensors in microwave devices and on the possibilities of quantifying this influence. The thesis explores the possibility of using these devices to measure ambient temperature using selected machine learning methods. The aim was to create a secure web application that will be used for area-based ambient temperature monitoring, thus expanding existing networks of meteorological measurement points. The theoretical part of the thesis focuses on the technology of microwave links and the environmental influences that affect the measured temperature of these devices. In the practical part of the thesis, a correlation analysis was performed between the measured temperatures from different telecommunication equipment technologies and the temperatures of the surrounding meteorological stations. The analysis aimed at selecting an appropriate technology for ambient temperature prediction. The next part of the practical work involved the process of training a machine learning model. The last part involves the development of a web application that displays temperature maps of the Czech Republic.
|
|
|
Econometric analysis of demographic aspects of economic development
LE, Václav Quang
The thesis focuses on econometric analysis of demographic aspects of economic development. The subject of the analysis is the sustainability of the pension system of the Czech Republic, which is examined from two perspectives, from the point of view of pension revenues and expenditures on pension benefits. The analysis is carried out using the multiple linear regression technique. Three models are presented for each of the variables examined. The dataset is time series in nature, has quarterly seasonality and the period under study is the time interval 2000-2022 Q1. According to the revenue models, revenue is positively correlated with GDP, wages and salaries, employers' social contributions, consumer price index (CPI) and negatively correlated with the number of employed and unemployed. Expenditures, on the other hand, are positively correlated with the number of pensions, CPI, average wages and past expenditures. The models presented were also evaluated for their forecast accuracy for 2018-2019 when there was no crisis and for 2020-2022 Q1 when there was a crisis. The models were able to capture the dynamics of the variables in the non-crisis period, but were not as accurate in the crisis period, with the expenditure models performing better in comparison. Based on cross-validation, the corrected Akaike information criterion and the Schwarz Bayesian information criterion, model 2 was selected for each variable to predict for Q2-Q4 2022. According to the revenue model, revenue should trend sideways/stagnate, while according to the expenditure model, expenditure should grow. Also, predicted expenditures are exceeding predicted revenues.
|
|
|
Analysis of ice and water rescue statistics.
Bohatý, Aleš ; Fiala, Miloš (advisor) ; Vilášek, Josef (referee)
Title: Analysis of ice and water rescue statistics. Objectives: The aim is to describe the work of rescuers during rescue operations on ice and water, to describe the watercourses and water areas freezing process, to describe hydrology of watercourses and water areas, to inform about the numbers of ice and water rescue interventions in past years and in each of Czech republic's regions and to determine a time series data tendency of ice and water rescue statistics - to predict whether the rescue interventions numbers will increase or decrease in the years to come. Methods: Literature and study sources research and their further summarization, ice and water rescue statistics analysis by determining the time series data tendency (trends) by calculating linear regression parameters of these statistics, tendencies visualization using graphs and heatmaps. Results: According to data analysis of years 2006 - 2021, water and ice rescue numbers will be decreasing in the future. On the other hand data analysis of years 2014 - 2021 predict an increase in these numbers. The conclusion is that the ice and water rescue numbers will be increasing in the future, although the numbers will not be as high as of past years of 2006 - 2014. Key words: Analysis, statistics, tendency, trend, time series data, linear...
|
|
|
Statistical inference of the Modified Smith?s model
Rušin, Michal ; Šmíd, Martin (advisor) ; Hlubinka, Daniel (referee)
The present work discuss the continuous double auction mechanisms and the order book models. After a brief introduction to selected models, a general model of the the continuous double auction from the thesis title is described. Further, a structure of british market data is given as well as an approach to them. Based on these data the validity of Smith Farmer's model and Cont Stoikov's model is tested in the context of general model by linear regression. Finally, based on the previous results, the own order book model is suggested and its validity tested.
|
|
|
Effect of swimming on the overall triathlon performance in triathlon races World Championships in years 2000 - 2010
Koktová, Veronika ; Kovářová, Lenka (advisor) ; Horčic, Josef (referee)
Title: The influence of swimming part of triathlon the total performance in competitions of world championships 2000-2010. Objectives: The aim is to investigate the influence of the swimming part of the total performance in triathlon in the lost 10 years. Methods: The relation between two variables (times from swimming and the total time of competitions from competitions of world championships 2000-2010 were described with the help of linear regression. Individual years were then compared in a point graph. Results: Our hypothese were confirmmed. It means that the result from the swimming part explains the result from the competition in less than 30%, which means the R2 is smaller than 0,3. We also found, that the influnence of the swimming part on the final result in triathlon has not changed in the last years. The relationship times in the swimming part and total (final) times was closest in 2005 (R2= 0,21). In other years, this dependence is lower, R2 was smaller than 0,07. Keywords: linear regression, longitudinal analysis, performance
|
|
|
Evaluation of body composition analysis using anthropometric measurements and methods based on bioimpedance
Provázek, Pavel ; Bunc, Václav (advisor) ; Musálek, Martin (referee)
Title: Evaluation of body composition analysis using anthropometric measurements and methods based on bioimpedance Aims: The main goal of this study is to analyze correlations of the data from bioimpedance with direct anthropometric measurements using statistical data analysis taking into consideration that the latter data is recognized as a gold standard. Methods: The sample of 42 men and 20 women was evaluated using standard anthropometric techniques. In addition, the dimensions, which are necessary to establish the weight of segments in upper and lower arms. The obtained data was firstly evaluated using a universal software ANTROPO. The both samples were concurrently investigated using the bioimpedance methods and the relationships between the aforementioned data and data from InBody was evaluated by three independent statistical methods such as substantive significance (Cohen's d), two-parameter linear regression and robust Passing- Bablok regression. Results: The results obtained enable to conclude that (with the exception of body height and BMI) the remaining parameters do not sufficiently correlate when using anthropometric measurements and data from InBody. As the relatively low number of participants may result in certain misrepresentation of the results, particularly in women, the...
|
|
|
Modern statistical approach in evaluating the compressive strength of concrete in structures using the rebound hammer method
Janka, Marek ; Kocáb, Dalibor (referee) ; Misák, Petr (advisor)
This diploma thesis examines various linear regression methods and their use to establish regression relationships between the compressive strength of concrete determined by the indirect method and by the crushing of the specimens in the press. It deals mainly with the uncertainty of values measured by the indirect method, which is neglected by the usually used ordinary least squares regression method. It also deals with the weighted least squares method, suitable for so-called heteroskedastic data. It compares different regression methods on several sets of previously measured data. The final part of the work examines the effect of removing too influential points identified by Cook's distance, which may skew the regression results.
|
guest ::
