|
| |
|
|
Reordering Text Fragments Using a Language Model
Holubec, Michael ; Kocour, Martin (referee) ; Beneš, Karel (advisor)
The aim of this work is to construct and experimentally verify the effectiveness of the language model in identifying the reading order. For this purpose language model with LSTM architecture was constructed. This work designs and implements three methods which are used to identify reading order. These methods are Language analysis, Spatial analysis and Combined analysis. Language analysis and combined analysis used constructed language model. The success of the language model, and all three methods, was measured on three datasets containing newspaper articles. Language analysis reaches 57,6 % and spatial analysis reaches 91,6 %. Combined analysis achieved the best results 92,9 %. The work shows that the language model can be used to identify reading order but use of additional data (e.g. spatial data
|
|
|
The effect of migration on electoral geography of populist-nationalist parties: the case of Freedom and Direct Democracy - Tomio Okamura party
Suchánek, Jonáš ; Hasman, Jiří (advisor) ; Maškarinec, Pavel (referee)
Analytical research of a migrant's presence in a certain location on election outcomes of populist-nationalist parties is a relatively new phenomena in the field of electoral geography. Media and political interest in migration and refugees has risen rapidly in the last few years and offers a broad opportunity for relevant scientific studies. This thesis stems from existing literature, that have studied such relation and focuses on the case of The Freedom and Direct Democracy - Tomio Okamura Party (SPD) and on the possible influence of the share of migrants on SPD's electoral support at two different scale levels (municipalities with authorized municipal offices and individual municipalities) during the 2017 parliamentary elections. Analysing the most important groups of migrants and additionally a formed group of migrants coming from countries with either dominant or significant Muslim native population can be considered as innovative. The main goal is to discover whether the election outcomes of SPD, which stands strongly opposed to migration, differ based on the share of migrants in a certain area, or if migration does not play any role at all. Furthermore, the electoral geography of SPD is compared to the of Tomio Okamura's former party - Dawn of Direct Democracy, whose rhetoric did not focus...
|
|
|
Possibilities of geographical research in the usage of liquid biofuels in transport
Valeš, Jiří ; Netrdová, Pavlína (advisor) ; Šatra, Jan (referee)
At first there is briefly shown the history of usage and present usage of liquid biofuels in transport. The paper describes its regional differenciation in EU and with the help of basic statistical methods researches the development of differences of the meaning of biofuels in Member States. For these purposes there is created a database of shares of biofuels in energy consumption in transport. If we understand the shares of biofuels showing the intensity or the meaning of biofuels usage, we can exemine its differences. With the help of Lorenz curve there is described the development of rate of inequality of biofuels production. There is also evaluated the meaning of biofuels production in Member States by relativising it to the area of arable land. Key words: liquid biofuels, statistical analysis, spatial analysis
|
|
| |
|
|
Quality of life in dimension of health: Czechia in regional perspective
Smetanová, Marie ; Netrdová, Pavlína (advisor) ; Dragomirecká, Eva (referee)
This thesis focuses on the quality of life in dimension of health at the regional level in the Czechia for the period 2010-2019. The main aim of this work is to describe and evaluate the spatial differentiation and spatio-temporal variability of the concept quality of life in dimension of health at the regional level of administrative districts of municipalities with extended powers. The assessment is based on objective indicators mapping the health status of the population, lifestyle, and the availability of primary health care. The theoretical part describes definitions quality of life, the characteristics of whole concept, health, its determinants, and inequalities that arise in health and can resonate at the regional level. This work also describes the types of prevention, as an effective tool in reducing health inequalities and the possible promotion of public health, in the form of improving health literacy. The analytical part is based on factor and cluster analysis and methods of spatial autocorrelation. In the Czech Republic, significant regional differentiation of quality of life in health dimension has been found. Furthermore, spatial patterns were discovered drawing attention to problematic and favourable areas within the observed concept. It turned out that the resulting quality of...
|
|
|
Spatial analysis of Airbnb apartment locations in Prague
Kroutil, Filip ; Pertold-Gebicka, Barbara (advisor) ; Nevrla, Matěj (referee)
This paper investigates the determinants of the spatial distribution of Airbnb listings in Prague, the capital city of the Czech Republic, and compares it with the distribution of traditional accommodation units such as hotels. The analysis is based on two datasets, one containing all 14 864 Airbnb listings in Prague in November 2019 and the other including a snapshot of 864 hotels from March 2020. Local indicators of spatial association and traditional OLS regression were used to study the determinants and differences between the distributions. The results show a simpler and more centered distribution in the case of Airbnb units. The study also provides a model describing Airbnb density in each municipal district with high predicting power. Insights from this thesis could help understand the principles behind Airbnb dispersion and so create a basis for future regulations of this relatively new market segment.
|
|
|
Real estate price modelling with a focus on location attributes
Charvát, Ondřej ; Polák, Petr (advisor) ; Hejlová, Hana (referee)
The thesis introduces several methods of real estate price modelling suitable either for prediction of the housing prices or for exploring the relationships between the price and its determinants. We compared the conventional linear regression approach to the tree-based methods of machine learning. The comparison analysis on the dataset of 28 019 apartments in Prague suggests that regression trees (especially the Random forest) yield a higher accuracy in the price prediction. Another objective was to examine the effects of location attributes (especially its accessibility and environmental quality) on the prices of nearby apartments. To address the spatial interactions in the geographical data, we employed three spatially conscious models to achieve more reliable results. The local analysis performed with the geographically weighted regression confirmed the presence of spatial heterogeneity and described the price effects relative to the location. In some areas, an increase of 100 meters in distance from the nearest metro station and the nearest park are associated with a decrease in the apartment prices by 644 CZK/m2 and 916 CZK/m2 , respectively. These findings are especially important for the apartments near the stations of the new metro line, which is currently in construction.
|
|
|
The spatial analysis of the 2018 Czech presidential election results in the capital city of Prague
Vratný, Radek ; Lepič, Martin (advisor) ; Šimon, Martin (referee)
The 2018 Czech presidential election were profoundly controversial and polarising event. One of the polarising factors was a perception that the voting behaviour in the capital city of Prague is significantly different compared to the voting behaviour in the rest of Czechia. Therefore, the primary objective of this thesis is to examine the electoral support of both runoff voting candidates across the territory of the capital city of Prague. The main part of the analysis focuses on the spatial differentiation of the election results of both candidates at the level of Prague's polling districts and on searching for the spatial clusters of electoral support. For the purpose of the study the methods of the exploratory spatial data analysis were used, specifically the global and local statistics of spatial autocorrelation. Subsequently, the thesis attempts to clarify which factors determined the voting behaviour through testing the socio-economic and demographic indicators using the method of multinomial linear regression. The analysis proved that the spatial differentiation of the election results of both candidates is significant across the territory of Prague and detected the spatial clusters of electoral support. The analysis also clarified that this voting behaviour can be explained particularly by...
|
|
|
Software for efficient use of material in 2D machining
Švanda, Ondřej ; Šeda, Miloš (referee) ; Lang, Stanislav (advisor)
Tato práce si klade za cíl obeznámit čtenáře s 2D CNC obráběním a rozličnými metodami popisu a manipulace s dvojrozměrnými objekty. Poté je představen tzv. Nesting problém a jsou popsány různé metody přístupu k jeho vyřešení. Praktická část pokrývá implementaci vlastního nesting softwaru, jenž je schopný efektivně rozmístit nepravidelné tvary do nepravidelné ohraničené plochy. Na závěr je provedeno zhodnocení řečeného softwaru a také je zmíněno jeho možné využití v praxi.
|
guest ::
