|
|
Visual Pattern Detection in Web Pages
Kotraš, Martin ; Bartík, Vladimír (referee) ; Burget, Radek (advisor)
The work solves the extraction of information from websites using the technique of searching for visual patterns - spatial relations between areas on the website and the same visual styles of these areas - with the extension of new techniques to improve results. It uses a user-specified ontological data model, which describes which data items will be extracted from the specified web page and how the individual items on the page look, mainly from a text point of view. As part of the work, a console application VizGet in Java was created using the FitLayout framework to obtain a visual model of the website. Testing the application on 7 different domains, including a list of the best movies, e-shop products, or weather forecasts, showed that the success rate of the application ranges in about 75 % of subtests above 85 % F-score and in more than 90 % of subtests above 60 % F-score, where 45 % of subtests achieve an F-score of 100 %. The VizGet application can thus be deployed for practical use in non-critical applications, while it is open to further extensions and possibilities for improvement.
|
|
|
Data Extraction from PDF Documents
Bartošák, Michal ; Bartík, Vladimír (referee) ; Burget, Radek (advisor)
The work focuses on extracting information from medical records saved in PDF format, which were created by heart pacemakers during regular patient monitoring in the hospital. The result of this work is a desktop application written in Java that retrieves and analyzes data from records using PDFBox and pdf2dom libraries. The output of the application is a CSV file, which represents the acquired values in table form, as well as extracted images that are saved to a user-defined output folder. Application testing on records from three different companies proved that record extraction is highly reliable (with overall precision and recall metrics reaching almost 100 % in every test), provided that the application arguments are correctly set.
|
|
|
Visual Pattern Detection in Web Pages
Kotraš, Martin ; Bartík, Vladimír (referee) ; Burget, Radek (advisor)
The work solves the extraction of information from websites using the technique of searching for visual patterns - spatial relations between areas on the website and the same visual styles of these areas - with the extension of new techniques to improve results. It uses a user-specified ontological data model, which describes which data items will be extracted from the specified web page and how the individual items on the page look, mainly from a text point of view. As part of the work, a console application VizGet in Java was created using the FitLayout framework to obtain a visual model of the website. Testing the application on 7 different domains, including a list of the best movies, e-shop products, or weather forecasts, showed that the success rate of the application ranges in about 75 % of subtests above 85 % F-score and in more than 90 % of subtests above 60 % F-score, where 45 % of subtests achieve an F-score of 100 %. The VizGet application can thus be deployed for practical use in non-critical applications, while it is open to further extensions and possibilities for improvement.
|
|
|
Quality of honey depending on processing technology
Fejt, Jaroslav ; Bušová, Milena (advisor) ; Luboš, Luboš (referee)
This diploma thesis is aimed at assessing the impact of using multiple technologies or practices on the quality of honey. The theoretical part includes a summary of the main methods currently used for assessing the quality of honey and/or establishing its origin. The suitability of the selected apicultural (beekeeping) technology, apiary placement, handling bee honeycombs and facilities for extraction of honey present the first condition for obtaining quality honey without pesticides, air pollutant microparticles, hazardous elements, microorganisms, volatile pollutants of coating substances, antibiotics, drugs used against varroa destructor parasites and their residues. There are mentioned all the known bactericidal and bacteriostatic properties of honey to help preserve its natural quality features without degrading changes.
In the practical part there are two groups of honey samples collected from own hives in 2015. Those were sent for analysis to the Institute of beekeeping in Dol (Czech Republic). In 2016, ten samples from beekeepers and ten from retail markets were used. Their partial analysis was carried out at the Department of Agricultural Product Quality. The samples were obtained in a conventional manner using modern honey extractors and in the second case by pressing. The above mentioned samples were tested for water content, HMF, conductivity, glucose, fructose, sucrose, starch and caramel colorants, titration factor, Fiehe´s honey violation by starch sugar or sweetener.
|
guest ::
