Zdena Dobesova

Dr. Zdena Dobesova

Department of Geoinformatics, Palacký University, Olomouc, Olomoucký Kraj, Czech Republic
orcid

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 October 2006 in Optik
Verified
Journal Article
Closed access
MDM. Dobeš
M. Dobeš
JMJ. Martinek
J. Martinek
DSD. Skoupil
D. Skoupil
Zdena DobesovaZdena Dobesova
Zdena Dobesova
JPJ. Pospíšil
J. Pospíšil

20 March 2024 in Computer Applications in Engineering Education
Verified
Journal Article
Open access
Zdena DobesovaZdena Dobesova
Zdena Dobesova
The study presents the advantages of, and possible uses for, Orange software for data mining in combination with processing spatial data by ArcGIS Pro software in education. To present suitability of Orange software in education, the scientific method of Physics of Notation by D. Moody is used to evaluate the Orange software's visual vocabulary. All nine principles are applied in the presented evaluation. As a result, a high level of effective cognition of the Orange visual vocabulary is proven by this method. Namely, the semantic transparency of visual vocabulary, thanks the explicit inner icons, is semantically immediate. Also, principle of dual coding is used properly by automatic text labels of graphical symbols with the opportunity to rename labels. Renaming is also a way to ensure the partial overloading of symbols found by the first principle of semiotic clarity. The principle of cognitive interaction is partially fulfilled by automatically reorganizing connector lines between symbols to reduce the crossing of lines. A high level of effective cognition is beneficial for students. The evaluation of the visual notation of Orange software is presented to inform teachers and the geoinformatics community of the highly effective cognitive aspects of Orange software. The two practical lectures of processing in Orange and ArcGIS Pro software are shown to the teachers and students of geoinformatics community as examples of machine learning tasks. They are cluster analyses carried out with the density‐based spatial clustering of applications with noise method, first for the location of cafés in Olomouc town and the second example concerns finding similar European towns based on their land use arrangement, using the neural network and following hierarchical clustering. Both examples could provide inspiration for the geoinformatics community to adopt Orange data mining software.

1 September 2011
Verified
Conference Paper
Closed access
Zdena DobesovaZdena Dobesova
Zdena Dobesova
Geographic information systems belong the group of applications that process spatial data. Some spatial analyses are operated repetitively in the same way for different area or district. Therefore it is useful when the data processing can be run automatically by program extension designed especially for batch data processing. ArcGIS software offers a possibility to design the steps of data processing by data flow diagram in the graphic editor ModelBuilder. In some cases the data flow diagram which is designed in ModelBuilder component is not sufficient for all require tasks. In such cases, it is possible to automatically convert data flow diagram into the Python language and supplement the program code with other program constructions and commands. Some practical examples are presented in this article. All Python scripts were developed as a part of several research projects at Department of Geinformatics at Palacky University in the Czech Republic. This article is a sum of experience with scripting in Python for ArcGIS geoprocessor.

Verified
Journal Article
Open access
PDF file
Zdena DobesovaZdena Dobesova
Zdena Dobesova
The integration of geography and machine learning can produce novel approaches in addressing a variety of problems occurring in natural and human environments. This article presents an experiment that identifies cities that are similar according to their land use data. The article presents interesting preliminary experiments with screenshots of maps from the Czech map portal. After successfully working with the map samples, the study focuses on identifying cities with similar land use structures. The Copernicus European Urban Atlas 2012 was used as a source dataset (data valid years 2015–2018). The Urban Atlas freely offers land use datasets of nearly 800 functional urban areas in Europe. To search for similar cities, a set of maps detailing land use in European cities was prepared in ArcGIS. A vector of image descriptors for each map was subsequently produced using a pre-trained neural network, known as Painters, in Orange software. As a typical data mining task, the nearest neighbor function analyzes these descriptors according to land use patterns to find look-alike cities. Example city pairs based on land use are also presented in this article. The research question is whether the existing pre-trained neural network outside cartography is applicable for categorization of some thematic maps with data mining tasks such as clustering, similarity, and finding the nearest neighbor. The article’s contribution is a presentation of one possible method to find cities similar to each other according to their land use patterns, structures, and shapes. Some of the findings were surprising, and without machine learning, could not have been evident through human visual investigation alone.

Verified
Journal Article
Open access
PDF file
MKMichal Kučera
Michal Kučera
Zdena DobesovaZdena Dobesova
Zdena Dobesova
The article presents a method for determining and evaluating the threat to railway infrastructure from falling trees. The main objective was to identify the degree of threat according to three parameters: the height of tree stands, species composition, and vegetation health. Identification of the threat to individual railway sections would allow the creation of measures that could increase operational safety. Evaluation should be carried out at regular intervals to assess vegetation health during certain seasons. We, therefore, recommend the use of satellite images to provide a data source and regular data updates. The potential benefit is a reduction in railway infrastructure damage and an increase in traffic flow, especially during periods of exceptional weather conditions involving high wind, ice or heavy snow. The new method presented in the paper, based on data for railway infrastructure, law and other data sources in the Czech Republic, determines a Vegetation Threat Index for Railways (VTIR). We selected the Liberec Region as an example case study because of its large spread of wooded areas around railway lines and high incidence of railway traffic accidents.