1. Evaluation of Orange data mining software and examples for lecturing machine learning tasks in geoinformatics.
- Author
-
Dobesova, Zdena
- Subjects
DATA mining software ,MACHINE learning ,GEOINFORMATICS ,SCIENTIFIC method ,ORANGES ,LINEAR network coding - Abstract
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. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF