| Autor: |
Olha Tokar, Serhii Havryliuk, Lubov Kolyasa, Mykola Korol, Olena Vovk |
| Rok vydání: |
2018 |
| Předmět: |
|
| Zdroj: |
2018 IEEE 13th International Scientific and Technical Conference on Computer Sciences and Information Technologies (CSIT). |
| DOI: |
10.1109/stc-csit.2018.8526646 |
| Popis: |
The Random Forest classification which has a range substantial advantages was used for land cover investigations. Such a classification algorithm was applied in R software. Main land cover areas (coniferous, deciduous, water, urban territory and grasslands) were interpreted on Landsat image and accuracy of classification was estimated using different indexes, including OOB (Out-of-Bag) and Kappa index. According to research results a thematic map of land cover was formed. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
