Show simple item record

dc.creatorMarjanović, Miloš
dc.creatorKovačević, Miloš
dc.creatorBajat, Branislav
dc.creatorMihalić, Snježana
dc.creatorAbolmasov, Biljana
dc.date.accessioned2019-04-19T14:17:23Z
dc.date.available2019-04-19T14:17:23Z
dc.date.issued2011
dc.identifier.issn1854-0171
dc.identifier.urihttp://grafar.grf.bg.ac.rs/handle/123456789/396
dc.description.abstractIn this research, machine learning algorithms were compared in a landslide-susceptibility assessment. Given the input set of GIS layers for the Starca Basin, which included geological, hydrogeological, morphometric, and environmental data, a classification task was performed to classify the grid cells to: (i) landslide and non-landslide cases, (ii) different landslide types (dormant and abandoned, stabilized and suspended, reactivated). After finding the optimal parameters, C4.5 decision trees and Support Vector Machines were compared using kappa statistics. The obtained results showed that classifiers were able to distinguish between the different landslide types better than between the landslide and non-landslide instances. In addition, the Support Vector Machines classifier performed slightly better than the C4.5 in all the experiments. Promising results were achieved when classifying the grid cells into different landslide types using 20% of all the available landslide data for the model creation, reaching kappa values of about 0.65 for both algorithms.en
dc.rightsrestrictedAccess
dc.sourceActa Geotechnica Slovenica
dc.subjectlandslidesen
dc.subjectsupport vector machinesen
dc.subjectdecision trees classifieren
dc.subjectStarca Basinen
dc.titleLandslide assessment of the Starca basin (Croatia) using machine learning algorithmsen
dc.typearticle
dc.rights.licenseARR
dc.citation.epage55
dc.citation.issue2
dc.citation.other8(2): 45-55
dc.citation.rankM23
dc.citation.spage45
dc.citation.volume8
dc.identifier.rcubconv_1571
dc.identifier.scopus2-s2.0-84892731922
dc.identifier.wos000299447200004
dc.type.versionpublishedVersion


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record