Development of a Supervised Classification Method To Construct 2d Mineral Maps on Backscattered Electron Images

dc.contributor.authorCamalan, Mahmut
dc.contributor.authorÇavur, Mahmut
dc.date.accessioned2020-06-08T19:07:18Z
dc.date.available2020-06-08T19:07:18Z
dc.date.issued2020
dc.departmentFakülteler, İşletme Fakültesi, Yönetim Bilişim Sistemleri Bölümüen_US
dc.description.abstractThe Mineral Liberation Analyzer (MLA) can be used to obtain mineral maps from backscattered electron (BSE) images of particles. This paper proposes an alternative methodology that includes random forest classification, a prospective machine learning algorithm, to develop mineral maps from BSE images. The results show that the overall accuracy and kappa statistic of the proposed method are 97% and 0.94, respectively, proving that random forest classification is accurate. The accuracy indicators also suggest that the proposed method may be applied to classify minerals with similar appearances under BSE imaging. Meanwhile, random forest predicts fewer middling particles with binary and ternary composition, but the MLA predicts more middling particles only with ternary composition. These discrepancies may arise because the MLA, unlike random forest, may also measure the elemental compositions of mineral surfaces below the polished section.en_US
dc.identifier.citation4
dc.identifier.doi10.3906/elk-1906-60en_US
dc.identifier.endpage1043en_US
dc.identifier.issn1300-0632en_US
dc.identifier.issn1303-6203en_US
dc.identifier.issn1300-0632
dc.identifier.issn1303-6203
dc.identifier.issue2en_US
dc.identifier.scopus2-s2.0-85085014985en_US
dc.identifier.scopusqualityQ3
dc.identifier.startpage1030en_US
dc.identifier.trdizinid335120en_US
dc.identifier.urihttps://hdl.handle.net/20.500.12469/2891
dc.identifier.urihttps://doi.org/10.3906/elk-1906-60
dc.identifier.urihttps://search.trdizin.gov.tr/yayin/detay/335120
dc.identifier.volume28en_US
dc.identifier.wosWOS:000522447800030en_US
dc.identifier.wosqualityQ4
dc.institutionauthorÇavur, Mahmuten_US
dc.institutionauthorÇavur, Mahmut
dc.language.isoenen_US
dc.publisherTubitaken_US
dc.relation.journalTurkish Journal of Electrical Engineering & Computer Sciencesen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectRandom foresten_US
dc.subjectMineral Liberation Analyzeren_US
dc.subjectBackscattered electron imagesen_US
dc.subjectMineral mapen_US
dc.subjectConfusion matrixen_US
dc.titleDevelopment of a Supervised Classification Method To Construct 2d Mineral Maps on Backscattered Electron Imagesen_US
dc.typeArticleen_US
dspace.entity.typePublication
relation.isAuthorOfPublication463fefd7-0e68-4479-ad37-0ea65fa6ae01
relation.isAuthorOfPublication.latestForDiscovery463fefd7-0e68-4479-ad37-0ea65fa6ae01

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Development of a supervised classification method to construct 2D mineral maps on backscattered electron images.pdf
Size:
5.45 MB
Format:
Adobe Portable Document Format
Description:

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: