Land Cover Mapping Using Ensemble Feature Selection Methods

Simple item page
dc.contributor.authorGidudu, A.
dc.contributor.authorAbe, B.
dc.contributor.authorMarwala, T.
dc.date.accessioned2023-02-01T20:56:21Z
dc.date.available2023-02-01T20:56:21Z
dc.date.issued2008
dc.description.abstractEnsemble classification is an emerging approach to land cover mapping whereby the final classification output is a result of a ‘consensus’ of classifiers. Intuitively, an ensemble system should consist of base classifiers which are diverse i.e. classifiers whose decision boundaries err differently. In this paper ensemble feature selection is used to impose diversity in ensembles. The features of the constituent base classifiers for each ensemble were created through an exhaustive search algorithm using different separability indices. For each ensemble, the classification accuracy was derived as well as a diversity measure purported to give a measure of the in-ensemble diversity. The correlation between ensemble classification accuracy and diversity measure was determined to establish the interplay between the two variables. From the findings of this paper, diversity measures as currently formulated do not provide an adequate means upon which to constitute ensembles for land cover mapping.en_US
dc.identifier.citationGidudu, A., Abe, B., & Marwala, T. (2008). Land Cover Mapping Using Ensemble Feature Selection Methods. arXiv preprint arXiv:0811.2016.en_US
dc.identifier.urihttps://arxiv.org/abs/0811.2016
dc.identifier.urihttps://nru.uncst.go.ug/handle/123456789/7466
dc.language.isoenen_US
dc.publisherarXiv preprint arXiven_US
dc.subjectEnsemble Feature Selectionen_US
dc.subjectDiversityen_US
dc.subjectDiversity Measuresen_US
dc.subjectLand Cover Mappingen_US
dc.titleLand Cover Mapping Using Ensemble Feature Selection Methodsen_US
dc.typeArticleen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Land Cover Mapping Using Ensemble Feature Selection Methods.pdf
Size:
210.79 KB
Format:
Adobe Portable Document Format
Description:
Article
Download
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:
Download
Collections
Natural Sciences