Feature Selection Using Self Organizing Map Oriented Evolutionary Approach

dc.contributor.authorCeylan, Oguzhan
dc.contributor.authorCeylan, Oğuzhan
dc.contributor.authorTaskin, Gulsen
dc.date.accessioned2023-10-19T15:05:32Z
dc.date.available2023-10-19T15:05:32Z
dc.date.issued2021
dc.departmentKadir Has Universityen_US
dc.department-temp[Ceylan, Oguzhan; Taskin, Gulsen] Kadir Has Univ, Management Informat Syst Dept, Istanbul, Turkiye; Istanbul Tech Univ, Inst Disaster Management, Istanbul, Turkiyeen_US
dc.description.abstractHyperspectral images are the multidimensional matrices consisting of hundreds of spectral feature vectors. Thanks to these large number of features, the objects on the Earth having similar spectral characteristics can easily be distinguished from each other. However, the high correlation and the noise between these features cause a significant decrease in the classification performances, especially in the supervised classification tasks. In order to overcome these problems, which is known in the literature as Hughes's effects or curse of dimensionality, dimensionality reduction techniques have frequently been used. Feature selection and feature extraction methods are the ones used for this purpose. The feature selection methods aim to remove the features, including high correlation and noise, out of the original feature set. In other words, a subset of relevant features that have the ability to distinguish the objects is determined. The feature extraction methods project the high dimensional space into a lower-dimensional feature space based on some optimization criterion, and hence they distort the original characteristic of the dataset. Therefore, the feature selection methods are more preferred than the feature extraction methods since they preserve the originality of the dataset. Based on this motivation, an evolutionary based optimization algorithm utilizing self organizing map was accordingly modified to provide a new feature selection method for the classification of hyperspectral images. The proposed method was compared to well-known feature selection methods in the classification of two hyperspectral datasets: Botswana and Indian Pines. According to the preliminary results, the proposed method achieves higher performance over other feature selection methods with a very less number of features.en_US
dc.description.woscitationindexConference Proceedings Citation Index - Science
dc.identifier.citationcount1
dc.identifier.doi10.1109/IGARSS47720.2021.9553491en_US
dc.identifier.doi10.1109/IGARSS47720.2021.9553491
dc.identifier.endpage4006en_US
dc.identifier.isbn9781665403696
dc.identifier.issn2153-6996
dc.identifier.scopus2-s2.0-85126023541en_US
dc.identifier.scopus2-s2.0-85126023541
dc.identifier.scopusqualityN/A
dc.identifier.startpage4003en_US
dc.identifier.urihttps://doi.org/10.1109/IGARSS47720.2021.9553491
dc.identifier.volume2021-Julyen_US
dc.identifier.wosWOS:001250139804044
dc.identifier.wosqualityN/A
dc.khas20231019-Scopusen_US
dc.language.isoenen_US
dc.publisherIeeeen_US
dc.relation.ispartofIEEE International Geoscience and Remote Sensing Symposium (IGARSS) -- JUL 12-16, 2021 -- ELECTR NETWORKen_US
dc.relation.ispartofseriesIEEE International Symposium on Geoscience and Remote Sensing IGARSS
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.scopus.citedbyCount3
dc.subjectSelf Organizing Mapsen_US
dc.subjectEvolutionary Methodsen_US
dc.subjectOptimizationen_US
dc.subjectHyperspectral Image Classificationen_US
dc.subjectFeature Selectionen_US
dc.titleFeature Selection Using Self Organizing Map Oriented Evolutionary Approachen_US
dc.typeConference Objecten_US
dspace.entity.typePublication
relation.isAuthorOfPublicationb80c3194-906c-4e78-a54c-e3cd1effc970
relation.isAuthorOfPublication.latestForDiscoveryb80c3194-906c-4e78-a54c-e3cd1effc970

Files

Original bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
4939.pdf
Size:
308.08 KB
Format:
Adobe Portable Document Format
Description:
Tam Metin / Full Text