dc.contributor.advisor | Kofod-Petersen, Anders | nb_NO |
dc.contributor.author | Dreyer, Sigve | nb_NO |
dc.date.accessioned | 2014-12-19T13:41:10Z | |
dc.date.available | 2014-12-19T13:41:10Z | |
dc.date.created | 2014-03-04 | nb_NO |
dc.date.issued | 2013 | nb_NO |
dc.identifier | 702890 | nb_NO |
dc.identifier | ntnudaim:8223 | nb_NO |
dc.identifier.uri | http://hdl.handle.net/11250/253635 | |
dc.description.abstract | This thesis contains research on feature selection, in particular feature selection using evolutionary algorithms. Feature selection is motivated by increasing data-dimensionality and the need to construct simple induction models.A literature review of evolutionary feature selection is conducted. After that a abstract feature selection algorithm, capable of using many different wrappers, is constructed. The algorithm is configured using a low-dimensional dataset. Finally it is tested on a wide range of datasets, revealing both it's abilities and problems.The main contribution is the revelation that classifier accuracy is not a sufficient metric for feature selection on high-dimensional data. | nb_NO |
dc.language | eng | nb_NO |
dc.publisher | Institutt for datateknikk og informasjonsvitenskap | nb_NO |
dc.title | Evolutionary Feature Selection | nb_NO |
dc.type | Master thesis | nb_NO |
dc.source.pagenumber | 76 | nb_NO |
dc.contributor.department | Norges teknisk-naturvitenskapelige universitet, Fakultet for informasjonsteknologi, matematikk og elektroteknikk, Institutt for datateknikk og informasjonsvitenskap | nb_NO |