Qualitative test-cost sensitive classification

dc.citation.epage2051en_US
dc.citation.issueNumber13en_US
dc.citation.spage2043en_US
dc.citation.volumeNumber31en_US
dc.contributor.authorCebe, M.en_US
dc.contributor.authorGunduz Demir, C.en_US
dc.date.accessioned2016-02-08T09:56:47Z
dc.date.available2016-02-08T09:56:47Z
dc.date.issued2010en_US
dc.departmentDepartment of Computer Engineeringen_US
dc.description.abstractThis paper reports a new framework for test-cost sensitive classification. It introduces a new loss function definition, in which misclassification cost and cost of feature extraction are combined qualitatively and the loss is conditioned with current and estimated decisions as well as their consistency. This loss function definition is motivated with the following issues. First, for many applications, the relation between different types of costs can be expressed roughly and usually only in terms of ordinal relations, but not as a precise quantitative number. Second, the redundancy between features can be used to decrease the cost; it is possible not to consider a new feature if it is consistent with the existing ones. In this paper, we show the feasibility of the proposed framework for medical diagnosis problems. Our experiments demonstrate that this framework is efficient to significantly decrease feature extraction cost without decreasing accuracy. © 2010 Elsevier B.V. All rights reserved.en_US
dc.description.provenanceMade available in DSpace on 2016-02-08T09:56:47Z (GMT). No. of bitstreams: 1 bilkent-research-paper.pdf: 70227 bytes, checksum: 26e812c6f5156f83f0e77b261a471b5a (MD5) Previous issue date: 2010en
dc.identifier.doi10.1016/j.patrec.2010.05.028en_US
dc.identifier.issn0167-8655en_US
dc.identifier.urihttp://hdl.handle.net/11693/22197en_US
dc.language.isoEnglishen_US
dc.publisherElsevier BVen_US
dc.relation.isversionofhttp://dx.doi.org/10.1016/j.patrec.2010.05.028en_US
dc.source.titlePattern Recognition Lettersen_US
dc.subjectCost - sensitive learningen_US
dc.subjectFeature extraction costen_US
dc.subjectFeature selectionen_US
dc.subjectQualitative decision theoryen_US
dc.subjectCost of feature extractionen_US
dc.subjectCost sensitive classificationsen_US
dc.subjectLoss functionsen_US
dc.subjectMedical diagnosisen_US
dc.subjectMisclassification costsen_US
dc.subjectQualitative testen_US
dc.subjectCostsen_US
dc.subjectDecision theoryen_US
dc.subjectDiagnosisen_US
dc.subjectMedical problemsen_US
dc.subjectFeature extractionen_US
dc.titleQualitative test-cost sensitive classificationen_US
dc.typeArticleen_US

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Qualitative test-cost sensitive classification.pdf
Size:
860.66 KB
Format:
Adobe Portable Document Format
Description:
Full printable version