Neural network method for failure detection with skewed class distribution

Simple item page
dc.contributor.authorCarvajal, K
dc.contributor.authorChacon, M
dc.contributor.authorMery, D
dc.contributor.authorAcuna, G
dc.date.accessioned2024-01-10T12:06:52Z
dc.date.available2024-01-10T12:06:52Z
dc.date.issued2004
dc.description.abstractThe automatic detection of flaws through non-destructive testing uses pattern recognition methodology with binary classification. In this problem a decision is made about whether or not an initially segmented hypothetical flaw in an image is in fact of law. Neural classifiers are one among a number of different classifiers used in the recognition of patterns. Unfortunately, in real automatic flaw detection problems there are a reduced number of flaws in comparison with the large number of non-flatus. This seriously limits the application of classification techniques such is artificial neural networks elite to the imbalance between classes. This work presents a new methodology for efficient training with imbalances in classes. The premise of the present work is that if there are sufficient cases of the smaller class, then it is possible to reduce the Size of the larger class by using the correlation between cases of this latter class, with a minimum information loss. It is then possible to create it training set for a neural model that allows good classification. To test this hypothesis a problem of great interest to the automotive industry is used, which is the radioscopic inspection of cast aluminium pieces. The experiments resulted in perfect classification of 22936 hypothetical flaws, of which only 60 were real flat-vs and the rest were false alarms.
dc.format.extent4 páginas
dc.fuente.origenWOS
dc.identifier.doi10.1784/insi.46.7.399.55578
dc.identifier.eissn1754-4904
dc.identifier.issn1354-2575
dc.identifier.urihttps://doi.org/10.1784/insi.46.7.399.55578
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/76216
dc.identifier.wosidWOS:000222602600012
dc.information.autorucIngeniería;Mery D;S/I;102382
dc.issue.numero7
dc.language.isoen
dc.nota.accesoSin adjunto
dc.pagina.final402
dc.pagina.inicio399
dc.publisherBRITISH INST NON-DESTRUCTIVE TESTING
dc.revistaINSIGHT
dc.rightsregistro bibliográfico
dc.subject.ods11 Sustainable Cities and Communities
dc.subject.odspa11 Ciudades y comunidades sostenibles
dc.titleNeural network method for failure detection with skewed class distribution
dc.typeartículo
dc.volumen46
sipa.codpersvinculados102382
sipa.indexWOS
sipa.indexScopus
sipa.trazabilidadCarga SIPA;09-01-2024
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Neural network method for failure detection with skewed class distribution.pdf
Size:
2.83 KB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Artículos de revistas