Validation of archetypal analysis

Suleman, A.

doi:10.1109/FUZZ-IEEE.2017.8015385

Utilize este identificador para referenciar este registo: http://hdl.handle.net/10071/16015

Registo completo

Campo DC	Valor	Idioma
dc.contributor.author	Suleman, A.	-
dc.date.accessioned	2018-06-07T10:53:17Z	-
dc.date.available	2018-06-07T10:53:17Z	-
dc.date.issued	2017	-
dc.identifier.isbn	978-1-5090-6034-4	-
dc.identifier.issn	1558-4739	-
dc.identifier.uri	https://ciencia.iscte-iul.pt/id/ci-pub-37991	-
dc.identifier.uri	http://hdl.handle.net/10071/16015	-
dc.description.abstract	We use an information-theoretic criterion to assess the goodness-of-fit of the output of archetypal analysis (AA), also intended as a fuzzy clustering tool. It is an adaptation of an existing AIC-like measure to the specifics of AA. We test its effectiveness using artificial data and some data sets arising from real life problems. In most cases, the results achieved are similar to those provided by an external similarity index. The average reconstruction accuracy is about 93%.	por
dc.language.iso	eng	por
dc.publisher	IEEE	por
dc.relation	info:eu-repo/grantAgreement/FCT/5876/147442/PT	por
dc.rights	openAccess	por
dc.subject	Fuzzy clustering	por
dc.subject	Archetypal analysis	por
dc.subject	Validation index	por
dc.title	Validation of archetypal analysis	por
dc.type	conferenceObject	en_US
dc.event.title	2017 IEEE International Conference on Fuzzy Systems	por
dc.event.type	Conferência	por
dc.publicationstatus	Publicado	por
dc.peerreviewed	yes	por
dc.journal	2017 IEEE International Conference on Fuzzy Systems, FUZZ 2017	en_US
degois.publication.location	Naples	por
degois.publication.title	2017 IEEE International Conference on Fuzzy Systems, FUZZ 2017	por
dc.date.updated	2018-06-07T10:51:54Z	-
dc.description.version	info:eu-repo/semantics/acceptedVersion	-
dc.identifier.doi	10.1109/FUZZ-IEEE.2017.8015385	-
Aparece nas coleções:	BRU-CRI - Comunicações a conferências internacionais

Ficheiros deste registo:

Ficheiro	Descrição	Tamanho	Formato
PID4716351-1.pdf	Pós-print	384,77 kB	Adobe PDF	Ver/Abrir

Mostrar registo em formato simples Visualizar estatísticas