Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Genetically Evolved Nearest Neighbor Ensembles
Högskolan i Borås, Institutionen Handels- och IT-högskolan. (CSL@BS)
Högskolan i Borås, Institutionen Handels- och IT-högskolan. (CSL@BS)
2009 (Engelska)Ingår i: Data Mining: Special Issue in Annals of Information Systems / [ed] Robert Stahlbock, Stefan Lessmann, Sven F. Crone, Springer Verlag , 2009, s. 299-313Kapitel i bok, del av antologi (Refereegranskat)
Abstract [en]

Both theory and a wealth of empirical studies have established that ensembles are more accurate than single predictive models. For the ensemble approach to work, base classifiers must not only be accurate but also diverse, i.e., they should commit their errors on different instances. Instance based learners are, however, very robust with respect to variations of a dataset, so standard resampling methods will normally produce only limited diversity. Because of this, instance based learners are rarely used as base classifiers in ensembles. In this paper, we introduce a method where Genetic Programming is used to generate kNN base classifiers with optimized k-values and feature weights. Due to the inherent inconsistency in Genetic Programming (i.e. different runs using identical data and parameters will still produce different solutions) a group of independently evolved base classifiers tend to be not only accurate but also diverse. In the experimentation, using 30 datasets from the UCI repository, two slightly different versions of kNN ensembles are shown to significantly outperform both the corresponding base classifiers and standard kNN with optimized k-values, with respect to accuracy and AUC.

Ort, förlag, år, upplaga, sidor
Springer Verlag , 2009. s. 299-313
Serie
Annals of Information Systems, ISSN 1934-3221 ; 8
Nyckelord [en]
knn, ensembles, genetic programming, Machine learning
Nyckelord [sv]
data mining
Nationell ämneskategori
Data- och informationsvetenskap Data- och informationsvetenskap
Identifikatorer
URN: urn:nbn:se:hb:diva-4925DOI: 10.1007/978-1-4419-1280-0Lokalt ID: 2320/5722ISBN: 978-1-4419-1279-4 (tryckt)ISBN: 978-1-4419-1280-0 (tryckt)OAI: oai:DiVA.org:hb-4925DiVA, id: diva2:884343
Tillgänglig från: 2015-12-17 Skapad: 2015-12-17 Senast uppdaterad: 2018-01-10Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltexthttp://www.mendeley.com/download/public/839011/2052332402/a71766fe7536e49a81601ffbfca56b127e1d5901/dl.pdf

Personposter BETA

Johansson, UlfKönig, Rikard

Sök vidare i DiVA

Av författaren/redaktören
Johansson, UlfKönig, Rikard
Av organisationen
Institutionen Handels- och IT-högskolan
Data- och informationsvetenskapData- och informationsvetenskap

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetricpoäng

doi
isbn
urn-nbn
Totalt: 90 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf