du.sePublikationer
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • chicago-author-date
  • chicago-note-bibliography
  • 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
Machine Learning Algorithms in Heavy Process Manufacturing
Högskolan Dalarna, Akademin Industri och samhälle, Datateknik.
Högskolan Dalarna, Akademin Industri och samhälle, Datateknik.
Högskolan Dalarna, Akademin Industri och samhälle, Datateknik.
Högskolan Dalarna, Akademin Industri och samhälle, Datateknik.ORCID-id: 0000-0002-1429-2345
2016 (Engelska)Ingår i: American Journal of Intelligent Systems, ISSN 2165-8978, E-ISSN 2165-8994, Vol. 6, nr 1, s. 1-13Artikel i tidskrift (Refereegranskat) Published
Abstract [en]

In a global economy, manufacturers mainly compete with cost efficiency of production, as the price of raw materials are similar worldwide. Heavy industry has two big issues to deal with. On the one hand there is lots of data which needs to be analyzed in an effective manner, and on the other hand making big improvements via investments in cooperate structure or new machinery is neither economically nor physically viable. Machine learning offers a promising way for manufacturers to address both these problems as they are in an excellent position to employ learning techniques with their massive resource of historical production data. However, choosing modelling a strategy in this setting is far from trivial and this is the objective of this article. The article investigates characteristics of the most popular classifiers used in industry today. Support Vector Machines, Multilayer Perceptron, Decision Trees, Random Forests, and the meta-algorithms Bagging and Boosting are mainly investigated in this work. Lessons from real-world implementations of these learners are also provided together with future directions when different learners are expected to perform well. The importance of feature selection and relevant selection methods in an industrial setting are further investigated. Performance metrics have also been discussed for the sake of completion.

Ort, förlag, år, upplaga, sidor
2016. Vol. 6, nr 1, s. 1-13
Nyckelord [en]
Heavy Process Manufacturing, Machine Learning, SVM, MLP, DT, RF, Feature Selection, Calibration
Nationell ämneskategori
Signalbehandling
Forskningsämne
Komplexa system - mikrodataanalys
Identifikatorer
URN: urn:nbn:se:du-21490DOI: 10.5923/j.ajis.20160601.01OAI: oai:DiVA.org:du-21490DiVA, id: diva2:931020
Tillgänglig från: 2016-05-26 Skapad: 2016-05-26 Senast uppdaterad: 2019-10-17Bibliografiskt granskad

Open Access i DiVA

fulltext(524 kB)336 nedladdningar
Filinformation
Filnamn FULLTEXT02.pdfFilstorlek 524 kBChecksumma SHA-512
e363c3047f25569cb5a8a0fd2588d02531d3c5aeb8534cd3dfafef4f5f6cc504ad942aa3f318b087c589bed45b86e199b99497e446961544b581f396ef9fcf95
Typ fulltextMimetyp application/pdf

Övriga länkar

Förlagets fulltext

Personposter BETA

Hansson, KarlYella, SirilDougherty, MarkFleyeh, Hasan

Sök vidare i DiVA

Av författaren/redaktören
Hansson, KarlYella, SirilDougherty, MarkFleyeh, Hasan
Av organisationen
Datateknik
I samma tidskrift
American Journal of Intelligent Systems
Signalbehandling

Sök vidare utanför DiVA

GoogleGoogle Scholar
Totalt: 426 nedladdningar
Antalet nedladdningar är summan av nedladdningar för alla fulltexter. Det kan inkludera t.ex tidigare versioner som nu inte längre är tillgängliga.

doi
urn-nbn

Altmetricpoäng

doi
urn-nbn
Totalt: 1419 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • chicago-author-date
  • chicago-note-bibliography
  • 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