https://www.mdu.se/

mdh.sePublikasjoner
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
DISTRIBUTED ARTIFICIAL INTELLIGENCE FOR ANOMALY DETECTION IN A MODULAR MANUFACTURING ENVIRONMENT
Mälardalens universitet, Akademin för innovation, design och teknik. Mälardalen University.
2023 (engelsk)Independent thesis Advanced level (degree of Master (One Year)), 10 poäng / 15 hpOppgave
Abstract [en]

This thesis investigates anomaly detection and classification in a simulated modular manufacturingenvironment using Machine Learning algorithm Random Forest. This algorithm is tested on a localcomputer and an embedded device, specifically the Raspberry PI. The performance of Random Forestmodels is evaluated for anomaly detection and classification tasks, considering different evaluationmetrics and execution time. The results indicate variations in model performance across differentmodules and classification tasks. It is observed that the limited computing resources of the RaspberryPI for anomaly detection tasks lead to significantly higher prediction times compared to a computer,highlighting the impact of embedded systems’ constraints on ML model execution

sted, utgiver, år, opplag, sider
2023. , s. 45
HSV kategori
Identifikatorer
URN: urn:nbn:se:mdh:diva-64579OAI: oai:DiVA.org:mdh-64579DiVA, id: diva2:1807076
Fag / kurs
Computer Science
Veileder
Examiner
Tilgjengelig fra: 2023-10-25 Laget: 2023-10-24 Sist oppdatert: 2023-10-25bibliografisk kontrollert

Open Access i DiVA

fulltext(1896 kB)169 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 1896 kBChecksum SHA-512
7b3cf830f77f34d7a3ff734f2009d329273b62cbf575d5756c9d57c7612152676f81ff23458a3a54d53fa67b819518f945937aa9ec15db3cc2464eff1b8a64cc
Type fulltextMimetype application/pdf

Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 169 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

urn-nbn

Altmetric

urn-nbn
Totalt: 425 treff
RefereraExporteraLink to record
Permanent link

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