https://www.mdu.se/

mdh.sePublikasjoner
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
USING ARTIFICIAL NETWORKS IN COMPLEX PROBLEMS ANALYSING PARAMETERS INFLUENCE
Mälardalens universitet, Akademin för innovation, design och teknik.
2023 (engelsk)Independent thesis Basic level (degree of Bachelor), 10 poäng / 15 hpOppgave
Abstract [en]

Mathematical statistical models are insufficient for describing complex phenomena. In contrast, Artificial Neural Networks (ANNs), have been used across various complex problem domains for solving problems. ANNs can learn complex patterns and capture non-linear relationships between parameters. Using ANNs to gain an understanding of complex problem domains can reveal hidden truths and lead to scientific discoveries not possible before with mathematical statistical models. In this thesis, a fully connected feed-forward neural network was built to analyse the parameter influence in the complex problem domain of football. The aim of this work was to demonstrate that a simple artificial neural network could be used to analyse parameter influence in complex problem domains. The investigation centred around the question of: How well can the fully connected feed-forward neural network be used for analysing parameter influence. To conduct this research, free publicly available statistical match data was gathered from online sources. Subsequently, an ANN model was built and trained to predict the outcomes of the Spanish La Liga matches during the 2021/2022 season. The network could achieve an average accuracy of 51.57\%, comparable to similar models in related studies. After the network was trained the weights were analysed to understand the influence of parameters on the outcomes of matches. The results obtained were random, indicating that this specific approach taken, requires a larger dataset. A different approach with a different type of network would be more suitable for this undertaking.

sted, utgiver, år, opplag, sider
2023. , s. 26
Emneord [en]
Artificial Intelligence (AI), Neural Networks, MLP, Complex Problem, Parameter, Analysis, Football
HSV kategori
Identifikatorer
URN: urn:nbn:se:mdh:diva-64459OAI: oai:DiVA.org:mdh-64459DiVA, id: diva2:1802757
Veileder
Examiner
Tilgjengelig fra: 2023-11-07 Laget: 2023-10-05 Sist oppdatert: 2023-11-07bibliografisk kontrollert

Open Access i DiVA

USING ARTIFICIAL NEURAL NETWORKS IN COMPLEX PROBLEMS FOR ANALYSING PARAMETER INFLUENCE(3699 kB)69 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 3699 kBChecksum SHA-512
91521298a38d7bd730bf1fde927314484371a1eb6d4788429d2d323cf0f1fbd16cdb8f05a16e2221950ed1b5686130394708c0c8ebf23e21798f7d6b1fa22dc0
Type fulltextMimetype application/pdf

Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 69 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: 225 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