https://www.mdu.se/

mdu.sePublications
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
USING ARTIFICIAL NETWORKS IN COMPLEX PROBLEMS ANALYSING PARAMETERS INFLUENCE
Mälardalen University, School of Innovation, Design and Engineering.
2023 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
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.

Place, publisher, year, edition, pages
2023. , p. 26
Keywords [en]
Artificial Intelligence (AI), Neural Networks, MLP, Complex Problem, Parameter, Analysis, Football
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:mdh:diva-64459OAI: oai:DiVA.org:mdh-64459DiVA, id: diva2:1802757
Supervisors
Examiners
Available from: 2023-11-07 Created: 2023-10-05 Last updated: 2023-11-07Bibliographically approved

Open Access in DiVA

USING ARTIFICIAL NEURAL NETWORKS IN COMPLEX PROBLEMS FOR ANALYSING PARAMETER INFLUENCE(3699 kB)56 downloads
File information
File name FULLTEXT01.pdfFile size 3699 kBChecksum SHA-512
91521298a38d7bd730bf1fde927314484371a1eb6d4788429d2d323cf0f1fbd16cdb8f05a16e2221950ed1b5686130394708c0c8ebf23e21798f7d6b1fa22dc0
Type fulltextMimetype application/pdf

By organisation
School of Innovation, Design and Engineering
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 56 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 225 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf