Application of Neural Network Tools in Process Mining
  • Metaadatok
Tartalom: http://real.mtak.hu/173590/
Archívum: REAL
Gyűjtemény: Status = Published
Type = Article
Subject = Q Science / természettudomány: QA Mathematics / matematika: QA76.527 Network technologies / Internetworking / hálózati technológiák, hálózatosodás
Cím:
Application of Neural Network Tools in Process Mining
Létrehozó:
Kovács, László
Baksáné Varga, Erika
Mileff, Péter
Kiadó:
Scientific Association for Infocommunications, Hungary (HTE)
Dátum:
2023
Téma:
QA76.527 Network technologies / Internetworking / hálózati technológiák, hálózatosodás
Tartalmi leírás:
Dominant current technologies in process mining use schema induction approaches based on graph and au- tomaton methods. The paper investigates the application of neural network approaches in schema induction focusing on three alternative architectures: MLP, CNN and LSTM networks. The proposed neural network models can be used to discover XOR, loop and parallel execution templates. In the case of loop detection, the performed test analyses show the dominance of CNN approach where the string is represented with a two- dimensional similarity matrix. The usability of the proposed approach is demonstrated with test examples.
Nyelv:
angol
Típus:
Article
PeerReviewed
info:eu-repo/semantics/article
Formátum:
text
Azonosító:
Kovács, László and Baksáné Varga, Erika and Mileff, Péter (2023) Application of Neural Network Tools in Process Mining. INFOCOMMUNICATIONS JOURNAL : A PUBLICATION OF THE SCIENTIFIC ASSOCIATION FOR INFOCOMMUNICATIONS (HTE), 15 (SI). pp. 13-19. ISSN 2061-2079
Kapcsolat:
MTMT:34130341 10.36244/ICJ.2023.5.3