Medoid-based MLP: an application to wood sawing simulator metamodeling - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Medoid-based MLP: an application to wood sawing simulator metamodeling

Résumé

Predicting the set of lumbers which would be obtained from sawing a log at a specific sawmill is a difficult problem, which complicates short and mid term decision making in this industry. While sawmill simulators able to simulate the sawing of a log from a 3D scan of its outer shape exist, they can be extremely computationally intensive. Several alternative approaches based on machine learning algorithms and different set of features were explored in previous works. This paper proposes the use of one hidden layer perceptrons, and a vector of features build from dissimilarities from the scans to a set of selected wood logs, chosen as the class medoids. Several architectures are tested and compared to validate the pertinence of the proposed set of medoid-based features. The lowest mean squared error was obtained for MISO neural networks with a sigmoid output activation function, to constrain the output value ranges.
Fichier principal
Vignette du fichier
NCTA(5).pdf (455.65 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03404548 , version 1 (26-10-2021)

Licence

Paternité - Pas d'utilisation commerciale - Pas de modification

Identifiants

  • HAL Id : hal-03404548 , version 1

Citer

Sylvain Chabanet, Philippe Thomas, Hind Bril El-Haouzi. Medoid-based MLP: an application to wood sawing simulator metamodeling. 13th International Conference on Neural Computation Theory and Applications, NCTA 2021, Oct 2021, Online streaming, Portugal. ⟨hal-03404548⟩
43 Consultations
73 Téléchargements

Partager

Gmail Facebook X LinkedIn More