Medoid-based MLP: An Application to Wood Sawing Simulator Metamodeling

Sylvain Chabanet, Philippe Thomas, Hind Bril El-Haouzi

2021

Abstract

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.

Paper Citation

in Harvard Style

Chabanet S., Thomas P. and Bril El-Haouzi H. (2021). Medoid-based MLP: An Application to Wood Sawing Simulator Metamodeling. In Proceedings of the 13th International Joint Conference on Computational Intelligence (IJCCI 2021) - Volume 1: NCTA; ISBN 978-989-758-534-0, SciTePress, pages 201-210. DOI: 10.5220/0010651400003063

in Bibtex Style

@conference{ncta21,
author={Sylvain Chabanet and Philippe Thomas and Hind Bril El-Haouzi},
title={Medoid-based MLP: An Application to Wood Sawing Simulator Metamodeling},
booktitle={Proceedings of the 13th International Joint Conference on Computational Intelligence (IJCCI 2021) - Volume 1: NCTA},
year={2021},
pages={201-210},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010651400003063},
isbn={978-989-758-534-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Computational Intelligence (IJCCI 2021) - Volume 1: NCTA
TI - Medoid-based MLP: An Application to Wood Sawing Simulator Metamodeling
SN - 978-989-758-534-0
AU - Chabanet S.
AU - Thomas P.
AU - Bril El-Haouzi H.
PY - 2021
SP - 201
EP - 210
DO - 10.5220/0010651400003063
PB - SciTePress