The effectiveness of data augmentation in compressive strength prediction of calcined clay cements using linear regression learning - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2023

The effectiveness of data augmentation in compressive strength prediction of calcined clay cements using linear regression learning

Résumé

Cement production is a major contributor to global CO2 emissions. To minimize its environmental impact while maintaining the required mechanical properties of cement, there is a pressing need for sustainable production processes. This paper explores the use of data augmentation techniques, specifically the copulas method, to improve the performance of linear regression models for linking the compressive strength of LC3 with its mix design. While data augmentation using copulas can be useful in augmenting tabular data, its effectiveness in improving linear regression performance may depend on the statistical characteristics of the original data. The method successfully generated additional data that preserved the original statistical properties, but it did not always lead to significant improvements in linear regression performance. The research highlights the potential of data-driven models for optimizing cement materials properties and emphasizes the importance of considering the statistical characteristics of the original data when applying data augmentation techniques.
Fichier principal
Vignette du fichier
Pre-print_P1-592_revised.pdf (274.25 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04166948 , version 1 (20-07-2023)

Identifiants

Citer

Yassine El Khessaimi, Youssef El Hafiane, Agnès Smith, Karim Tamine, Samir Adly, et al.. The effectiveness of data augmentation in compressive strength prediction of calcined clay cements using linear regression learning. 2023. ⟨hal-04166948⟩
54 Consultations
35 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More