Machine learning for the optimization of porosity-hygroscopy correlations of porous geopolymers in indoor thermal comfort: A hybrid feature selection approach
Published in Open Ceramics, 2025
This work combines machine learning with materials science to optimize sustainable building materials. We develop a hybrid feature selection methodology to identify key porosity-hygroscopy correlations in geopolymer matrices, contributing to energy-efficient indoor thermal comfort solutions through AI-driven material optimization.
Recommended citation: L. Tiogning-Djiogue, H. Tcheneghon Motcheyo, E. Kamseu, et al. (2025). "Machine learning for the optimization of porosity-hygroscopy correlations of porous geopolymers in indoor thermal comfort: A hybrid feature selection approach." Open Ceramics.
Download Paper