EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Fiber Reinforcement Mechanisms and Intelligent AI-based evolutionary Modeling for High-Strength Glass Fiber Concrete Incorporating Nano silica and Aluminum Sulphate

Amirhossein Hojati

Journal of Intelligent Decision Making and Information Science · 09.09.2026 · 3 (18s) · 1149-1175

DOI: 10.17762/jidmis.v3.5835 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Intelligent Decision Making and Information Science, online erschienen am 09.09.2026. Verfasst von Amirhossein Hojati. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate prediction of concrete compressive strength is essential for the efficient design and performance assessment of concrete mixtures. However, the complex and nonlinear relationships among mixture constituents, material proportions, and curing age can limit the predictive capability of conventional regression models. This study investigates the application of the Multivariate Adaptive Regression Splines (MARS) method and proposes a hybrid MARS–CH-ALOAO framework to improve the prediction of concrete compressive strength. The proposed framework integrates the Ant Lion Optimizer (ALO) and Aquila Optimizer (AO) algorithms through a chaos-based optimization strategy to identify suitable MARS model parameters and improve predictive performance. A reference dataset comprising 1,030 observations from the University of California, Irvine (UCI) Machine Learning Repository was considered alongside 57 experimental observations obtained from the investigated concrete mixtures. Model performance was evaluated using the correlation coefficient (R), root mean square error (RMSE), and mean absolute error (MAE) across the training, testing, and validation stages. The results indicate that the hybrid model outperformed the standalone MARS model during training, increasing R from 0.901 to 0.939 and reducing RMSE from 28.703 to 19.416 MPa and MAE from 4.64 to 3.13 MPa. The reported testing results also showed improvements in predictive performance, with the hybrid model achieving an R value of 0.911, an RMSE of 22.605 MPa, and an MAE of 3.66 MPa. Overall, the findings demonstrate the potential of combining MARS with hybrid metaheuristic optimization to improve the prediction of concrete compressive strength. Nevertheless, further verification of the dataset partitioning and reported statistical indices is necessary to establish the robustness and generalizability of the proposed framework.

Zitieren

APA

Hojati, A. (2026). Fiber Reinforcement Mechanisms and Intelligent AI-based evolutionary Modeling for High-Strength Glass Fiber Concrete Incorporating Nano silica and Aluminum Sulphate. Journal of Intelligent Decision Making and Information Science, 3(18s), 1149-1175. https://doi.org/10.17762/jidmis.v3.5835

Vancouver

Hojati A. Fiber Reinforcement Mechanisms and Intelligent AI-based evolutionary Modeling for High-Strength Glass Fiber Concrete Incorporating Nano silica and Aluminum Sulphate. Journal of Intelligent Decision Making and Information Science. 2026;3(18s):1149-1175. doi:10.17762/jidmis.v3.5835

BibTeX
@article{Hojati2026,
  author = {Hojati, Amirhossein},
  title = {Fiber Reinforcement Mechanisms and Intelligent AI-based evolutionary Modeling for High-Strength Glass Fiber Concrete Incorporating Nano silica and Aluminum Sulphate},
  journal = {Journal of Intelligent Decision Making and Information Science},
  year = {2026},
  volume = {3},
  number = {18s},
  pages = {1149--1175},
  doi = {10.17762/jidmis.v3.5835}
}
Kostenlos starten →