Implement machine learning methods on the compressive strength of cement concrete material

Created by W.Langdon from gp-bibliography.bib Revision:1.8414

@Article{Nguyen:2025:trpro,

• author = "Van-Hung Nguyen and Truong Dinh {Thao Anh} and Tien-Dung Nguyen and Ba-Anh Le and Bao-Viet Tran and Viet-Hung Vu",
• title = "Implement machine learning methods on the compressive strength of cement concrete material",
• journal = "Transportation Research Procedia",
• year = "2025",
• volume = "85",
• pages = "241--247",
• note = "TRPRO SDCAT 2023",
• keywords = "genetic algorithms, genetic programming, symbolic regression, compressive strength, machine learning, concrete",
• ISSN = "2352-1465",
• URL = "https://www.sciencedirect.com/science/article/pii/S2352146525002170",
• DOI = "doi:10.1016/j.trpro.2025.03.158",
• abstract = "In this study, we investigate the implementation of genetic programming-based symbolic regression models for predicting the compressive strengths of both normal and high-performance concrete. The three predictive genetic programming algorithms Operon, GP-GOMEA, and GPLearn are selected based on the results presented in SRBench, a comprehensive and continually updated benchmark for symbolic regression. Using Yeh's dataset on the compressive strength of conventional concrete, we use the models to yield interesting results. The results show that the Operon model outperforms the others in terms of trade-off between accuracy and model complexity while significantly reducing computational requirements",

}

Genetic Programming entries for Van-Hung Nguyen Truong Dinh Thao Anh Tien-Dung Nguyen Ba-Anh Le Bao-Viet Tran Viet-Hung Vu

Citations