Soft Computing Approach for Predicting the Effects of Waste Rubber-Bitumen Interaction Phenomena on the Viscosity of Rubberized Bitumen

Created by W.Langdon from gp-bibliography.bib Revision:1.8129

@Article{lanotte:2022:Sustainability,

• author = "Michele Lanotte",
• title = "Soft Computing Approach for Predicting the Effects of Waste Rubber-Bitumen Interaction Phenomena on the Viscosity of Rubberized Bitumen",
• journal = "Sustainability",
• year = "2022",
• volume = "14",
• number = "21",
• pages = "Article No. 13798",
• keywords = "genetic algorithms, genetic programming",
• ISSN = "2071-1050",
• URL = "https://www.mdpi.com/2071-1050/14/21/13798",
• DOI = "doi:10.3390/su142113798",
• abstract = "The ability to anticipate the effects of the interaction between waste rubber particles from end-of-life tires and bitumen can encourage the use of rubberized bitumen, a material with proven environmental benefits, in civil engineering applications. In this study, a predictive model of rubberized bitumen viscosity is presented for this purpose. A machine learning-based approach (Multi-Gene Genetic Programming—MGGP) and a more traditional multi-variable least square regression (MLSR) method are compared. The statistical analysis indicates that the robustness and the capability of the MGGP algorithm led to a better estimation of the rubberized bitumen’s viscosity. Additionally, the MGGP analysis returned an actual equation that could be easily implemented in any spreadsheet for an initial tuning of the production protocol based on the desired level of interaction between the rubber and bitumen.",
• notes = "also known as \cite{su142113798}",

}

Genetic Programming entries for Michele Lanotte

Citations