首页|University of Melbourne Researchers Provide New Data on Machine Learning (Using ensemble machine learning and metaheuristic optimization for modelling the elast ic modulus of geopolymer concrete)
University of Melbourne Researchers Provide New Data on Machine Learning (Using ensemble machine learning and metaheuristic optimization for modelling the elast ic modulus of geopolymer concrete)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
Fresh data on artificial intelligence are presented in a new report. According to news reporting from Melbourne, Austr alia, by NewsRx journalists, research stated, "Geopolymer concrete emerges as a sustainable and durable alternative to conventional concrete, addressing its hig h carbon footprint and enhanced durability. The distinct properties of geopolyme r concrete, governed by supplementary cementitious materials and alkaline activa tors, promise reduced environmental impact and improved structural resilience." The news editors obtained a quote from the research from University of Melbourne : "However, its complex composition complicates the prediction of mechanical pro perties such as the elastic modulus, crucial for structural applications. This s tudy introduces an innovative approach using the eXtreme Gradient Boosting (XGBo ost) technique integrated with the multi-objective grey wolf optimizer to model the elastic modulus of geopolymer concrete. By dynamically selecting influential features and optimizing model accuracy, this methodology advances beyond tradit ional empirical models, which fail to capture the nonlinear interactions intrins ic to geopolymer concrete. Utilizing a comprehensive database gathered from exte nsive literature, 22 potential variables were examined that influence geopolymer concrete's elastic modulus. After mitigating multicollinearity and optimizing h yperparameters via Bayesian optimization, six XGBoost models were developed with different combinations of input variables, revealing compressive strength and t otal water content as pivotal predictors. The findings illustrate the models' pr ecision, with the trade-off between prediction accuracy and model simplicity vis ualized through the relationship between the number of input variables and predi ction error. The study culminates in a user-friendly graphical user interface th at enables easy prediction of geopolymer concrete's elastic modulus and fosters educational engagement."
University of MelbourneMelbourneAust raliaAustralia and New ZealandCyborgsEmerging TechnologiesMachine Learni ng
NETL
NSTL
