首页|Study Data from University of Technology Update Knowledge of Machine Learning (P redicting the Compressive Strength of Engineered Geopolymer Composites Using Aut omated Machine Learning)
Study Data from University of Technology Update Knowledge of Machine Learning (P redicting the Compressive Strength of Engineered Geopolymer Composites Using Aut omated Machine Learning)
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
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – A new study on Machine Learning is now available. According to news reporting out of Seri Iskandar, Malaysia, by NewsR x editors, research stated, “Engineered Geopolymer Composites (EGC) offer a sust ainable and high-performance alternative to traditional concrete and Engineered Cementitious Composites, boasting reduced environmental impact and enhanced mech anical properties. However, optimising EGC mix design for specific applications requires an accurate prediction of its compressive strength.” Financial support for this research came from Universiti Teknologi PETRONAS Mala ysia. Our news journalists obtained a quote from the research from the University of T echnology, “This study investigates the application of Automated Machine Learnin g using the PyCaret library to develop reliable predictive models for EGC compre ssive strength. A comprehensive experimental program was conducted, testing 132 EGC specimens with varying mix design parameters, including binder ratio, silica fume content, activator ratio, water content, superplasticizer dosage, and curi ng method. The collected data was used to train and evaluate twenty different ma chine learning models. Model performance was assessed using various metrics. The top six models were shortlisted and optimised using Random Search algorithm. Th e models were assessed through a detailed analysis of their residual plots and l earning curves. Additionally, Feature importance and SHAP analysis were employed to understand the influence of each input parameter on the predicted compressiv e strength. The results demonstrate the effectiveness of AML in accurately predi cting EGC compressive strength, with the Gradient Boosting Regressor and CatBoos t Regressor models exhibiting superior performance, achieving Mean Absolute Erro r (MAE) below 1.2 MPa and R2 exceeding 0.96.”
Seri IskandarMalaysiaAsiaCyborgsEmerging TechnologiesEngineeringMachine LearningUniversity of Technology
NETL
NSTL
