Investigating the effectiveness of hybrid gradient boosting models and optimization algorithms for concrete strength prediction

Keyphrases

• Optimization Algorithm 100%
• R2 Value 100%
• Modeling Algorithm 100%
• Light Gradient Boosting Machine 100%
• CatBoost 100%
• Gradient Boosting Model 100%
• Concrete Strength Prediction 100%
• Gradient Boosting Regressor 100%
• Hybrid Gradient 100%
• Machine Learning Models 66%
• Random Forest 66%
• Process Optimization 66%
• XGBoost 66%
• Best Model 33%
• Web Browser 33%
• Gaussian Process 33%
• Cement Content 33%
• Compressive Strength 33%
• Surrogate Model 33%
• Categorical Features 33%
• Hyperparameters 33%
• Hybrid Machine Learning 33%
• Extreme Gradient Boosting(XGBoost) 33%
• Adaptive Boosting 33%
• Fly Ash 33%
• Bayesian Optimization 33%
• Gradient Boosting 33%
• Least Squares Support Vector Regression (LSSVR) 33%
• Gradient Boosting Decision Tree 33%
• Standout 33%
• Concrete Compressive Strength 33%
• Shapley Additive Explanations 33%
• Concrete Types 33%
• Gaussian Random 33%
• Curing Age 33%
• Random Search Optimization 33%

Engineering

• Learning System 100%
• Regressors 100%
• Light Gradient Boosting Machine 100%
• Concrete Strength 100%
• Xgboost 100%
• Compression Strength 66%
• Compressive Strength 66%
• Random Forest 66%
• Testing Dataset 66%
• Gaussians 33%
• Support Vector Machine 33%
• Data Sample 33%
• Cement Content 33%
• Surrogate Model 33%

Chemical Engineering

• Learning System 100%
• Xgboost 100%
• Support Vector Machine 33%
• Bayesian Optimization 33%