A Data-Driven Approach to Evaluate the Compressive Strength of Recycled Aggregate Concrete

Keyphrases

• Data-driven Approach 100%
• Recycled Aggregate Concrete 100%
• Compressive Strength 100%
• Machine Learning Models 50%
• Histogram Gradient Boosting 50%
• Machine Learning Techniques 25%
• Machine Learning Algorithms 25%
• Prediction Accuracy 25%
• Comprehensive Dataset 25%
• Sensitivity Analysis 25%
• Training Set 25%
• Machine Learning Applications 25%
• Feature Selection 25%
• Hyperparameter Tuning 25%
• Machine Learning Training 25%
• Forest-based 25%
• Random Histograms 25%
• Water-cement Ratio 25%
• Root Mean Square Error 25%
• Lasso Regression 25%
• Multiple Linear Regression 25%
• Error Metrics 25%
• Cement Content 25%
• Influential Parameters 25%
• Regression Forest 25%
• Concrete Compressive Strength 25%
• Concrete Testing 25%
• Gradient Boosting Model 25%

Engineering

• Recycled Concrete Aggregate 100%
• Learning System 100%
• Compression Strength 100%
• Compressive Strength 100%
• Histogram 66%
• Metrics 33%
• Machine Learning Algorithm 33%
• Machine Learning Technique 33%
• Feature Extraction 33%
• Test Result 33%
• Root-Mean-Squared Error 33%
• Cement Content 33%
• Input Feature 33%
• Random Forest 33%
• Cement Ratio 33%
• Concrete Compressive Strength 33%
• Recycled Aggregate 33%

Chemical Engineering

• Learning System 100%