Estimating Optimal Additive Content for Soil Stabilization Using Machine Learning Methods

Keyphrases

• Machine Learning Techniques 100%
• Additive Content 100%
• Unconfined Compressive Strength 100%
• Soil Stabilization 100%
• False Positive Rate 66%
• Soil Properties 33%
• Machine Learning Models 33%
• Logistic Regression 33%
• Pavement 33%
• Discriminant Analysis 33%
• Soil Survey Geographic Database (SSURGO) 33%
• Statistical Classification 33%
• Prediction Accuracy 33%
• Model-driven Development 33%
• Laboratory Work 33%
• Stabilizer 33%
• Chemical Stabilization 33%
• Subgrade 33%
• Discrete Field 33%
• Correctness Prediction 33%
• Stabilized Soil 33%
• Collection Strategy 33%
• Additive Type 33%
• K-nearest 33%
• Treatment Type 33%
• Area under the Curve 33%
• Field Sampling 33%
• Support Vector Machine 33%
• 5-fold Cross Validation 33%
• Multiple Trials 33%
• Strength Requirement 33%
• Atterberg Limits 33%
• Prediction Rate 33%

Engineering

• Compression Strength 100%
• Soil Stabilization 100%
• Machine Learning Method 100%
• Compressive Strength 100%
• Additive Content 100%
• Learning System 33%
• Pavement 33%
• Stabilised Soil 33%
• Subgrade 33%
• Base Material 33%
• Stabilizer 33%
• Statistical Study 33%
• Atterberg Limit 33%
• Support Vector Machine 33%
• Nearest Neighbor 33%
• Strength Requirement 33%

Material Science

• Compressive Strength 100%
• Stabilizer (Agent) 33%
• Pavement 33%
• Geotechnology 33%
• Discriminant Analysis 33%