Self-Paced Ensemble-SHAP Approach for the Classification and Interpretation of Crash Severity in Work Zone Areas

Keyphrases

• Work Zone 100%
• Crash Severity 100%
• Shapley Additive Explanations 100%
• Self-paced Ensemble 100%
• Explanation Approaches 100%
• Machine Learning Models 75%
• Work Zone Crashes 75%
• Crash 50%
• Ensemble Model 50%
• Binary Logistic Regression 50%
• Tree-based Machine Learning 50%
• New Jersey 25%
• Proposed Methodology 25%
• Right Angle 25%
• Causal Factors 25%
• Crash Data 25%
• Classification and Regression Tree 25%
• Class Imbalance 25%
• Imbalanced Classification 25%
• Outcome Prediction 25%
• Severe Crash 25%
• State Highway 25%
• Interpretation System 25%
• Crash Type 25%
• Severe Injury 25%
• Road Safety 25%
• Road System 25%
• Ensemble Framework 25%
• Light Gradient Boosting Machine 25%
• Ensemble Learning Approach 25%
• Influence Degree 25%
• Adaptive Boosting 25%
• Adaptive Classification 25%
• Street Lighting 25%
• Barrier Types 25%

Computer Science

• Machine Learning 100%
• Shapley Additive Explanation 100%
• Binary Logistic Regression 66%
• Learning Approach 33%
• Regression Tree 33%
• Ensemble Learning 33%
• Gradient Boosting 33%
• adaptive boosting 33%

Engineering

• Road 100%
• Learning Approach 50%
• Adaptability 50%
• Marine Safety 50%
• Light Gradient Boosting Machine 50%
• Causative Factor 50%