Using Ensemble Data Mining Modelling for Nonbinary Overflow Detection in Urban Flooding

Keyphrases

• Classification Ensemble 14%
• Confusion Matrix 14%
• Data Mining Techniques 28%
• Data-driven Modeling 14%
• Decision Tree 14%
• Decision Tree Structure 14%
• Discriminant Analysis 14%
• Ensemble Data Mining 100%
• Ensemble Model 57%
• Flood Occurrence 14%
• Flood Risk Management 14%
• Flood Warning System 14%
• Gaussian Process Regression 14%
• Hazard Situations 14%
• Hybrid Data Mining 14%
• K-nearest 28%
• Key Performance Indicators 14%
• Machine Learning Models 14%
• Miss Rate 28%
• Model Accuracy 14%
• Multi-classification 14%
• Nagging 14%
• Nave Bayes 14%
• Neural Network Classifier 14%
• Nonbinary 100%
• Overflow 28%
• Overflow Monitoring 100%
• Partial Least Squares Analysis 14%
• Performance Assessment 14%
• Positive Ratio 14%
• Rainfall 42%
• Rainfall Duration 14%
• Rainfall Features 28%
• Rainfall Intensity 14%
• Rainfall Occurrence 28%
• Random Forest 14%
• Socio-economic Impact 14%
• Support Vector Machine 14%
• Sustainable Solutions 14%
• Time Concepts 14%
• Urban Drainage System 14%
• Urban Flooding 100%
• Warning Alarm 14%
• Water Level Prediction 14%
• Water Surface Elevation 28%
• Weak Learner 14%

Earth and Planetary Sciences

• Discriminant Analysis 50%
• Drainage System 50%
• Kriging 50%
• London 50%
• Machine Learning 50%
• Performance Assessment 50%
• Precipitation Intensity 50%
• Real Time 50%
• Risk Management 50%
• Support Vector Machine 50%
• Time Series 100%
• United Kingdom 50%
• Urban Drainage 50%
• Urban Flooding 100%