A Distance-Based Weighted Undersampling Scheme for Support Vector Machines and its Application to Imbalanced Classification

Keyphrases

• Support Vector Machine 100%
• Undersampling 100%
• Distance-based 100%
• Imbalanced Classification 100%
• Computational Complexity 16%
• Popular 16%
• Data Distribution 16%
• Soaring 16%
• Area under the Curve 16%
• Euclidean Distance 16%
• Comprehensive Experiment 16%
• Class Imbalance 16%
• State-of-the-art Techniques 16%
• Classification Performance 16%
• Improved Algorithm 16%
• Distribution Information 16%
• Local Minima 16%
• Sampling Process 16%
• Hyperplane 16%
• Overfitting 16%
• Good Reputation 16%
• Imbalance Problem 16%
• Large-scale Samples 16%
• F-measure 16%
• G-mean 16%
• Space Geometry 16%
• Binary Class 16%
• Structural Risk Minimization 16%
• Multi-class 16%
• Traditional Machine Learning 16%
• Highest Weight 16%
• Data Imbalance Problem 16%

Computer Science

• Support Vector Machine 100%
• Computational Complexity 16%
• Machine Learning 16%
• Data Distribution 16%
• Support Vector Machine 16%
• Euclidean Distance 16%
• Class Imbalance 16%
• Classification Performance 16%
• Distribution Information 16%
• Local Minimum 16%
• Random Sampling Process 16%
• Risk Minimization 16%

Mathematics

• Support Vector Machine 100%
• Euclidean Distance 16%
• Local Minimum 16%
• Data Distribution 16%
• Structural Risk Minimization 16%
• Original Data Set 16%
• Distance Geometry 16%