A Hybrid Feature Selection Scheme Based on Local Compactness and Global Separability for Improving Roller Bearing Diagnostic Performance

Engineering

• Class Separability 33%
• Classification Accuracy 66%
• Experimental Result 33%
• Fault Diagnosis 33%
• Feature Extraction 100%
• Hybrid Model 33%
• Metrics 33%
• Performance Improvement 33%
• Rolling Element 33%
• Selection Algorithm 33%
• Selection Method 33%
• Separability 100%
• Support Vector Machine 33%

Computer Science

• Algorithm Selection 33%
• Classification Accuracy 66%
• Evaluation Metric 33%
• Experimental Result 33%
• Fault Diagnosis 33%
• Feature Selection 100%
• Performance Improvement 33%
• Sequential Forward 33%
• Support Vector Machine 33%