Adapting Random Forest Classifier Based on Single and Multiple Features for Surface Electromyography Signal Recognition

Keyphrases

• Multi-feature 100%
• Random Forest Classifier 100%
• Surface Electromyography (sEMG) 100%
• Signal Recognition 100%
• Single Feature 100%
• Signal Model 50%
• Performance Metrics 25%
• Learning Process 25%
• Human Expert 25%
• Surgeons 25%
• Control Problem 25%
• Control Model 25%
• Classification Accuracy 25%
• Finger Movement 25%
• Training Process 25%
• Pattern Recognition 25%
• Real-time Integration 25%
• Interventional Robot 25%
• Reliable Signals 25%
• Ninapro 25%
• Motion Classification 25%
• Robotic Intervention 25%
• Robotic Mechanism 25%
• Hand Gesture Recognition 25%
• Effective Surface 25%
• Surgical Systems 25%
• Mechanical Control 25%
• Intravascular Procedures 25%
• Real-time Decoding 25%

Engineering

• Random Forest 100%
• Robot 66%
• Signal Model 66%
• Experimental Result 33%
• Mechanical Systems 33%
• Control Model 33%
• Classification Accuracy 33%
• Metrics 33%
• Pattern Recognition 33%
• Human Expert 33%
• Single Feature 33%

Computer Science

• Random Forest Classifier 100%
• Electromyography 100%
• Robot 50%
• Experimental Result 25%
• Performance Metric 25%
• Learning Process 25%
• Classification Accuracy 25%
• Training Process 25%
• Pattern Recognition 25%
• Single Feature 25%