Study of stability of time-domain features for electromyographic pattern recognition

Keyphrases

• Autoregressive Coefficients 16%
• Cepstral Coefficients 16%
• Classification Accuracy 16%
• Classification Performance 33%
• Classifier Training 16%
• Clinical Application 16%
• Contact Location 16%
• Effort Level 16%
• Electrode Contact 16%
• Electrode Location 33%
• Electromyographic Patterns 100%
• Electromyography 100%
• Electromyography Signal 66%
• Feature Combination 33%
• High Classification Accuracy 16%
• Human-machine Interface 33%
• Location Shifts 33%
• Motor Deficits 16%
• Muscle Contraction 16%
• Muscle Fatigue 33%
• Pattern Classification 16%
• Pattern Recognition 100%
• Physical Changes 16%
• Physical Experiment 16%
• Physiological Changes 16%
• Real-world Challenges 16%
• Rehabilitation Goals 16%
• Robust Classification 16%
• Simple Solution 16%
• Stability Index 16%
• Stable Set 16%
• Time Domain Features 100%
• Training Strategy 16%

Engineering

• Autoregression 25%
• Classification Accuracy 50%
• Classification Performance 50%
• Clinical Application 25%
• Domain Feature 100%
• Electrode Contact 25%
• Human-Machine Interface 50%
• Pattern Recognition 100%
• Time Domain 100%

Computer Science

• Classification Accuracy 50%
• Classification Performance 50%
• Clinical Application 25%
• Domain Feature 100%
• Feature Individual 25%
• Human Machine Interface 50%
• Location Shift 50%
• Pattern Classification 25%
• Pattern Recognition 100%
• Stability Index 25%