Quantitative relationship between feature extraction of sEMG and upper limb elbow joint angle

Feature extraction is an important part in the classifier systems. In this study, feature extraction was used to extract the information of the surface electromyography (sEMG) and to predict upper limb elbow joint angle. To predict the upper limb elbow joint angle, we explored the EMG signal characteristics on biceps, triceps lateral head and triceps long head. Time domain of feature extraction is still the best feature extraction to get the information on signal in a real time processing. Feature extraction, RMS, MAV, I EMG, ZC, VAR, and SSC are commonly used by researchers to extract feature in sEMG. The quantification of the relationship between feature extraction and elbow joint angle was measured using the root mean square error (RMSE) and Pearson Correlation Coefficient (CC). In this research, we found that the feature extraction ZC was the best feature extraction in time domain to predict the elbow joint angle, with normalized RMSE 0.187
^o
and CC 0.907. With these findings, it can facilitate the researcher in classifier step to build exoskeleton based EMG control.