Performance Analysis of the Windowing Technique on Elbow Joint Angle Estimation Using Electromyography Signal

Abstract

In the digital signal processing, the windowing technique is essential in the feature extraction process because it influences the performance of the proposed models. The objective of this study is to evaluate the performance of the windowing technique in the elbow joint angle estimation based on electromyography (EMG) signal. In the elbow joint angle estimation, the results showed that the window length and percentage of overlap in windowing technique affected the performance of the estimation for all time-domain features. In the adjacent windowing technique, a window length of 100 milliseconds has the highest performance in estimation. In the overlap windowing technique, the percentage of overlap is 10% .It is the highest performance of the estimation. Features ZC, SSC, WAMP, and MYOP have better RMSE than the others. In the window length of 100 milliseconds, the mean and standard deviation of RMSE for the features ZC, SSC, WAMP, and MYOP are 14.41°±3.86°, 15.20°±4.59°, 14.50°±3.33° and 13.56°±3.53°, respectively.