Estimation of Finger Joint Angles from sEMG Using a Neural Network Including Time Delay Factor and Recurrent Structure

Figure 3

The estimating system at the training phase and estimating phase. System parameter Syspara represents the parameters set in Figure 2. The main purpose of the training phase is to optimize neural network coefficient data _oW represents high-precision input-output mapping (from sEMG to the finger joint angle dynamics system). During the estimating phase, the estimated angle vector 𝐎_𝑘 is calculated from feature vectors that are not used for training or optimizing _oW.