Research Article

Feature Extraction of Surface Electromyography Using Wavelet Weighted Permutation Entropy for Hand Movement Recognition

Table 2

Recognition accuracies of d3 and undecomposed sEMG for the seven hand movements (×100%).

Hand movementd3 (PE/WPE)Undecomposed sEMG(PE/WPE)
SVMBPNNSVMBPNN

Open0.64/0.710.77/1.000.87/0.921.00/0.62
Close0.62/0.870.69/1.001.00/0.830.92/0.62
Point0.71/0.820.85/0.920.82/1.000.85/0.92
Ok0.78/0.790.38/0.850.90/0.800.54/0.77
Yeah0.76/0.920.92/0.770.69/0.920.92/1.00
Tripod0.92/0.890.92/0.920.92/0.930.62/1.00
Grip0.88/1.000.54/0.690.80/0.920.38/0.85