Table 3 Obtained accuracy results of the proposed HGR model compared with other works.
From: A Deep Q-Network based hand gesture recognition system for control of robotic platforms
Approach | Signal | Classification accuracy (%) |
|---|---|---|
DQN and CNN-based agent (our RL method) | EMG-IMU | \(97.45 \pm 1.02\) |
Q-learning and ANN (RL)24 | EMG | 90.78 |
SMV classifier with orientation correction (ML)44 | EMG | 92.4 |
SMV classifier with orientation correction (ML)7 | EMG | 94.9 |
SMV classifier (ML)7 | EMG | 81.2 |
K-NN with dynamic warping (ML)20 | EMG | 89.5 |
K-NN classifier (ML)12 | EMG | 86 |
