Research Article
A Neuromuscular Interface for Robotic Devices Control
Table 1
Comparison of various myoelectric control devices.
| Indicator measured | NI | Fougner et al., 2012, [16] | Wurth et al., 2014, [17] | Jiang et al., 2012, [18] | Hahne et al., 2014, [19] | Hahne et al., 2016, [4] | Earley et al., 2016, [6] |
| Average recognition accuracy | 92.5% | - | 96% | >90% | - | ~90% | - |
| Control | Command and proportional | Consistent proportional | Motion pattern recognition. Proportional | Proportional | Proportional | Command and proportional | Motion pattern recognition. Proportional |
| Classifier | ANN (perceptron) | LDA | LDA | ANN (perceptron) | ANN (perceptron) | Linear regression | LDA |
| Number of gestures / degrees of freedom (DoF) | 9 gestures | 5 gestures | 2 DoF, 5 gestures | 3 DoF | 2 DoF, 4 gestures | 2 DoF, 4 gestures | 8 gestures |
| Number of EMG channels /sensors | 8 for recording + 1 reference | 5 | 6 | 7 pairs for each forearm | 192-channel electrode array in the monopolar configuration | 4 for each type of electrode | 12 pairs of bipolar electrodes |
|
|