Table 3.
Offline error rates using bilateral sensor information to control a powered leg prosthesis with an intent recognition framework.
| Steady-state (%) | Transitional (%) | Overall (%) | ||
|---|---|---|---|---|
| 1. | Prosthesis only | 0.53 | 3.75 | 0.90 |
| 2. | Prosthesis, Contra Shank | 0.36 | 3.00 | 0.67 |
| 3. | Prosthesis, Contra Shank† | 1.26 | 4.99 | 1.69 |
| 4. | Prosthesis, Contra Thigh | 0.30 | 2.50 | 0.55 |
| 5. | Prosthesis, Contra Thigh† | 1.42 | 3.99 | 1.72 |
| 6. | Prosthesis, Contra Thigh/Shank | 0.20 | 1.50 | 0.35 |
| 7. | Prosthesis, Contra Thigh/Shank† | 1.02 | 3.49 | 1.31 |
| 8. | Prosthesis, Contra Thigh/Shank ▾ | 0.53 | 3.74 | 0.90 |
| Total decisions | 3,027 | 400 | 3,427 |
Error rates are shown for different mode-specific classifier configurations with varying amounts of kinematic information from the non-prosthesis side. The total number of classifier decisions for each step type is also shown in the bottom row.
†
Control system neither merges LW and RA classes nor includes 90 ms delay.
▾
Control system neither merges LW and RA classes nor includes 90 ms delay; toe off classifier uses prosthesis signals only.