Table II.
Dataset | Model | Correlation Coefficient |
||
---|---|---|---|---|
mlGRFa | apGRFa | vGRFa | ||
| ||||
Overground Walking | Supervised Learning Baseline | 0.94 ± 0.03 | 0.93 ± 0.02 | 0.92 ± 0.03 |
Motion Transfer Pre-training | 0.95 ± 0.02 | 0.93 ± 0.02 | 0.93 ± 0.03 | |
Task Transfer Pre-training | 0.96 ± 0.01 | 0.94 ± 0.02 | 0.94 ± 0.02 | |
Proposed SSL Pre-trainingb | 0.96 ± 0.02 | 0.94 ± 0.02 | 0.94 ± 0.03 | |
| ||||
Treadmill Walking | Supervised Learning Baseline | 0.89 ± 0.02 | 0.96 ± 0.01 | 0.93 ± 0.03 |
Motion Transfer Pre-training | 0.92 ± 0.01 | 0.97 ± 0.01 | 0.96 ± 0.02 | |
Task Transfer Pre-training | 0.93 ± 0.01 | 0.98 ± 0.01 | 0.97 ± 0.01 | |
Proposed SSL Pre-trainingb | 0.94 ± 0.02 | 0.98 ± 0.01 | 0.97 ± 0.02 | |
| ||||
Drop Landing | Supervised Learning Baseline | 0.74 ± 0.12 | 0.88 ± 0.08 | 0.93 ± 0.05 |
Motion Transfer Pre-training | 0.75 ± 0.12 | 0.87 ± 0.09 | 0.93 ± 0.04 | |
Task Transfer Pre-training | 0.75 ± 0.13 | 0.90 ± 0.08 | 0.93 ± 0.05 | |
Proposed SSL Pre-trainingb | 0.75 ± 0.12 | 0.90 ± 0.08 | 0.92 ± 0.06 |
ml: medial-lateral; ap: anterior-posterior; v: vertical
The model is pre-trained on the synthetic IMU dataset.