Table 4 FOG effect detected by multiple sensors
From: Recognition of freezing of gait in Parkinson’s disease based on combined wearable sensors
Sensor Position | Sensitivity (Recall) | Specificity | Accuracy | precision | F-score |
|---|---|---|---|---|---|
Left thigh | 76.02% | 90.46% | 89.20% | 43.24% | 55.13% |
Left shank | 76.73% | 90.74% | 89.52% | 44.15% | 56.05% |
Waist | 73.86% | 91.89% | 90.32% | 46.49% | 57.06% |
Left foot | 72.68% | 89.58% | 88.11% | 39.92% | 51.53% |
Waist + left thigh | 78.90% | 91.32% | 90.24% | 46.40% | 58.44% |
Waist + left shank | 78.17% | 92.29% | 91.06% | 49.17% | 60.37% |
Left thigh + left shank | 77.71% | 90.88% | 89.73% | 44.91% | 56.92% |
Left foot + left thigh | 77.12% | 90.93% | 89.73% | 44.73% | 56.62% |
Sole pressure + left thigh | 76.65% | 90.04% | 88.87% | 42.42% | 54.61% |
Sole pressure + left shank | 75.71% | 90.48% | 89.19% | 43.22% | 55.03% |
Left foot + left shank | 75.49% | 91.40% | 90.01% | 45.66% | 56.90% |