Table 1.
Confusion matrix for classifier using the load cell data
| Load cell dataset | Predicted Class | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| EF | AB | ER | HAB | EE | AD | IR | HAD | |||
| Actual Class | Flexion | Elbow Flexion (EF) | 92 | 4 | 3 | 1 | 0 | 0 | 0 | 0 |
| Abduction (AB) | 3 | 87 | 10 | 0 | 0 | 0 | 0 | 0 | ||
| External Rotation (ER) | 2 | 8 | 89 | 1 | 0 | 0 | 0 | 0 | ||
| Horizontal Abduction (HAB) | 0 | 0 | 2 | 97 | 0 | 0 | 0 | 0 | ||
| Extension | Elbow Extension (EE) | 0 | 0 | 0 | 0 | 98 | 1 | 0 | 0 | |
| Adduction (AD) | 0 | 0 | 1 | 0 | 1 | 84 | 13 | 0 | ||
| Internal Rotation (IR) | 0 | 0 | 0 | 0 | 1 | 14 | 83 | 2 | ||
| Horizontal Adduction (HAD) | 0 | 0 | 0 | 0 | 1 | 0 | 2 | 96 | ||
Data are averaged across all participants and rounded to nearest whole number. Movements implicated in flexion synergy are in upper/left portion of table while extension synergy movements are in lower/right portion. Bold numbers identify class accuracy while non-bold numbers indicate percent of misclassification. Flexion synergy: Elbow flexion (EF), shoulder abduction (AB), external rotation (ER) and horizontal abduction (HAB). Extension synergy: elbow extension (EE), shoulder adduction (AD), internal rotation (IR), and horizontal adduction (HAD)