Table 2.
Confusion matrix
| a | b | c | d | e | f | g | h | i | j | <— classified as | |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 30 |
0 |
1 |
0 |
0 |
0 |
0 |
0 |
0 |
0 |
a |
Pelvis |
| 0 |
25 |
0 |
6 |
0 |
0 |
0 |
0 |
0 |
0 |
b |
Sternum |
| 1 |
0 |
30 |
0 |
0 |
0 |
0 |
0 |
0 |
0 |
c |
Head |
| 0 |
1 |
0 |
61 |
1 |
0 |
0 |
0 |
0 |
0 |
d |
Shoulder |
| 0 |
0 |
0 |
0 |
61 |
0 |
0 |
0 |
0 |
0 |
e |
Upper arm |
| 0 |
0 |
0 |
0 |
0 |
62 |
0 |
0 |
0 |
0 |
f |
Forearm |
| 0 |
0 |
0 |
0 |
0 |
3 |
59 |
0 |
0 |
0 |
g |
Hand |
| 0 |
0 |
0 |
0 |
0 |
0 |
0 |
62 |
0 |
0 |
h |
Upper leg |
| 0 |
0 |
0 |
0 |
0 |
0 |
0 |
0 |
62 |
0 |
i |
Lower leg |
| 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 62 | j | Foot |
Resulting from testing the decision tree in Figure 2 with 10-fold cross-validation, using 31 walking trials. From the (31 ·17=)527 inertial sensors, 514 were correctly classified (97.5%).