Table 3.
Increase of the results on the testing data set (in percent of r2) by using the sigmoid function to compute the relative position of the target. The values in bold are significant (p<0.05). (The multiple linear regression technique was used with the sliding windows approach, two electrodes and features selection.)
| User | A | B | C | D | E | F | G | H | Mean |
|---|---|---|---|---|---|---|---|---|---|
| Increase (%) | −1.53 | 8.22 | 1.5 | −3.49 | 3.12 | 23.9 | 5.77 | 7.7 | 5.4 |
| Confidence Interval at 95% | −3.8; 0.8 | −0.4; 17 | −3.3; 7.7 | −2.2; 9.1 | 2.3; 4.6 | −1.9; 56 | 2.7; 9.7 | 3.6; 11.9 | 4.1; 6.7 |