Table 1. Online performance.
TPR | FPR | FPR† | ||||
Subject | L | R | L | R | L | R |
1 | 0.64 | 0.39 | 0.02 | 0.07 | 0.00 | 0.00 |
2 | 0.28 | 0.13 | 0.03 | 0.00 | 0.00 | 0.00 |
3 | 0.55 | 0.08 | 0.04 | 0.01 | 0.01 | 0.00 |
4 | 0.17 | 0.54 | 0.02 | 0.09 | 0.00 | 0.02 |
5 | 0.68 | 0.21 | 0.00 | 0.00 | 0.00 | 0.00 |
6 | 0.18 | 0.29 | 0.02 | 0.01 | 0.00 | 0.00 |
7 | 0.40 | 0.11 | 0.01 | 0.00 | 0.00 | 0.00 |
Average | 0.41 | 0.25 | 0.02 | 0.03 | 0.00 | 0.00 |
8 | 0.73 | 0.81 | 0.19 | 0.29 | 0.09 | 0.13 |
9 | 0.77 | 0.89 | 0.18 | 0.31 | 0.05 | 0.16 |
Average | 0.75 | 0.85 | 0.19 | 0.30 | 0.07 | 0.15 |
Online True Positive Rate (TPR) and False Positive Rate (FPR). Fixed thresholds of 1.5 and -1.5 were used for Subjects 1 to 7, whereas adaptive thresholding was applied to Subjects 8 and 9 (see Table 2). (L = left attention, R = right attention,
excluding the ’attend center’ condition.)