Table 5 Comparison of TRL-FM with baseline RL. AUCs when RL (baseline) and TRL-FM are applied to build a classification rule model on three datasets, Petalidis (brain), KangA (IPF), and Lapointe (prostate). For TRL-FM, the FMs are the medium through which knowledge transfer occurs. “Union” is an ensemble of all FMs. The mean and the standard error of the mean (SEM) for the AUC of a dataset was obtained by 10-fold cross-validation
Dataset | Petalidis | KangA | Lapointe |
|---|---|---|---|
AUC (SEM) | AUC (SEM) | AUC (SEM) | |
Baseline | 0.83 (0.06) | 0.86 (0.07) | 0.93 (0.03) |
FM1 | 0.82 (0.07) | 0.93 (0.05) | 0.87 (0.04) |
FM2 | 0.89 (0.07) | 0.92 (0.05) | 0.88 (0.04) |
FM3 | 0.89 (0.07) | 0.85 (0.07) | 0.96 (0.02) |
FM4 | 0.88 (0.06) | 0.89 (0.07) | 0.90 (0.03) |
FM5 | 0.84 (0.08) | 0.81 (0.07) | 0.90 (0.03) |
FM6 | 0.85 (0.06) | 0.86 (0.07) | 0.94 (0.02) |
FM7 | 0.81 (0.07) | 0.82 (0.07) | 0.95 (0.03) |
FM8 | 0.86 (0.06) | 0.93 (0.05) | 0.92 (0.03) |
FM9 | 0.81 (0.07) | 0.86 (0.07) | 0.88 (0.04) |
FM10 | 0.84 (0.08) | 0.86 (0.07) | 0.89 (0.03) |
FM11 | 0.89 (0.07) | 0.82 (0.07) | |
FM12 | 0.86 (0.07) | ||
FM13 | 0.93 (0.05) | ||
FM14 | 0.93 (0.05) | ||
Union | 0.91 (0.06) | 0.97 (0.03) | 0.97 (0.02) |