Table 12.
Methods | External 1 (CNUH) | External 2 (YNU) | External 3 (KNUH) |
---|---|---|---|
MSE (95% CI) | MSE (95% CI) | MSE (95% CI) | |
Proposed model | 1.441 (0.760-2.122) | 1.435 (1.195–1.676) | 1.458 (1.147–1.768) |
w/o pre-train | 1.737 (1.037–2.437) | 2.319 (1.907–2.732) | 1.835 (1.402–2.268) |
w/o Transformer | 1.544 (0.882–2.206) | 1.977 (1.682–2.272) | 1.374 (1.091–1.657) |
w/o PCAM | 1.436 (0.777–2.095) | 2.205 (1.881–2.529) | 1.353 (1.058–1.648) |
w/o position embedding | 1.447 (0.838–2.056) | 1.504 (1.257–1.750) | 1.522 (1.237–1.807) |
Note:, denote the better performance of ours with statistical significance (, ). CI: confidence interval.