Var Num Cross validation (inner/outer) Performance of Training dataset
CC RMSE MAE RAE RRSE
5 inner1 0.4651 10.1162 7.2018 0.8693 0.8855
inner2 0.4684 10.1391 7.1953 0.8672 0.8837
inner3 0.4681 10.0993 7.1854 0.8687 0.8839
inner4 0.4646 10.1212 7.1967 0.8700 0.8857
inner5 0.4655 10.1357 7.2052 0.8702 0.8853
outer 0.4692 10.1052 7.1783 0.8668 0.8833
15 inner1 0.5559 9.6909 6.7923 0.8199 0.8482
inner2 0.5546 9.7411 6.7971 0.8192 0.8490
inner3 0.5580 9.6846 6.7783 0.8195 0.8475
inner4 0.5528 9.7142 6.7863 0.8204 0.8501
inner5 0.5574 9.7036 6.7913 0.8202 0.8475
outer 0.5653 9.6396 6.7350 0.8133 0.8426
30 inner1 0.5675 9.6735 6.7625 0.8163 0.8467
inner2 0.5648 9.7334 6.7691 0.8158 0.8483
inner3 0.5688 9.6707 6.7520 0.8163 0.8463
inner4 0.5644 9.6995 6.7587 0.8171 0.8488
inner5 0.5686 9.6900 6.7604 0.8165 0.8463
outer 0.5787 9.6069 6.6955 0.8085 0.8397
50 inner1 0.5546 9.7149 6.7959 0.8203 0.8503
inner2 0.5513 9.7787 6.8099 0.8208 0.8523
inner3 0.5551 9.7201 6.7899 0.8209 0.8507
inner4 0.5525 9.7366 6.7939 0.8213 0.8520
inner5 0.5556 9.7331 6.7987 0.8211 0.8501
outer 0.5682 9.6381 6.7287 0.8125 0.8424
100 inner1 0.5643 9.6711 6.7409 0.8137 0.8465
inner2 0.5579 9.7510 6.7563 0.8143 0.8498
inner3 0.5637 9.6803 6.7365 0.8144 0.8472
inner4 0.5606 9.7010 6.7381 0.8146 0.8489
inner5 0.5636 9.6955 6.7415 0.8142 0.8468
outer 0.5760 9.5959 6.6652 0.8049 0.8387
300 inner1 0.5551 9.6912 6.7585 0.8158 0.8483
inner2 0.5483 9.7728 6.7785 0.8170 0.8517
inner3 0.5538 9.7031 6.7618 0.8175 0.8492
inner4 0.5496 9.7298 6.7611 0.8174 0.8515
inner5 0.5523 9.7276 6.7643 0.8170 0.8496
outer 0.5662 9.6215 6.6852 0.8073 0.8410
all inner1 0.5147 9.9085 6.9437 0.8381 0.8673
inner2 0.5077 9.9881 6.9640 0.8393 0.8705
inner3 0.5148 9.9088 6.9445 0.8396 0.8672
inner4 0.5095 9.9408 6.9462 0.8397 0.8699
inner5 0.5113 9.9471 6.9554 0.8400 0.8688
outer 0.5255 9.8525 6.8823 0.8311 0.8612
Table 4: The predicting results from the combined dataset by using Random Forest.