Skip to main content

Table 2 Definition of all 44 classification models compared in this work, according to feature sets and learning algorithms. M ij is the classifier induced with the feature set i and algorithm j, i=1,…,12 and j=1,2,3, and w ij is the cross-validation accuracy of the classifier M ij . \(\hat {M}_{ij}\) is the predicted class by \(\text {M}_{ij},\hat {M}_{ij} \in \{-1,1\}\). Emv=Ensemble majority votes, Ewv=Ensemble weighted votes

From: Automatic learning of pre-miRNAs from different species

  1. SVMs 2. RF 3. J48
1. FS1 M11 M12 M13
2. FS2 M21 M22 M23
3. FS6 M31 M32 M33
4. FS7 M41 M42 M43
5. FS3 M51 M52 M53
6. FS4 M61 M62 M63
7. FS5 M71 M72 M72
8. SELECT M81 M82 M83
9. Hyb37 M91 M92 M93
10. Hyb S 7 M101 M102 M103
11. Hyb 17 M111 M112 M113
12. Ss1 M121 M122 M123
Emv8 \(\sum \hat {M}_{i1},i=5,\ldots,12\) \(\sum \hat {M}_{i2},i=5,\ldots,12\) \(\sum \hat {M}_{i3},i=5,\ldots,12\)
Ewv8 \(\sum w_{i1}\hat {M}_{i1},i=5,\ldots,12\) \(\sum w_{i2}\hat {M}_{i2},i=5,\ldots,12\) \(\sum w_{i3}\hat {M}_{i3},i=5,\ldots,12\)
Emv24 \(\sum \hat {M}_{ij},i=5,\ldots,12\) and j=1,2,3
Ewv24 \(\sum w_{ij}\hat {M}_{ij},i=5,\ldots,12\) and j=1,2,3