Table 3

The performance evaluation of the wrapper feature selection methods

Classifier

Wrapper

Specificity

Sensitivity

F-measure

ROC score

Dimensionality


SVM

SVM

0.761

0.723

0.742

0.786

320

KNN

KNN

0.705

0.731

0.718

0.745

300

SVM

NULL

0.733

0.72

0.731

0.732

All

KNN

NULL

0.637

0.753

0.69

0.723

All


The performance comparison of two classifiers (SVM and kNN) for promoter classification: with the wrapper feature selection (the first two rows) vs. without wrapper feature selection (the last two rows).

Gan et al. BMC Bioinformatics 2012 13:4   doi:10.1186/1471-2105-13-4

Open Data