Skip to main content
. 2021 Jul 21;136:104650. doi: 10.1016/j.compbiomed.2021.104650

Table 4.

Classification of SARS-CoV-2 and non-SARS-CoV-2 via ten-fold CV on the training data.

Classifiers Genome biomarkers selection methods Accuracy (%) (mean ± SD) F-measure (mean ± SD) Kappa-score (mean ± SD) Model built time (second)
k-NN CFS 96.47 ± 0.89 0.96 ± 0.01 0.92 ± 0.02 0.002
Correlation 97.56 ± 1.35 0.97 ± 0.02 0.95 ± 0.03 0.01
SVM-RBF CFS (C-100, gamma-0.001) 97.29 ± 1.96 0.96 ± 0.03 0.94 ± 0.04 0.2
Correlation (C-1000, gamma-0.001) 97.73 ± 1.43 0.96 ± 0.02 0.96 ± 0.03 0.29
DT CFS 96.47 ± 1.74 0.95 ± 0.02 0.93 ± 0.04 0.14
Correlation 97.46 ± 1.41 0.96 ± 0.02 0.94 ± 0.03 0.04
RF CFS 97.92 ± 1.66 0.97 ± 0.02 0.96 ± 0.03 0.22
Correlation 98.78 ± 1.09 0.98 ± 0.02 0.98 ± 0.02 0.27

k-NN – k-nearest neighbors; SVM-RBF: Support vector machine-radial basis function; DT-Decision tree; RF-Random forest, CFS-correlation-based feature selection, Correlation-Pearson correlation coefficient.