Skip to main content

Table 2 Performance (five-fold cross validation) of the predictive models for each serotype when using OneR for feature selection. SVM: Support Vector Machine; Sn: Sensitivity; Sp: Specificity; Acc: Accuracy; MCC: Matthews Correlation Coefficient

From: Rapid classification of group B Streptococcus serotypes based on matrix-assisted laser desorption ionization-time of flight mass spectrometry and machine learning techniques

Serotype

Feature selection

Classifiers

Bin size

Number of features

Sn

Sp

Acc

MCC

Ia

OneR

Random Forest

9

42

95.1%

89.1%

90.9%

0.804

SVM

9

38

93.5%

91.9%

92.4%

0.828

Ib

Random Forest

7

48

83.7%

81.0%

81.8%

0.611

SVM

7

46

76.4%

74.3%

74.9%

0.473

III

Random Forest

9

28

90.1%

87.4%

88.3%

0.753

SVM

9

16

86.5%

85.5%

85.8%

0.700

V

Random Forest

1

43

86.2%

85.9%

86.0%

0.690

SVM

1

43

81.3%

81.0%

81.1%

0.590

VI

Random Forest

3

47

93.2%

91.6%

92.2%

0.837

SVM

9

13

91.2%

89.6%

90.2%

0.796