Skip to main content

Table 8 Methods

From: Performance Analysis of Intrusion Detection Systems Using a Feature Selection Method on the UNSW-NB15 Dataset

ML methods

Feature extraction technique

Training AC (%)

Binary AC (%)

Multiclass AC (%)

DT [24]

IG

–

–

57.01

J48 [25]

PSO-FO-GO-GA

90.48

–

–

SVM [25]

PSO-FO-GO-GA

90.11

–

–

RF [26]

FI

–

–

75.56

Bagging Forest [27]

PSO-GA-ACO

91.27

–

–

RF [28]

IG

–

85.78

–

RepTree [29]

IGC

–

88.95

–

IELM [30]

APCA

–

–

75.36

DBN [31]

Corr.

–

85.73

–

CNN-BiLSTM [32]

O-SS-SMOS

–

–

77.16

DT

XGBoost

94.12

90.85

67.57

ANN

XGBoost

94.21

84.39

77.51

LR

XGBoost

89.20

77.64

65.29

kNN

XGBoost

95.86

84.46

72.30

SVM

XGBoost

75.42

60.89

53.95