Research Article

[Retracted] Research on Boruta-ET-Based Anomalous Traffic Detection Model

Table 6

The performance of the methods in the study.

Methodā€‰BenignDoSPort scanBotBrute forceWeb attackInfiltration

NBPrecision0.870.810.760000.01
Recall0.980.5800000.70
F10.920.6800000.02

LGBMPrecision0.880.610.8300.080.100
Recall0.900.640.1400.030.710
F10.890.140.2300.050.180

DTPrecision0.990.990.990.410.950.660.17
Recall10.9410.630.880.931
F10.990.97100.500.910.770.29

XgboostPrecision0.950.9910.4110.990.24
Recall10.930.460.250.460.861
F10.970.960.630.310.630.920.38

RFPrecision0.96110.550.990.991
Recall10.940.560.260.770.891
F10.980.970.710.350.870.941

DNNPrecision0.920.850.9800.9800
Recall0.970.770.5000.5300
F10.950.810.6600.6900

The method proposed Boruta-ETPrecision110.990.8710.981
Recall1110.260.980.951
F11110.400.990.971