Table 12. Classification performance on the UNSW-NB15 dataset with RF-RFE features (15 features).

Classifier	Accuracy	Precision	Recall	F1-measure
Random forest	97.73%	98.01%	98.02%	98.01%
KNN	86.50%	82.31%	87.41%	84.78%
SVM	84.60%	78.11%	85.40%	81.59%
Decision tree	97.58%	98.24%	98.12%	98.17%
MLP	74.21%	77.43%	77.14%	77.78%
Ensemble	98.53%	98.79%	98.78%	98.78%