Skip to main content

Table 2 Confusion matrixes of the best four performing ML models trained on the reduced feature space

From: A novel feature extraction methodology using Siamese convolutional neural networks for intrusion detection

AB   Class 1 Class 2 Per class accuracy
Class 1 9323 388 96.00%
Class 2 2624 10,209 79.55%
  Overall accuracy 86.64%
RF   Class 1 Class 2 Per class accuracy
Class 1 9336 375 96.14%
Class 2 2692 10,141 79.02
  Overall accuracy 86.40%
NB   Class 1 Class 2 Per class accuracy
Class 1 9393 318 96.73%
Class 2 2800 10,033 78.18%
  Overall accuracy 86.17%
SVM   Class 1 Class 2 Per class accuracy
Class 1 9400 311 96.80%
Class 2 2842 9991 77.85%
  Overall accuracy 86.01%