Cybersecurity

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%

Back to article page