Table 11.

Comparison of different models.

Data set	Algorithm	Evaluation indicators (%)
		Accuracy	Precision	Recall	F1-score
NSL-KDD	Random forest	75.41	84.00	75.41	77.53
	K-means clustering	79.34	78.01	79.34	76.28
	Decision tree	76.92	71.98	54.52	55.97
	S-ResNet [49]	98.33	98.39	98.33	98.34
	CNN [50]	97.78	97.74	97.78	97.75
	CNN-GRU [51]	99.15	99.15	99.15	99.15
	CNN-LSTM [21]	98.64	98.61	98.64	98.56
	CNN-BiLSTM [52]	99.22	99.18	99.14	99.15
	SRFCNN-BiGRU	99.81	99.76	99.81	99.79
UNSW_NB15	Random forest	75.41	84.00	75.41	77.53
	K-means clustering	70.93	82.42	70.91	76.23
	Decision tree	73.37	80.94	73.36	76.30
	S-ResNet [49]	83.8	85.0	83.8	84.4
	CNN [50]	82.9	82.6	82.9	82.7
	CNN-GRU [51]	84.3	83.7	84.3	84.0
	CNN-LSTM [21]	82.6	81.9	82.6	80.6
	CNN-BiLSTM [52]	82.08	82.68	80.00	81.32
	SRFCNN-BiGRU	85.55	86.24	85.55	85.61
CIC-IDS2017	Random forest	98.21	98.58	93.40	95.92
	K-means clustering	95.03	96.40	95.21	95.80
	Decision tree	96.60	97.62	96.66	97.14
	S-ResNet [49]	95.94	96.10	95.94	95.41
	CNN [50]	89.14	84.18	89.14	85.56
	CNN-GRU [51]	99.42	99.34	99.42	99.38
	CNN-LSTM [21]	96.64	96.87	96.64	96.45
	CNN-BiLSTM [52]	99.43	99.39	99.42	99.40
	SRFCNN-BiGRU	99.70	99.68	99.70	99.69