Network Traffic Anomaly Detection Model Based on Feature Reduction and Bidirectional LSTM Neural Network Optimization

Table 10

Detection results of the four models.

Dataset	Model	Evaluation metrics
		Accuracy (%)	Precision (%)	Recall (%)	F-score (%)
NSL-KDD	FR-ASPSO-BiLSTM	90.99	85.06	97.35	90.79
	FR-QPSO-BiLSTM	91.46	85.29	97.60	91.03
	FR-HPSO-BiLSTM	90.92	84.90	97.19	90.55
	FR-APPSO-BiLSTM	91.76	85.37	98.50	91.46
UNSW-NB15	FR-ASPSO-BiLSTM	89.84	97.01	97.23	97.12
	FR-QPSO-BiLSTM	91.15	97.53	97.45	97.49
	FR-HPSO-BiLSTM	91.14	97.54	97.75	97.77
	FR-APPSO-BiLSTM	92.08	97.88	98.32	98.10
CICIDS-2017	FR-ASPSO-BiLSTM	95.03	98.36	97.85	98.11
	FR-QPSO-BiLSTM	95.21	98.47	98.13	98.30
	FR-HPSO-BiLSTM	94.99	98.21	97.91	98.01
	FR-APPSO-BiLSTM	95.44	98.58	98.40	98.49