MAFSIDS: a reinforcement learning-based intrusion detection model for multi-agent feature selection networks

Journal of Big Data

Table 5 The experimental results for the four methods in terms of accuracy and F1-Score on the CSE-CIC-IDS2018 and NSL-KDD datasets are as follows

Model	Feature Selection	Accuracy	F1-Score	Dataset ID
DT	No	0.931	0.922	1
DT	No	0.971	0.969	2
DQN	No	0.941	0.925	1
DQN	No	0.982	0.979	2
DQN + RFE	Yes	0.962	0.949	1
DQN + RFE	Yes	0.988	0.986	2
MAFS	Yes	0.968	0.963	1
MAFS	Yes	0.991	0.991	2

Here, Dataset ID 1 represents the CSE-CIC-IDS2018 dataset, and Dataset ID 2 represents the NSL-KDD dataset