Table 2 Experimental analysis of considered methods based on accuracy and F1 score on CICIDS2018 dataset.

From: Bi directional sparse attention recurrent autoencoder based intrusion detection for VANET security with tuna swarm optimization

Models

Feature selection

Accuracy

F1 Score

DT

No

0.942

0.931

DQN

No

0.951

0.925

RFE

Yes

0.961

0.954

DNN (Suggested)

Yes

0.981

0.972