Improved Grey Wolf Optimization- (IGWO-) Based Feature Selection on Multiview Features and Enhanced Multimodal-Sequential Network Intrusion Detection Approach

Algorithm 2

EMS-DHPN’s procedures while testing and training.

Input: flow information from network’s connections

Output: the probability of categories in flows

Step 1: model for multimodal fusions

1: Generation of MDAE based on Algorithm 2

2: Integration of MDAE with multiple features internally

Step 2: model for sequential learning

3: for from 1 to do

4: Use STM on externally selected temporal features

5: end for

Step 3: generate progressive hierarchical networks by joining MDAE with AB-LSTM

6: Creating EMS-DHPN by adding layers at the end of AB-LSTMs

7: While train not to end do

8: Obtain probable outputs by

9: Calculate cross-entropies and update EMS-DHPN correspondingly

Step 4: test

10: Test the EMS-DHPN model with the network’s traffic flows

11: Return a probable list of categories