Advanced Feature Extraction and Selection Approach Using Deep Learning and Aquila Optimizer for IoT Intrusion Detection System

. 2021 Dec 26;22(1):140. doi: 10.3390/s22010140

Algorithm 1 Proposed FS For IoT security.

1:
Input: total number of generations (T), and number of agents (N).
2:
Use Equation (14) to normalize the collected IoT data.
3:
Using proposed CNN technique to extract the features (as in Section 4.2).
4:
After extracting the features, divide the data into training and testing sets.
5:
Use Equation (19) to generate population X.
6:
Put $t = 1$ .
7:
while $t < = T$ do
8:
Apply Equation (20) to generate the Binary version of $X_{i}$ .
9:
Use Equation (21) to calculate the fitness value $F i t_{i}$ for $X_{i}$ .
10:
Find the best agent $X_{b}$ .
11:
Enhance $X_{i}$ as in Equations (2)–(9)
12:
$t = t + 1$ .
13:
end while
14:
Remove irrelevant features from testing set that corresponding to zeros in $X_{b}$ .
15:
Output: Consider $X_{b}$ as output and the evaluate the performance.