Intrusion Detection System for IoT Based on Deep Learning and Modified Reptile Search Algorithm

Algorithm 1

Developed IoT for feature selection.

	Input: : number of generations, and : number of agents.
	Using equation (11) to normalize the IoT data.
	Apply the CNN-based feature extraction (see Section 4.2).
	Dividing the dataset into training and testing according to the extracted features.
	Generate initial population by applying (15).
	Set .
	While do
	Apply (16) to find boolean form for each solution.
	Use (17) to calculate the fitness value for each .
	Allocating the best solution.
	Updating using (3)–(9).
	.
	Use the relevant features (corresponding to ones) inside for reducing the testing set.
	Outputs: Return by the and the values of evaluation indicators.