Intrusion detection in clustering wireless network by applying extreme learning machine with deep neural network algorithm

Abstract

Nowadays, intrusion detection systems (IDSs) have growingly come to be considered as an important method owing to their possible to expand into a key factor, which is crucial for the security of wireless networks. In wireless network, when there is a thousand times more traffic, the effectiveness of normal IDS to identify hostile network intrusions is decreased by an average factor. This is because of the exponential growth in network traffic. This is due to the decreased number of possibilities to discover the intrusions. This is because there are fewer opportunities to see possible risks. We intend an extreme learning machine with deep neural network (DNN) algorithm-based intrusion detection in clustering (EIDC) wireless network. The main objective of this article is to detect the intrusion efficiently and minimize the false alarm rate. This mechanism utilizes the extreme learning machine (ELM) with a deep neural network algorithm for optimizing the weights of input and hidden node biases to deduce the network output weights. Simulation outcomes illustrate that the EIDC mechanism not only assures a better accuracy for detection, considerably minimizes an intrusion detection time, and shortens the false alarm rate.