An Optimal Multilayer Perceptron with Dragonfly Algorithm for Intrusion Detection in Wireless Sensor Networks

Abstract

Wireless sensor network (WSN) comprises several sensor nodes which are randomly deployed in the interesting region for data gathering operations. Since the sensor nodes are majorly deployed in harsh and accessible open regions, it is highly vulnerable to attacks and thereby necessitates an effective intrusion detection system (IDS). The rise of machine learning (ML) algorithms finds useful in the design of IDS, particularly for energy constrained WSN. In this view, this study introduces Optimal Multilayer Perceptron (OMLP) with Dragonfly Algorithm (DA) for intrusion detection in WSN. The major intention of OSVM is to determine the possible intrusions and identifies the class type effectually. The OMLP technique is mainly used to determine the weights and bias of the MLP by the DA. The utilization of DA results in the effective choice of weight and bias values and thereby led to improved detection performance. The experimental validation of the OMLP model takes place on the benchmark NSL KDDCup 99 dataset. The obtained experimental outcome reported the proficient performance of the OMLP model with higher accuracy and detection rate of 94.21% and 95.18% respectively.