Title: Intrusion detection of wireless sensor networks based on IPSO algorithm and BP neural network

Authors: Xue Lu; Dezhi Han; Letian Duan; Qiuting Tian

Addresses: School of Information Engineering, Shanghai Maritime University, 1550 Pudong Avenue, Pudong New Area, Shanghai, Shanghai, 201306, China ' School of Information Engineering, Shanghai Maritime University, 1550 Pudong Avenue, Pudong New Area, Shanghai, Shanghai, 201306, China ' School of Information Engineering, Shanghai Maritime University, 1550 Pudong Avenue, Pudong New Area, Shanghai, Shanghai, 201306, China ' School of Information Engineering, Shanghai Maritime University, 1550 Pudong Avenue, Pudong New Area, Shanghai, Shanghai, 201306, China

Abstract: The sensor nodes of wireless sensor networks (WSNs) are deployed to an open and unsupervised region, and they are vulnerable to various types of attacks. Intrusion detection system can detect network attacks that nodes suffer from. This paper combines improved particle swarm optimisation (IPSO) algorithm and back-propagation neural network (BPNN), named IPSO-BPNN. We propose an intrusion detection model of WSNs based on a hierarchical structure. First, we use IPSO algorithm to optimise the initial parameters of BPNN to avoid falling into the local optimum. Then, we apply IPSO-BPNN to the intrusion detection of WSNs. Finally, we use benchmark NSL-KDD and UNSW-NB15 datasets to verify the performance of the IPSO-BPNN. The simulation results show that IPSO-BPNN has faster convergence speed, higher detection accuracy rate and lower false positive rate compared with BPNN and BPNN optimised by PSO algorithm, which can meet the WSNs intrusion detection requirements.

Keywords: wireless sensor network; WSN; particle swarm optimisation; PSO; back-propagation neural network; BPNN; intrusion detection.

DOI: 10.1504/IJCSE.2020.107344

International Journal of Computational Science and Engineering, 2020 Vol.22 No.2/3, pp.221 - 232

Received: 26 Feb 2019
Accepted: 18 Jul 2019

Published online: 18 May 2020 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article