Premium
Analysis of security and energy efficiency for shortest route discovery in low‐energy adaptive clustering hierarchy protocol using Levenberg‐Marquardt neural network and gated recurrent unit for intrusion detection system
Author(s) -
Mittal Mohit,
Iwendi Celestine,
Khan Suleman,
Rehman Javed Abdul
Publication year - 2021
Publication title -
transactions on emerging telecommunications technologies
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.366
H-Index - 47
ISSN - 2161-3915
DOI - 10.1002/ett.3997
Subject(s) - computer science , dijkstra's algorithm , node (physics) , intrusion detection system , shortest path problem , cluster analysis , network packet , wireless sensor network , routing protocol , artificial intelligence , computer network , real time computing , engineering , graph , structural engineering , theoretical computer science
Wireless sensor network (WSN) is a collection of a huge number of autonomous sensor nodes having capabilities such as sensing, processing, and manipulation. In any WSN, routing protocols are the backbone for performing all type tasks such as sensing, controlling, and transmission of packets in ubiquitous environment. In this article, a LEACH protocol with Levenberg‐Marquardt neural network (LEACH‐LMNN) is considered to analyze the overall network lifetime. The aim of LEACH‐LMNN protocol comprises two parts: selection of cluster head node using LMNN approach and the second part is to locate the shortest path from the cluster‐head node to base‐station node adopting various route discovery algorithms, that is, breadth‐first search, Bellman‐Ford, and Dijkstra. The simulation result shows that the LEACH‐LMNN protocol with the Dijkstra shortest path algorithm outperforms other route discovery algorithms. In addition to this, this work also analyzes normal and anomaly detection based on intrusion detection system in wireless sensor networks using gated mechanism, that is, long short‐term memory (LSTM) and gated recurrent unit (GRU) in deep learning models. The proposed model achieves the highest detection rate of 97.84% for GRU and 97.85% for LSTM as well as improves the false positive rate (FPR) of 5.87% and 3.88% FPR for GRU and LSTM, respectively.