Title: Context-aware detection of selfish nodes in mobile ad-hoc networks using fusion of hybrid leader optimisation with barnacles mating optimiser and adaptive deep belief network

Authors: K. Sudhaakar; K.T. Meena Abarna; E. Mohan

Addresses: Department of Computer Science and Engineering, Annamalai University, Annamalai Nagar, Chidambaram, Tamil Nadu, India ' Department of Computer Science and Engineering, Annamalai University, Annamalai Nagar, Chidambaram, Tamil Nadu, India ' Department of ECE, Saveetha School of Engineering, SIMATS, Thandalam, Kuthambakkam, Tamil Nadu, India

Abstract: A self-configuring network of mobile nodes linked by wireless connections is a Mobile Ad-hoc Network (MANET). Like the existence of an attack node, the selfish node is present in the network and cannot transfer the information to the neighbour nodes. Owing to this reason, the performance gets affected. Hence, this work considers the attributes of nodes, such as hop count, residual energy and cooperation history, termed as the input factors. With the help of these constraints, the Adaptive Deep Belief Network (ADBN) is newly developed to determine the target value for the cooperation rate. Further, the hyper-parameters in the Deep Belief Network (DBN) are optimally chosen by proposing the Fusion of Hybrid Leader Optimisation with Barnacles Mating Optimiser (FHLO-BMO). From the results, the accuracy and precision rate of the developed model are 92.86% and 93.29%. Finally, the effectiveness of the model is validated and measured with various metrics.

Keywords: selfish node detection; mobile ad-hoc network; adaptive deep belief network; fusion of hybrid leader optimisation; barnacles mating optimiser.

DOI: 10.1504/IJWMC.2026.150857

International Journal of Wireless and Mobile Computing, 2026 Vol.30 No.1, pp.32 - 52

Received: 22 Jan 2024
Accepted: 09 Jun 2024
Published online: 24 Dec 2025 *

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