UPM Institutional Repository

A lightweight graph-based pattern recognition scheme in mobile ad hoc networks.


Raja Mahmood, Raja Azlina and Muhamad Amin, Anang Hudaya and Amir, Amiza and Khan, Asad I. (2012) A lightweight graph-based pattern recognition scheme in mobile ad hoc networks. In: Trustworthy Ubiquitous Computing. Atlantis Ambient and Pervasive Intelligence (6). Atlantis Press, Amsterdam, pp. 177-206. ISBN 9789491216701; EISBN: 9789491216718


A lightweight, low-computation, distributed intrusion detection scheme termed the distributed hierarchical graph neuron (DHGN) was proposed to be incorporated into a cooperative intrusion detection system (IDS) in mobile ad hoc networks (MANETs). Its one-cycle learning and divide and distribute recognition task approach allows DHGN to detect similar patterns in short of time. An IDS of such properties is essential in the resource constrained MANETs environment. MANETs are distributed and self-configuring networks, with limited resources and dynamic nodes. Their characteristics have made them highly susceptible to many attacks and securing the networks a challenging task. This paper discusses the operations of the proposed three stage cooperative IDS in detecting packet drop attacks. The comparison study between DGHN and the iterative, highly computational self organizing map (SOM) is also reviewed. Both algorithms show comparable detection results. Thus, the lightweight, low computation DHGN based detection scheme offers an effective security solution in MANETs.

Download File

Full text not available from this repository.

Additional Metadata

Item Type: Book Section
Divisions: Faculty of Computer Science and Information Technology
DOI Number: https://doi.org/10.2991/978-94-91216-71-8_9
Publisher: Atlantis Press
Keywords: Lightweight; Mobile ad hoc networks; Wireless networks; Network.
Depositing User: Nurul Ainie Mokhtar
Date Deposited: 12 Mar 2014 08:11
Last Modified: 12 Mar 2014 08:11
URI: http://psasir.upm.edu.my/id/eprint/26090
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item