 Machine Learning based Methodology for Intrusion Detection in Mobile Adhoc Networks

  • B.Harikrishnan, Dr. T. Balasubramanian, Dr. A.Ravi Kumar, Dr.G.Suresh, Dr.V.Shanmugasundaram, Dr. Sushma Jaiswal
Keywords: Mobile Adhoc Network, MANET, Machine Learning, Intrusion Detection, Rough Set Theory, RST, Enhanced Support Vector Machine, eSVM

Abstract

A mobile adhoc network has lately acquired popularity owing to the ubiquity of portable connection and their adaptability to serve particular non-permanent and immediate applications like floods and war scenarios Due to the lack of a single point of control, fluctuating network architecture, transitory existence, and uncoordinated communication, MANET presents a number of security problems. As a first-line security solution, there are many suggestions for using encryption and authentication methods to reduce security risks. Unauthorized entry into the Mobile Adhoc Network can't be completely eliminated, but an efficient intrusion detection system may help. Due to the open medium, complicated topology, dispersion, absence of centralized administration, and resource-constrained node groups, the function of intrusion detection in Mobile Adhoc Networks is very challenging. Traditional intrusion detection systems developed for Mobile Adhoc Networks Technology have no direct equivalent that may be utilized on a wireless network Because of this, the technology utilized in it must be adaptable. With the new machine learning architecture used in this system, detection has been much improved. Intelligent Decision Support combines Enhanced Support Vector Machine (eSVM) accuracy with Rough Set Theory's enhanced scalability (RST).

Published
2021-09-27
How to Cite
Dr.V.Shanmugasundaram, Dr. Sushma Jaiswal, B. D. T. B. D. A. K. D. (2021).  Machine Learning based Methodology for Intrusion Detection in Mobile Adhoc Networks. Design Engineering, 14689-14696. Retrieved from http://www.thedesignengineering.com/index.php/DE/article/view/4755
Section
Articles