Graph Based Multi-Kernel SVM (G-mkSVM) for Data Transmission in MANET

Document Type : Primary Research paper


1 Professor, Department of Electronics and Communication Engineering, Bannari Amman Institute of Technology, Sathyamangalam

2 Assistant Professor, Department of Computer Science and Engineering, J.K.K.Munirajah College of Technology, T.N.Palayam.


MANET merges the collaborative networking environment where the dynamic
network leads to topological variations. The nodes cooperate efficiently during route establishment
and data transmission. The cooperative nature helps to forward data transmission
over the network. This work provides the widen concept behind the graph based kernel
SVM and explains the graph kernel optimization and multi-graph optimization principle.
In this work, a Graph based multi-kernel Support Vector Machine (G-mkSVM) is proposed
for MANET. This approach provides the preliminary idea behind the multi-graph kernel,
computes the idea behind graph kernel optimization and multi-graph kernels with n-hops.
The proposed G-mkSVM applies the shortest path for connecting various CH nodes for
transmitting packets. G-mkSVM algorithm performances like packet loss ratio, control
packets ratio, and average E2E delay are computed on MATLAB environment. The anticipated
model gives better performance than prevailing approaches.


Volume 12, Issue 3 - Serial Number 3
ICMMNT-2021 International Virtual Conference on Materials, Manufacturing and Nanotechnology, 30th June, 2021.
June 2021
Pages 1070-1077