20.500.12556/RUNG-6425
Design & analysis of clustering based intrusion detection schemes for e-governance
Design and analysis of clustering based intrusion detection schemes for e-governance
The problem of attacks on various networks and information systems is increasing. And with systems working in public domain like those involved under E-Governance are facing more problems than others. So there is a need to work on either designing an altogether different intrusion detection system or improvement of the existing schemes with better optimization techniques and easy experimental setup. The current study discusses the design of an Intrusion Detection Scheme based on traditional clustering schemes like K-Means and Fuzzy C-Means along with Meta-heuristic scheme like Particle Swarm Optimization. The experimental setup includes comparative analysis of these schemes based on a different metric called Classification Ratio and traditional metric like Detection Rate. The experiment is conducted on a regular Kyoto Data Set used by many researchers in past, however the features extracted from this data are selected based on their relevance to the E-Governance system. The results shows a better and higher classification ratio for the Fuzzy based clustering in conjunction with meta-heuristic schemes. The development and simulations are carried out using MATLAB.
particle swarm optimization
intrusion detection
anomaly detection
intrusion detection system
network intrusion detection
true
true
false
Angleški jezik
Ni določen
Neznano
2021-04-02 12:47:22
2021-04-02 18:02:46
2023-06-09 03:43:09
0000-00-00 00:00:00
2016
0
0
Str. 461-471
2016
0000-00-00
NiDoloceno
NiDoloceno
NiDoloceno
0000-00-00
0000-00-00
0000-00-00
58232579
004
58232067
10.1007/978-3-319-47952-1_36
URN:SI:UNG:REP:M9ZZ5O7R
https://doi.org/10.1007/978-3-319-47952-1_36
1
https://repozitorij.ung.si/Dokument.php?lang=slv&id=21906
Univerza v Novi Gorici
0
2
0