An Efficient Approach to Categorize Data Using Improved Dendritic Cell Algorithm with Dempster Belief Theory - Proceedings of All India Seminar on Biomedical Engineering 2012 (AISOBE-2012) - page 158

An Efficient Approach to Categorize Data
Using Improved Dendritic Cell Algorithm
with Dempster Belief Theory
Kalpana Kumari, Anurag Jain and Aakriti Jain
Abstract One of the central challenges with computer security is determining the
difference between normal and potentially harmful activity. Intrusions, in partic-
ular, Web-based ones, have become increasing threats for important information.
The unique features of AIS encourage researchers to employ their techniques in a
variety of applications and especially in intrusion detection systems. Among the
wide range of available approaches, it is always challenging to select the optimal
algorithm for intrusion detection. In this paper we compare the performance one of
the algorithms of an artificial immune system called dendritic cell algorithm based
on Dempster belief theory with the dendritic cell algorithm and Support vector
machine. In terms of accuracy and computational complexity we observe that
DCA-BF has a strong detection ability and good generalization performance.
Keywords Artificial immune system Intrusion detection system Human
immune system Negative selection algorithm DCA Dempster-belief theory
K. Kumari ( & ) A. Jain
Department of CSE, RITS, Bhopal, India
e-mail: [e-mail]
A. Jain
e-mail: [e-mail]
A. Jain
Department of CSE, SIRT-S, Bhopal, India
e-mail: [e-mail]