Static clonal selection algorithm based on match range model

Authors:
Jungan Chen;Dongyong Yang;Feng Liang
Affiliations:
Zhejiang Wanli University, Ningbo, Zhejiang, China;Zhejiang University of Technology, Hangzhou, Zhejiang, China;Zhejiang Wanli University, Ningbo, Zhejiang, China
Venue:
IEA/AIE'06 Proceedings of the 19th international conference on Advances in Applied Artificial Intelligence: industrial, Engineering and Other Applications of Applied Intelligent Systems
Year:
2006

Citing 6
Cited 0

Using Genetic Algorithms for Concept Learning

Machine Learning - Special issue on genetic algorithms
Self-Nonself Discrimination in a Computer

SP '94 Proceedings of the 1994 IEEE Symposium on Security and Privacy
An immunological model of distributed detection and its application to computer security

An immunological model of distributed detection and its application to computer security
A study of artificial immune systems applied to anomaly detection

A study of artificial immune systems applied to anomaly detection
Using genetic algorithms to explore pattern recognition in the immune system

Evolutionary Computation
Learning and optimization using the clonal selection principle

IEEE Transactions on Evolutionary Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Static Clonal Selection Algorithm (SCSA) is proposed to generate detectors to intrusion detection. A gene expression is used to express detector which exists as a form of classification rules. But full match rule is used and the gene expression can not express classification rules with OR operator freely. In this work, by combined the gene expression with partial match rule which is an important component in negative selection algorithm, a new expression which can express classification rules with OR operator is proposed. But the match threshold in match rule is difficult to set. Inspired from the T-cell maturation, a match range model is proposed. Base on this model and new expression proposed, a Static Clonal Selection Algorithm based on Match Range Model is proposed. The proposed algorithm is tested by simulation experiment for self/nonself discrimination. The results show that the proposed algorithm is more effective to generate detector with partial classification rules than SCSA which generates detector with full conjunctive rules with ‘and’; match range is self-adapted.