Theoretical advances in artificial immune systems

J. Timmis, Andrew Hone, Thomas Stibor, E. Clark

Research output: Contribution to journalArticlepeer-review

Abstract

Artificial immune systems (AIS) constitute a relatively new area of bio-inspired computing. Biological models of the natural immune system, in particular the theories of clonal selection, immune networks and negative selection, have provided the inspiration Cor AIS algorithms. Moreover, such algorithms have been successfully employed in a wide variety of different application areas. However, despite these practical successes, until recently there has been a dearth of theory to justify their Use. In this paper, the existing theoretical work oil AIS is reviewed. After the presentation of a simple example of each of the three main types of AIS algorithm (that is, clonal selection, immune network and negative selection algorithms respectively), details of the theoretical analysis for each of these types are given. Some of the future challenges in this area are also highlighted. (C) 2008 Elsevier B.V. All rights reserved.

Original languageEnglish
Pages (from-to)11-32
Number of pages22
JournalTheoretical Computer Science
Volume403
Issue number1
DOIs
Publication statusPublished - 20 Aug 2008

Keywords

  • artificial immune systems
  • clonal selection
  • negative selection
  • immune networks
  • Markov chains
  • k-CNF satisfiability
  • IDIOTYPIC NETWORKS
  • CLONAL SELECTION
  • CELL ALGORITHM
  • IMMUNOLOGY
  • DISCRIMINATION
  • OPTIMIZATION
  • PRINCIPLE
  • MODEL
  • SIZE

Cite this