An Expanded Lateral Interactive Clonal Selection Algorithm and Its Application

Shangce GAO  Hongwei DAI  Jianchen ZHANG  Zheng TANG  

Publication
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E91-A   No.8   pp.2223-2231
Publication Date: 2008/08/01
Online ISSN: 1745-1337
DOI: 10.1093/ietfec/e91-a.8.2223
Print ISSN: 0916-8508
Type of Manuscript: PAPER
Category: Neural Networks and Bioengineering
Keyword: 
clonal selection algorithm,  somatic hypermutation,  receptor editing,  idiotype,  traveling salesman problem,  

Full Text: PDF(547.5KB)>>
Buy this Article




Summary: 
Based on the clonal selection principle proposed by Burnet, in the immune response process there is no crossover of genetic material between members of the repertoire, i.e., there is no knowledge communication during different elite pools in the previous clonal selection models. As a result, the search performance of these models is ineffective. To solve this problem, inspired by the concept of the idiotypic network theory, an expanded lateral interactive clonal selection algorithm (LICS) is put forward. In LICS, an antibody is matured not only through the somatic hypermutation and the receptor editing from the B cell, but also through the stimuli from other antibodies. The stimuli is realized by memorizing some common gene segment on the idiotypes, based on which a lateral interactive receptor editing operator is also introduced. Then, LICS is applied to several benchmark instances of the traveling salesman problem. Simulation results show the efficiency and robustness of LICS when compared to other traditional algorithms.