Publication IEICE TRANSACTIONS on Information and SystemsVol.E89-DNo.4pp.1515-1524 Publication Date: 2006/04/01 Online ISSN: 1745-1361 DOI: 10.1093/ietisy/e89-d.4.1515 Print ISSN: 0916-8532 Type of Manuscript: PAPER Category: Human-computer Interaction Keyword: immune systems, affinity, artificial immune system, pattern recognition,
Full Text: PDF(457.3KB)>>
Summary: Immune system protects living body from various attacks by foreign invades. Based on the immune response principles, we propose an improved lateral interaction artificial immune system model in this paper. Considering that the different epitopes on the surface of antigen can be recognized by a set of different paratopes expressed on the surface of immune cells, we build a neighborhood set that consists of immune cells with different affinities to a certain input antigen. We update all the weights of the immune cells located in neighborhood set according to their affinities. Simulations on noisy pattern recognition illustrate that the proposed artificial immune system model has stronger noise tolerance ability and is more effective at recognizing noisy patterns than that of our previous models.