WSEAS Transactions on Information Science and Applications
Print ISSN: 1790-0832, E-ISSN: 2224-3402
Volume 13, 2016
Model and Algorithm of Artificial Immune System for the Recognitions of Single Symbol and their Comparison with Existing Methods
Authors: , ,
Abstract: The present paper is devoted to the creation of a model and algorithm of an artificial immune system (AIS). In the description of the proposed artificial immune system model and algorithm the terminology from the natural immune system is preserved. The adopted concept of B-cells are responsible for producing antibodies, a special class of complex proteins on the surface of B-lymphocytes, capable of binding to certain types of molecules (antigens) is used. The full set of antigenic receptors of all B-cells is a plurality of antibodies that can be produced by the organism. The proposed model is considered for realization of the problem of single symbols recognition. The uniform algorithm of realization of the artificial immune system for solving problems of recognition (recognition of single symbols) is developed, and its improved distributed version, using the concept of decentralized nature of immune system, is carried out. Accuracy of calculations is compared to that for other methods, particularly to neural networks. The program product involving the algorithms is developed, and computing experiments for each considered task are made.
Search Articles
Keywords: artificial immune system, model, algorithm, lymphocytes, affinity, object-oriented model, immune network, immune memory
Pages: 38-45
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 13, 2016, Art. #5