Affiliation of Author(s):计算机科学与技术学院/人工智能学院/软件学院

Journal:Commun. Comput. Info. Sci.

Abstract:For the problem that the termination condition of artificial immune network algorithm aiNet is difficult to determine, an intelligent artificial immune network algorithm S-aiNet is proposed. The S-aiNet determines whether the network is saturated by monitoring the change trend of new generation population in the iterative process according to the affinity of the new generation of network cells and existing cells. The algorithm improves the adaptability of aiNet and reduces the number of parameters. For the problem that the network of aiNet updates slowly, a regional search optimization algorithm AS-aiNet is proposed. The AS-aiNet equally divides the antibody space where the network cells and antigen located, and only searches the antibody cells located in the same region as antigens in the immune response. The AS-aiNet reduces the workload of search in the process of immune response and effectively enhances the time efficiency of algorithm operation. Adopting public data set, experiments show that the time efficiency of AS-aiNet is 10% better than that of aiNet. © 2017, Springer Nature Singapore Pte Ltd.

ISSN No.:1865-0929

Translation or Not:no

Date of Publication:2017-01-01

Co-author:李宗堃

Correspondence Author:Pi Dechang