A Novel Approach of Detector Generation for Real-Valued Negative Selection Algorithm

• Published in: Applied Mechanics and Materials Vol. 121-126; pp. 3736 - 3740
• Main Authors: Zhao, Peng, Hu, Rong Hua, Lou, Pei Huang
• Format: Journal Article
• Language: English
• Published: Zurich Trans Tech Publications Ltd 01.01.2012
• Subjects: Detector Generation; Neighborhood Search; Negative Selection Algorithm; Clonal Selection
• ISBN: 3037852828; 9783037852828
• ISSN: 1660-9336; 1662-7482; 1662-7482
• DOI: 10.4028/www.scientific.net/AMM.121-126.3736

The detector sets generated by Real-Valued Negative Selection Algorithm (RNSA) are usually numerous, without optimization, and can not work under real-time condition. Thus, a novel approach of detector generation for RNSA based on Clonal Selection and Neighborhood Search (CSNS-RNSA) is proposed. Clonal selection of the immune mechanism is introduced to implement global search in a quasi-random sequence. The Gaussian mutation operator is proposed to get the global optimal detection sets of N-dimensional space through Neighborhood search. The resulting detector sets achieved a good coverage of non-self space, and also significantly reduced the number of detector sets, thus overcome the limitations of original RNSA. Finally, experiments verify the effectiveness of the algorithm.