Negative Selection Algorithm Based on Double Matching Rules
The theory of artificial immune had been widely used in the research of network intrusion detection. Nowadays, the existing detector generating algorithms based on negative selection usually use a certain matching rule, as a result, too many detectors may generate, and the false alarm rate will become more serious. This paper proposes an improved negative selection algorithm using double matching rule: candidate detectors should be selected by the improved Hamming distance matching first, then the remaining detectors go through the segmented r-chunks(rch) matching rule. Experiments show that compared with traditional algorithms, this method brings a small number and more efficient detectors, reduces the false alarm rate and guarantees the efficiency of detectors.
Helen Zhang, Gang Shen and David Jin
Y. Hu and B. Li, "Negative Selection Algorithm Based on Double Matching Rules", Advanced Materials Research, Vols. 204-210, pp. 42-45, 2011