Multiple-Point Bit Mutation Method of Detector Generation

In self and nonself discrimination (SNSD) model, it is very important to generate a desirable detector set since it decides the performance and scale of the SNSD model based task. This chapter proposed a novel detector generating algorithm on the basis of the negative selection principle in natural immune systems. It utilizes random multiple-point mutation to look for nonself detectors in a large range of the space of detectors, such that one can obtain a required detector set in a reasonable computing time. The chapter describes the work procedure of the proposed detector generating algorithm. Then, it tests the algorithm on many datasets and compared it with the Exhaustive Detector Generating Algorithm (EDGA) in detail. The experimental results show that the proposed algorithm outperforms the EDGA in both detection performance and computational complexity. The major difference between growth algorithm and negative selection algorithm (NSA) is the generating method of candidate detectors.