A negative selection algorithm based on adaptive immunoregulation

Abstract

Negative selection algorithm (NSA) is an important detectors training algorithm in artificial immune system (AIS). In NSAs, the self radius and location of detectors affect the performance of algorithms. However, the traditional NSAs preset the self radius empirically and generate detectors randomly without considering the distribution of antigens resulting in the performance of AIS varies greatly in different applications. To deal with these limitations, an adaptive immunoregulation based real value negative selection algorithm (AINSA) is proposed in this paper. AINSA utilizes the "adaptive immunoregulation" mechanism to calculate the self radius and optimize the location of the candidate detectors. In this way, AINSA can attain the suitable self radius for different application and effectively generate the detectors in the region where antigens distribute densely. The experimental results show, on the artificial dataset and the UCI standard datasets, AINSA can reach the higher detection rate with better detectors generation efficiency compared to the classical RNSA and V-detector algorithm.