Negative Selection Algorithm Based on Antigen Density Clustering

Abstract

The negative selection algorithm (NSA) is one of the basic algorithms of the artificial immune system. In the traditional negative selection algorithm, candidate detectors are randomly generated without considering the uneven distributions of self-antigens and nonself-antigens, thereby resulting in many redundant detectors, and it is difficult for these detectors to fully cover the area of nonself-antigens. To overcome the problem of low detector generation efficiency, a negative selection algorithm that is based on antigen density clustering (ADC-NSA) is proposed in this paper. The algorithm divides the process of detector generation into three steps: the first step is to calculate the density of the antigens by using the method of antigen density clustering to select nonself-clusters. The second step is to prioritize the abnormal points (nonself-antigens that are not clustered) as the centers of candidate detectors and to generate the detectors via calculation. The third step is to generate the detectors via the traditional algorithm. Detector generation via these three steps can reduce the randomness of the detector generation in the traditional algorithm, thereby improving the efficiency of detector generation. The experimental results demonstrate that on the BCW and KDD-Cup datasets, the negative selection algorithm that is based on antigen density clustering can effectively increase the detection rate while reducing the false-positive rate compared with the traditional negative selection algorithm (RNSA) and two improved algorithms at the same expected coverage. INDEX TERMS Artificial immunity, negative selection algorithm, antigen density clustering, detector.

A negative selection algorithm with hypercube interface detectors for anomaly detection

“…As shown in Fig. The comparison results of different anomaly detection methods [25,30] for the BCW dataset are given in Table 3. Setting the same parameter rs=0.1.…”

Continual learning fault diagnosis method based on grid-based artificial immune system

“…In recent years, scholars have improved it and achieved the following results: clustered negative selection algorithm and fruit fly optimization for e-mail spam detection proposed by Chikh et al In this method, the samples cluster through k-nearest neighbors (KNNs) and then use the mutation idea of the Drosophila algorithm to learn the negative data [25]. The negative selection algorithm based on antigen density clustering was proposed by Yang et al Different methods have been applied to analyse the data-intensive part and the data-sparse part and use the antigen density as the weight of each detector, so as to improve the diagnostic effect [26]. Aissa et al proposed a negative selection-based network anomaly detection approach with relevant feature subset and applied it to the field of network anomaly detection.…”