A Feedback Negative Selection Algorithm to Anomaly Detection

Negative selection algorithm (NSA) lacks adaptability and needs a large number of self elements to build the profile of the system and train detectors. In order to overcome these limitations and build an appropriate profile of the system in a varying self and nonself condition, this paper presents a feedback negative selection algorithm, which is referred to FNSA algorithm, and its applications to anomaly detection. The proposed approach uses the feedback technique, which adjusts the self radius of self elements, the detection radius of detectors and the number of detectors, to adapt the varieties of self nonself space and build the appropriate profile of the system based on some of self elements. Furthermore, the approach can increase the accuracy in solving the anomaly detection problem. To determine the performance of the approach, the experiments with well-known dataset were performed and compared with other works reported in the literature. Results exhibited that our proposed approach outperforms the previous techniques.