A boundary-fixed negative selection algorithm with online adaptive learning under small samples for anomaly detection. (April 2016)

• Record Type: Journal Article
• Authors: Li, Dong; Liu, Shulin; Zhang, Hongli
• Is Part Of: Engineering applications of artificial intelligence. Volume 50(2016:Feb.)
• Page Start: 93
• Page End: 105
• Publication Date: 2016-04
• Subjects: Artificial immune system -- Negative selection algorithm -- Anomaly detection -- Online adaptive learning; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2015.12.014
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: The traditional negative selection algorithm (NSA) lacks online adaptive learning ability, and this restricts its application range. A new NSA, boundary-fixed negative selection algorithm with online adaptive learning under small samples (OALFB-NSA), is proposed in this paper. Boundary-fixed negative selection algorithm (FB-NSA) generates a layer of detectors, which are around the self space. These detectors are only related to the training samples, and have nothing to do with the training times. OALFB-NSA detectors can adapt themselves to real-time variety of self space during the testing stage. Experimental comparison among FB-NSA, V-detector and other anomaly detection algorithms on Iris data sets and biomedical dataset shows that the FB-NSA can obtain the higher detection rate and lower false alarm rate in most cases. The experimental comparison between OALFB-NSA, interface detector with online adaptive learning under small training samples (OALI-detector) and V-detector on Iris data sets shows that when overfitting does not occur, the OALFB-NSA can obtain the higher detection rate and lower false alarm rate, even if onlyone self sample is used for training.