A novel radius adaptive based on center-optimized hybrid detector generation algorithm

• Published in: IEEE/CAA journal of automatica sinica Vol. 7; no. 6; pp. 1627 - 1637
• Main Author: Chen, Jinyin
• Format: Journal Article
• Language: English
• Published: Piscataway Chinese Association of Automation (CAA) 01.11.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE); College of Information Engineering, Zhejiang University of Technology, Hangzhou 310023, China
• Subjects: Adaptation models; Algorithms; Anomalies; Artificial intelligence; Biological system modeling; Datasets; Detectors; False alarms; Hybrid power systems; Immune system; Optimization; Sensors; Artificial immunity; negative detector; hybrid detect; center optimized; negative selection algorithm (NSA); radius adaptive
• ISSN: 2329-9266; 2329-9274
• DOI: 10.1109/JAS.2018.7511192

Negative selection algorithm &#x0028 NSA &#x0029 is one of the classic artificial immune algorithm widely used in anomaly detection. However, there are still unsolved shortcomings of NSA that limit its further applications. For example, the nonself-detector generation efficiency is low; a large number of nonself-detector is needed for precise detection; low detection rate with various application data sets. Aiming at those problems, a novel radius adaptive based on center-optimized hybrid detector generation algorithm &#x0028 RACO-HDG &#x0029 is put forward. To our best knowledge, radius adaptive based on center optimization is first time analyzed and proposed as an efficient mechanism to improve both detector generation and detection rate without significant computation complexity. RACO-HDG works efficiently in three phases. At first, a small number of self-detectors are generated, different from typical NSAs with a large number of self-sample are generated. Nonself-detectors will be generated from those initial small number of self-detectors to make hybrid detection of self-detectors and nonself-detectors possible. Secondly, without any prior knowledge of the data sets or manual setting, the nonself-detector radius threshold is self-adaptive by optimizing the nonself-detector center and the generation mechanism. In this way, the number of abnormal detectors is decreased sharply, while the coverage area of the nonself-detector is increased otherwise, leading to higher detection performances of RACOHDG. Finally, hybrid detection algorithm is proposed with both self-detectors and nonself-detectors work together to increase detection rate as expected. Abundant simulations and application results show that the proposed RACO-HDG has higher detection rate, lower false alarm rate and higher detection efficiency compared with other excellent algorithms.