A boundary-fixed negative selection algorithm with online adaptive learning under small samples for anomaly detection
A boundary-fixed negative selection algorithm with online adaptive learning under small samples for anomaly detection
复制标题
一种用于异常检测的小样本下在线自适应学习的边界固定负选择算法
DOI：
10.1016/j.engappai.2015.12.014
复制
发表时间：
2016-04
影响因子：
8
通讯作者：
Hongli Zhang
中科院分区：
文献类型：
--
作者：
Dong Li;Shulin Liu;Hongli Zhang
传统的否定选择算法（NSA）缺乏在线自适应学习能力，限制了其应用范围。本文提出了一种新的负选择算法--小样本下带在线自适应学习的边界固定负选择算法（OALFB-NSA）。固定边界的否定选择算法（FB-NSA）在自空间周围生成一层检测器。这些检测器只与训练样本有关，与训练次数无关。OALFB-NSA检测器在检测阶段能够实时适应自身空间的变化。在Iris数据集和生物医学数据集上对FB-NSA、V-detector等异常检测算法进行了实验比较，结果表明FB-NSA在大多数情况下都能获得较高的检测率和较低的误报率。在Iris数据集上对OALFB-NSA、小训练样本下在线自适应学习的界面检测器（OALI-检测器）和V-检测器进行了实验比较，结果表明，在不发生过拟合的情况下，OALFB-NSA即使只使用自身样本进行训练，也能获得较高的检测率和较低的虚警率。
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 onlyoneself sample is used for training.
登录
查看更多内容
DOI：
10.1007/s11432-008-0040-2
发表时间：
2008-06
期刊：
Science in China Series F: Information Sciences
影响因子：
--
作者：
Maoguo Gong;L. Jiao;Wenping Ma;Haifeng Du
通讯作者：
Maoguo Gong;L. Jiao;Wenping Ma;Haifeng Du
DOI：
10.1109/tsmcb.2003.817026
发表时间：
2004-02-01
影响因子：
--
作者：
Esponda, F;Forrest, S;Helman, P
通讯作者：
Helman, P
影响因子：
56.9
作者：
VONBOEHMER, H;KISIELOW, P
通讯作者：
KISIELOW, P
DOI：
10.1145/1068009.1068061
发表时间：
2005-06
期刊：
--
影响因子：
--
作者：
T. Stibor;Philipp H. Mohr;J. Timmis;C. Eckert
通讯作者：
T. Stibor;Philipp H. Mohr;J. Timmis;C. Eckert
DOI：
10.1016/j.asoc.2011.07.014
发表时间：
2011-12
期刊：
Appl. Soft Comput.
影响因子：
--
作者：
Zhonghua Li;Yunong Zhang;Hongzhou Tan
通讯作者：
Zhonghua Li;Yunong Zhang;Hongzhou Tan