一种基于自我聚类的异常检测学习方法

提出一种新的基于正选择的异常检测方法,该方法通过聚类学习正常空间特征,在每个类中选择有代表性的自我样本构造检测器集,之后利用正选择算法进行异常检测。这种方法既能适用于自我样本集较多的情形,克服了T. Stibor提出的正选择的局限,又具备了一定的学习能力。同时,该方法还避免了负选择中随机选择样本带来的弊端。通过实验分析,该方法比VDetector具备更好的检测性能,是一种有效的异常检测方法。

Anomaly detection method by clustering normal data

A new anomaly detection method was proposed based on positive selection. The method learned the characteristic of "self" space by clustering, and then selected typical samples from every cluster to construct detectors. And positive selection was used to detect anomalies. The new algorithm is not only effective in certain application with large number of "self" samples, but also avoids the shortcoming by randomly selecting sample in VDetector. Experimental results on Ring data and biomedical data show that the new method is more effective in anomaly detection.