基于马氏椭球学习机的监督野点探测  

Supervised outlier detection based on Mahalanobis ellipsoidal learning machine

作　　者：李建民[1] 李永新[1] 薛贞霞[2,3] 

机构地区：[1]平顶山学院数学系,河南平顶山467002 [2]河南科技大学数学系,河南洛阳471003 [3]西安电子科技大学应用数学系,西安710071

出　　处：《计算机工程与应用》2009年第13期200-202,210,共4页Computer Engineering and Applications

基　　金：国家自然科学基金 No.60705004,No.60703118~~

摘　　要：针对有少量野点出现的情况,提出一种基于马氏椭球学习机的监督野点探测(supervised outlier detection based on Mahalanobis ellipsoidal learning machine,SODMELM)方法。这种方法通过一个超椭球对正常类进行较好的描述的同时,将野点排除在该椭球外面,继承了马氏椭球学习机(Mahalanobis Ellipsoidal Learning Machine,MELM)将样本点的协方差矩阵即样本点的分布信息考虑进去的优点。真实数据上的实验表明了所提的方法在一般意义上能提高野点探测的效率。With the help of a few labeled outlier samples,a supervised outlier detection based on Mahalanobis ellipsoidal learning machine （SODMELM） is proposed,which provides good description for the normal class as well as pushes the outlier samples away.This method inherits the advantage of Mahalanobis ellipsoidal learning machine （MELM） that considering the covariance matrix information of examples,i.e.,the distribution information of samples. Experiment results show that this method, on the average,can improve efficiency for outlier detection.

关 键 词：监督学习 野点探测 马氏距离 超椭球结构 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]