Computer Engineering and Applications ›› 2009, Vol. 45 ›› Issue (13): 200-202.DOI: 10.3778/j.issn.1002-8331.2009.13.059

• 图形、图像、模式识别 • Previous Articles     Next Articles

Supervised outlier detection based on Mahalanobis ellipsoidal learning machine

LI Jian-min1,LI Yong-xin1,XUE Zhen-xia2,3   

  1. 1.Department of Mathematics,Pingdingshan University,Pingdingshan,Henan 467002,China
    2.Department of Mathematics,Henan University of Science and Technology,Luoyang,Henan 471003,China
    3.Department of Applied Mathematics,Xidian University,Xi’an 710071,China
  • Received:2009-01-08 Revised:2009-03-23 Online:2009-05-01 Published:2009-05-01
  • Contact: LI Jian-min

基于马氏椭球学习机的监督野点探测

李建民1,李永新1,薛贞霞2,3   

  1. 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
  • 通讯作者: 李建民

Abstract: 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.

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。