一种基于信息熵的异常数据挖掘算法  

A kind of outlier mining algorithm based on information entropy

作　　者：陈玉明[1] 吴克寿[1] 李向军[1,2] 

机构地区：[1]厦门理工学院计算机科学与技术系,福建厦门361024 [2]南昌大学计算机科学与技术系,南昌330031

出　　处：《控制与决策》2013年第6期867-872,共6页Control and Decision

基　　金：国家自然科学青年基金项目(61103246)

摘　　要：信息熵是粒计算理论中度量不确定信息的重要工具之一,已有的异常数据挖掘算法主要针对确定性的异常数据挖掘,采用信息熵度量不确定性数据进行异常数据挖掘的研究报道较少.鉴于此,在引入信息熵概念的基础上,定义基于信息熵的异常度来度量数据之间的异常程度,并提出基于信息熵的异常数据挖掘算法,该算法可有效进行异常数据的挖掘.理论分析与实验结果表明,所提出算法是有效可行的.Information entropy is one of the important tool to measure the uncertainty information in the information theory. Many existing algorithms of outlier mining mainly aim at certainty data, and little work has been done for the uncertainty data aiming to outlier mining based on the information entropy. Therefore, after introducing information entropy concept, outlier degree based on information entropy is defined for measuring the outlier data. Furthermore, an algorithm for outlier mining based on information entropy is proposed, which can effectively obtain outliers from data set Finally, theoretical analysis and experimental results show that the algorithm is efficient and feasible.

关 键 词：粗糙集 粒计算 异常数据挖掘 信息熵 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]