基于统计方法的正负时态相关性挖掘  

A Method Based on Statistics for Mining Positive and Negative Temporal Correlation

作　　者：周铁军[1] 谭义红[2] 

机构地区：[1]中南林学院现代实验与技术中心 [2]长沙大学数学与信息科学系

出　　处：《湘潭大学自然科学学报》2005年第3期28-31,40,共5页Natural Science Journal of Xiangtan University

基　　金：国家自然科学基金资助项目(69973016)

摘　　要：传统相关性挖掘是在整个事务数据库的时间范围内进行的,但有时用户需得到某一特定时间段(如商品促销活动)内商品的相关性.该文对这类问题进行了详细的讨论,提出了一种基于统计方法的正负时态相关性挖掘算法.在详细讨论了该算法模型的基础上,给出了具体的算法设计,并通过实例检验该算法的有效性和可行性.The correlations are discovered traditionally in the interval of the whole transaction database. The users, However, sometimes are interested in the correlations among commodities in a special interval （ the sales promotion period for example）. In this paper we discuss this problem in detail and put forward a method of mining positive and negative temparal corrclation based on statistics. With the model of the algorithm discussed at fitst, the particular design of the algorithm is presented, and an example is also given to demonstrate the algorithms validity and feasibility.

关 键 词：数据挖掘 统计方法 时态相关性 相关性挖掘 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]