【作者】 刘惠； 邱天爽；

【Author】 Hui Liu Tianshuang Qiu Department of Electronic Engineering,Dalian University of Technology,Dalian 116024,China

【机构】 大连理工大学电子与信息工程学院；

【摘要】 分类是数据挖掘技术的一个重要课题。用于分类问题的关联规则挖掘方法要求将连续属性的数据划分到各区间,实际这种离散化方法并不符合人类知识的表达方式。基于模糊集理论的分类算法更易于人类理解。本文提出的基于模糊集理论和信息增益分析技术的数据挖掘分类算法,经试验证明比Hisao算法具有计算量小、无需事先确定分类属性个数且可得到较高分类正确率的优点。更多还原

【Abstract】 Classification is an important topic in data mining research.When we generate association rule for classification, continuous attributes have to be discretized into intervals while our knowledge representation is not always based on such discretization.Classification based on the fuzzy set theory can handle continuous attributes by rule-based systems in a human understandable manner.In this paper,we propose an approach based on the fuzzy set theory and the information gain analysis technique.The experimental results show that the proposed approach achieves higher accuracy with less computation and without the input of the number of attributes for classification than the algorithm of Hisao.更多还原