基于知识依赖的决策树生成算法的研究  

Research of an Algorithm for Generating Decision Trees Based on Knowledge Dependency

作　　者：叶明凤[1] 

机构地区：[1]黑龙江科技学院计算机与信息工程学院,黑龙江哈尔滨150027

出　　处：《计算机工程与科学》2008年第7期108-109,113,共3页Computer Engineering & Science

摘　　要：本文对利用数据挖掘技术解决大数据量的处理问题进行了较深入的研究,基于粗糙集理论提出了基于知识依赖的属性约简方法。该方法能够快速有效地找出真正影响决策的属性。此外,又提出了以知识依赖为启发规则的决策树生成方法。该方法预测精度高,计算简便。This paper studies the methods of processing massive data with data mining techniques, and proposes an attribute reduction method based on knowledge dependency with the rough set theory, which can quickly and effectively find the attributes that really affect decisions. In addition, the paper puts forth an algorithm for generating decision trees based on knowledge dependency,which features high prediction precision and easy computation.

关 键 词：决策树 生成算法 知识依赖 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]