决策树分类中SLIQ算法的改进
首发时间:2010-01-14
摘要:大型数据库中的数据挖掘是目前数据挖掘领域重要的前沿课题。SLIQ算法采用了预排序技术,广度优先策略以及MDL修剪方法,是处理大型数据库数据的有效算法之一。然而在树的生长阶段需要计算大量样本点的Gini指标,限制了算法效率的提高。本文在介绍SLIQ算法的相关技术的基础上,提出了对SLIQ算法的一点改进,提高了SLIQ算法的效率。
For information in English, please click here
Improvement of SLIQ in Decision Tree Classification
Abstract:Data mining in large database is a cutting-edge topic. SLIQ, whieh employs pre-sorting, breadth-first strategy and MDL method, is effective in decision tree classification. However, a large number of calculations of Gini indexes while growing the decision tree demand a lot of time. This paper proposes a method to solve this problem and improve the efficiency of SLIQ.
Keywords: Data mining Decision tree SLIQ Gini index MDL
基金:
论文图表:
引用
No.3897851066812634****
同行评议
共计0人参与
勘误表
决策树分类中SLIQ算法的改进
评论
全部评论0/1000