一种自适应局部概念漂移的数据流分类算法  

Adaptive Method for Handling Local Concept Drift of Data Streams Classification

作　　者：尹志武[1] 黄上腾[1] 

机构地区：[1]上海交通大学计算机科学与工程系,上海200240

出　　处：《计算机科学》2008年第2期138-139,143,共3页Computer Science

摘　　要：本文基于DB2算法提出一个能实时检测局部概念漂移,并随之自适应调整的数据流分类算法IncreDB2。该算法动态增量维护一个层次分类树。当局部概念漂移出现时,IncreDB2不是重新构造一个全新的分类树,而是仅更新漂移所影响到的局部结点,具有较高的时间效率。实验结果表明了该算法的正确性和有效性。Based on the DB2 method, an adaptive method called IncreDB2 is proposed to detect and adapt to local concept drift continuously in data stream classification This method dynamically maintains a hierarchical classification tree. When local concept drift is detected, IncreDB2 only updates the nodes that affected by this drift rather than re- builds a new classification tree from scratch, which means that it has better time efficiency. Experimental results demonstrated the validity and efficiency of this method.

关 键 词：数据流挖掘 多分类 局部概念漂移 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论] TP391.41[自动化与计算机技术—计算机科学与技术]