作者其他论文
文献详情
Classifying noisy data streams
文献类型:会议
作者:Wang, Yong[1]  Li, Zhanhuai[2]  Zhang, Yang[3]  
机构:[1]Dept. Computer Science and Software, Northwestern Polytechnical University, China
[2]Dept. Computer Science and Software, Northwestern Polytechnical University, China
[3]School of Information Engineering, Northwest A and F University, China
年:2006
通讯作者:Zhang, Y.(Zhangyang@nwsuaf.edu.cn)
会议名称:3rd International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2006
页码范围:549-558
会议地点:Xi'an, China
会议开始日期:2006-09-24
会议结束日期:2006-09-28
收录情况:EI(20064510224211)  
所属部门:计算机学院
人气指数:860
浏览次数:844
语言:外文
摘要:
The two main challenges associated with mining data streams are concept drifting and data noise. Current algorithms mainly depend on the robust of the base classifier or learning ensembles, and have no active mechanisms to deal noisy. However, noise still can induce the drastic drops in accuracy. In this paper, we present a clustering-based method to filter out hard instances and noise instances from data streams. We also propose a trigger to detect concept drifting and build RobustBoosting, an ...More
0
评论(0 条评论)
登录