基于变精度粗糙集的KNN 分类改进算法.pdf

文档介绍：第 25 卷第 4 期模式识别与人工智能 Vol. 25 No. 4
2012 年 4 月 PR & AI Aug 2012
基于变精度粗糙集的 KNN 分类改进算法*
余鹰1,2 苗夺谦1 刘财辉1 王磊1
1
同济大学计算机科学与技术系上海 201804
2
江西农业大学软件学院南昌 330045
,
摘要传统 KNN 算法具有简单、稳定和高效的特点在实际领域得到广泛应用. 但算法的时间复杂度与样本规
, ,
模成正比大规模或高维数据会降低 KNN 分类效率. 文中通过引入变精度粗糙集模型提出一种改进的 KNN 分类
, ,
算法. 算法运用变精度粗糙集上下近似概念将各类训练样本划分为核心和边界区域分类过程计算新样本与各类
, , , , ,
的近似程度获取新样本的归属区域减小分类代价增强算法的鲁棒性. 实验表明与传统 KNN 算法相比文中算
,
法保持较高的分类精度并有效提高分类效率具有一定的理论与实际价值.
, ,
关键词 K 最近邻 KNN 变精度粗糙集上下近似

中图法分类号 TP 391 TP 181
An Improved KNN Algorithm Based on Variable Precision Rough Sets
,
1 2 , 1 , 1 , 1
YU Ying MIAO Duo-Qian LIU Cai-Hui WANG Lei
1 , ,
Department puter Science and Technology Tongji University Shanghai 201804
2 , ,
School of Software Jiangxi Agricultural University Nanchang 330045
ABSTRACT
,
K Nearest Neighbor KNN is a simple stable and effective supervised classification algorithm in
machine learning and is used in many practical applications. plexity increases with the number of
, ,
instances and thus it is not practicable for large-scale or high dimensional data. In this paper an

improved KNN algorithm based on variable parameter rough set model RSKNN is proposed. By
,
introducing the concept of upper and lower approximations in variable precision rough set model the
,
instances of each class are classified into core and boundary areas