无先序条件约束的KNN算法  

No Previous Ordering for KNN Algorithm

作　　者：孙岩[1] 吕世聘[2] 唐一源[3] 

机构地区：[1]辽宁师范大学计算机与信息技术学院 [2]大连理工大学计算机科学与工程系,辽宁大连116023 [3]大连理工大学神经信息学研究所,辽宁大连116023

出　　处：《小型微型计算机系统》2008年第4期682-686,共5页Journal of Chinese Computer Systems

基　　金：国家自然基金项目(60472017,30670699)资助

摘　　要：KNN(K-Nearest Neighbor)是向量空间模型中最好的分类算法之一,非常有效和容易实现.文中介绍了KNN算法的基本思想,并针对KNN算法在解决问题的时候存在只考虑样本的数值特征,没有考虑样本结构特征的缺点,利用贝叶斯网络结构的学习算法,加入了变量之间的因果关系,产生分类数据库中样本的结构特征权重,提出在无先序条件约束下,基于贝叶斯结构特征加权的KNN算法(BS-KNN,Bayesianstructure KNN).实验结果表明,BS-KNN算法能够有效地提高分类的正确率.K-nearest neighbor algorithm is one of the best classified algorithm and it is very effective and easy to implement. This paper introduces the basic idea of KNN algorithm. But the KNN algorithm only considers the numerical characteristics between variables and do not take the structural characteristics of them into account. This paper make use of the learning algorithm of Bayesian network structure without prior conditions and add causal relationship between the variables ,furthermore, the weighted KNN algorithm （BS-KNN） based on learning Bayesian network structure is presented. Experiments show that BS-KNN algorithm can be used to improve the classification accuracy.

关 键 词：贝叶斯网络 K-近邻算法 距离加权 特征加权 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]