KNN系数修正迭代求精算法  

Parameter Iteratively Modified-KNN

作　　者：许朝阳[1] 

机构地区：[1]莆田学院电子信息工程学系,福建莆田351100

出　　处：《计算机与现代化》2010年第10期20-22,42,共4页Computer and Modernization

摘　　要：随着WWW的迅猛发展,文本分类成为处理和组织大量文档数据的关键技术。KNN方法是一种简单、有效、非参数的分类方法。本文提出利用KNN分类器的封闭测试的结果对分类器进行调整修正系数的算法PIM-KNN(Parameter Iteratively Modified-KNN):错误分类的样本应该拉近与所属类别的"距离",而增大与被误判的类别的"距离"。实验结果表明,经过PIM-KNN算法调整的KNN分类器的分类效果得到显著提高。With the development of World Wide Web,text classification has become a key technology in organizing and processing large amount of document data.It＇s a simple,effective and nonparametric classification method.This paper proposes an algorithm PIM-KNN（Parameter Iteratively Modified-KNN） to adjust parameter in classifier according to results of close test of the KNN algorithm： the sample of wrong judged should reduce the distance between itself and the class which it belongs to,enlarge the distance between itself and the class which wrong judged.The experiments results show that the classification results can be improved significantly by adjusting parameter of the PIM-KNN.

关 键 词：文本分类 K近邻 迭代 距离 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]