基于中心向量KNN算法的改进  

The Improvement of KNN Algorithm Based on Center Vector

作　　者：王兆龙[1] 

机构地区：[1]安徽文达信息工程学院

出　　处：《哈尔滨师范大学自然科学学报》2017年第2期18-21,共4页Natural Science Journal of Harbin Normal University

摘　　要：针对KNN算法在中文文本分类时计算开销大的问题,在已有改进算法的基础上进行了更深入的研究,提出改进的基于中心向量KNN算法.算法首先引入基于密度的思想对训练样本进行调整,同时计算各类别的类中心向量.在保证类中心向量准确性的前提条件下,使分类阶段的复杂计算提前到分类器的训练过程中.实验结果表明,该算法在不损失精确度的情况下,提高了分类实时性.In order to solve the problem of high computational cost in Chinese text classification, a deep research on the improved algorithm based on KNN algorithm is made, and an improved algorithm is proposed based on KNN algorithm. Firstly, the density of the training samples is adjusted, and the class center vectors are calculated. Under the premise of ensuring the accuracy of the center vector, the complex computation in the classification stage is advanced to the training process of the classifier. The experimental results show that the proposed algorithm improves the classification performance without losing the accuracy.

关 键 词：文本分类 多级分类器 类中心向量 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]