支持向量机分类算法研究要领.pdfVIP

  • 1
  • 0
  • 约3.15万字
  • 约 5页
  • 2017-06-18 发布于湖北
  • 举报
计算机工程与应用 , ( ) Computer Engineering and Applications 2009 45 1 159 支持向量机分类算法研究 周宽久,张世荣 , ZHOU Kuan-jiu ZHANG Shi-rong 大连理工大学软件学院,辽宁大连 116620 Software School ,Dalian University of Technology ,Dalian,Liaoning 116620 ,China E-mail :Zhoukj@ ZHOU Kuan -jiu ,ZHANG Shi -rong.Support vector machines based classification algorithm .Computer Engineering and Applications ,2009 ,45 (1):159-162. Abstract :The accuracy of classification of SVM in a two -class classification problem would be decreased because of those promiscuous samples.KCNN-SVM is proposed in this paper as an improved NN-SVM algorithm ,which prunes a sample according to their nearest neighbor ’s class label as well as the average distance in kernel space between it and its k congener nearest neighbors.Experimental results show that KCNN -SVM algorithm is better than both SVM and NN -SVM in accuracy of classification and the total training and testing time is comparative to that of NN-SVM. Key words :Support Vector Machine ;kernel space ;text categorization 摘 要:支持向量机在处理两类分类问题时,当两类样本混杂严重时会降低分类精度。在NN-SVM 分类算法的基础上,通过计算 样本点与其最近邻点类别的异同以及该点与其 个同类近邻点在核空间的平均距离修剪混淆点,进而提出了一种改进的 k NN- 算法——— 。实验数据表明, 算法与 以及 相比,有着更高的分类精度和更快的训练、分 SVM KCNN-SVM KCNN-SVM SVM NN-SVM 类时间。 支持向量机;核空间;文本分类 关键词: DOI :10.3778/j.issn.1002-8331.2009.01.050 文章编号:1002-8331 (2009)01-0159-04 文献标识码:A 中图分类号:TP391 1 引言 复杂,需要反复使用SVM 训练;文献[5]提出了另一种改进的 支持向量机((Support Vector Machine ,SVM)是20 世纪 SVM——NN-SVM (Nearest Neighbor-Support Vector Machine): 90 年代中期在统计学习理论基础上发展起来的一种新型机器 他先对训练集进行修剪,根据每个样本与其最近邻(nearest [1]

文档评论(0)

1亿VIP精品文档

相关文档