计算机工程与应用 ›› 2010, Vol. 46 ›› Issue (28): 132-134.DOI: 10.3778/j.issn.1002-8331.2010.28.037

• 数据库、信号与信息处理 • 上一篇    下一篇

凹半监督支持向量机及其应用

冼广铭1,2,齐德昱1,方 群2,柯 庆3,曾碧卿4,庞雄文5   

  1. 1.华南理工大学,广州 510640
    2.广州天河软件园管委会博士后科研工作站,广州 510663
    3.蓝盾信息安全技术股份有限公司,广州 510631
    4.华南师范大学 南海学院,广东 佛山 528225
    5.华南师范大学 计算机学院,广州 510640
  • 收稿日期:2008-04-08 修回日期:2008-12-01 出版日期:2010-10-01 发布日期:2010-10-01
  • 通讯作者: 冼广铭

Application of concave semi-supervised support vector machines

XIAN Guang-ming1,2,QI De-yu1,FANG Qun2,KE Qing3,ZENG Bi-qing4,PANG Xiong-wen5   

  1. 1.South China University of Technology,Guangzhou 510640,China
    2.Guangzhou Tianhe Software Park MC Post-doctoral Research Station,Guangzhou 510663,China
    3.Bluedon Information Security Technology Co.,Ltd,Guangzhou 510631,China
    4.Nanhai Campus,South China Normal University,Foshan,Guangdong 528225,China
    5.College of Computer,South China Normal University,Guangzhou 510640,China
  • Received:2008-04-08 Revised:2008-12-01 Online:2010-10-01 Published:2010-10-01
  • Contact: XIAN Guang-ming

摘要: 在训练集不足的情况下,SVM算法有待改进,以提高其评价的准确性。采用凹半监督支持向量机,利用少量标注样本和大量未标注样本进行机器学习,提高了模型预测的精度。

关键词: 凹半监督支持向量机, 机器学习, 未标注样本

Abstract: In case of lack of sufficient training set,SVM algorithm is expected to improve its accuracy.The concave semi-
supervised support vector machines is adopted and the little labeled sample and lots of labeled samples are utilized for machine learning.Accuracy of the model is improved by this method.

Key words: concave semi-supervised support vector machines, machine learning, unlabeled samples

中图分类号: