期刊文献+

最大间隔椭球形多类分类算法 被引量:2

Maximal Margin Ellipsoid-shaped Multi-class Classification Algorithm
下载PDF
导出
摘要 针对多类分类问题中现有算法精度不高的问题,基于一类分类马氏椭球学习机,提出一种最大间隔椭球形多类分类算法,将每一类数据用超椭球来界定,数据空间由若干个超椭球组成,每个超椭球包围一类样本点,并以最大间隔排除不属于该类的样本点,该算法同时考虑了不同类样本点的协方差矩阵,即分布信息。真实数据上的实验结果表明该方法能提高分类精度。 For the problem of low accuracy in existing multi-class classification algorithm, based on Mahalanobis ellipsoidal learning machine for one class classification, a maximal margin ellipsoid-shaped multi-class classification algorithm is proposed, which bounds each class data using a hyper-ellipsoid and the data space is composed of several hyper-ellipsoids. Each hyper-ellipsoid encloses all samples from one class and at the same time excludes all samples from the rest class with maximal margin, In addition, the covariance matrix, i,e., the distribution information of examples from different classes is considered. Experimental results on real data sets show that the method can improve accuracy for classification.
出处 《计算机工程》 CAS CSCD 北大核心 2010年第7期185-186,189,共3页 Computer Engineering
基金 国家自然科学基金资助项目(60705004 60703118)
关键词 模式识别 多类分类 最大间隔 超椭球 pattern recognition multi-class classification maximal margin hyper-ellipsoid
  • 相关文献

参考文献7

  • 1Platt J C, Cristianini N, Shawe-Taylor J. Large Margin DAG's for Mutticlass Classification[C]//Proceedings of Neural Information Processing Systems. Cambridge, MA, USA: MIT Press, 2000.
  • 2Zhu Meilin, Wang Yue, Chen Slfifu, et al. Sphere-structured Support Vector Machines for Multi-class Pattern Recognition[M]//Rough Sets, Fuzzy Sets, Data Mining, and Granular Computing. Berlin, Germany: Springer-Verlag, 2003.
  • 3Hao Peiyi, Lin Yen-Hsiu. A New Multi-class Support Vector Machine with Multi-sphere in the Feature Space[M]//New Trends in Applied Artificial Intelligence. Berlin, Germany: Springer-Verlag, 2007.
  • 4Hao Peiyi, Chiang Jung-Hsien, Lin Ycn-Hsiu. A New Maximal- margin Spherical-struclured Multi-class Support Vector Machine[J]. Applied Intelligence, 2007, 30(2): 98-111.
  • 5Tax D, Duin R. Support Vector Domain Description[J], Pattern Recognition Letters, 1999, 20( 11 - 13): 1 191 - 1199.
  • 6Wei Xunkai, Huang Guangbin B, Li Yinghong. Mahalanobis Ellipsoidal Learning Machine for One Class Classification[C]//Proc. of ICMLC'07. [S. l.]:IEEE Press, 2007.
  • 7Asuncion A, Newman D .1. UCI Machine Learning Reposilory[Z]. (2007-01-01 ). http://www.ics.uci.edu/-m iearn/M LRepository.html.

同被引文献19

  • 1孙晋文,肖建国.基于SVM的中文文本分类反馈学习技术的研究[J].控制与决策,2004,19(8):927-930. 被引量:16
  • 2王晔,黄上腾.基于支持向量机的文本兼类标注[J].计算机工程与应用,2006,42(2):182-185. 被引量:10
  • 3Vapnik V. The Nature of Statistical I.earning Theory [M]. New York:Springer, 1995.
  • 4Joachims T. Text Categorization with Support Vector Ma- chines:Learning with Many Relevant Feature [ A] // Procee- dings of ECML-98, 10th European Conference on Machine Learning[C]. Berlin Springer, 1998 .. 137-142.
  • 5Bennett K P. Combining Support Vector and Mathematical Pro- gramming Methods for Classification[A]//Advances in Kernel MethodsSupport Vector Learning[C]. Cambridge, MA: MIT press, 1999 307-326.
  • 6Krebel U G. Pairwise Classification and Support Vector Ma- chines [A] ff Advances in Kernel Methods: Support Vector Learning[C]. Cambridge, MA: MIT press, 1999 : 255-268.
  • 7Platt J C, Cristianini N, Shawe-Taylor J. Large Margin DAGs for multielass elassifieation[A] ff Advances in Neural Informa- tion Processing Systems[C]. Cambridge, MA: MIT Press, 2000 547-553.
  • 8Wei X K, Huang G ]3. Mahalanobis Eillpsoidal Learning Ma- chine for One Class Classifieatian[C] ff International Conference on Machine Learning and Cybernetics. 2007 3528-3533.
  • 9Vapnik V.The nature of statistical learning theory[M].New York:Springer,1995.
  • 10Krebel U G.Pairwise classification and support vector machines[C].Advances in Kernel Methods:Support Vector Learning.Cambridge,MA:MIT Press,1999,255-268.

引证文献2

二级引证文献4

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部