期刊文献+

增强的主分量分类器 被引量:2

Enhanced Principle Component Classifier
下载PDF
导出
摘要 主分量分类器是在最大化样本投影代数和的前提下求解分类面法方向,并采用核方法解决线性不可分问题.它对所有真实世界样本(包括野值)的重视程度相同,且只考虑了一个野值.设计并实现了一类鲁棒性较主分量分类器更强的增强型主分量分类器,其中重点讨论了三种典型权设置下的分类器特性.分析和实验证实了增强的主分量分类器的抗野值、噪声性能以及学习和推广能力均优于主分量分类器. Principle Component Classifier (PCC) takes the normal vector of a hyperplane as the projecting direction, onto which the algebraic sum of all samples' projections is maximized, and deals with linearly nonseparable problem using kernel tricks. It is unreasonable in real world that PCC views outliers, together with noises, as important as other normal samples.A classifier named Enhanced Principle Component Classifier (EnPCC) with better robustness has been designed and implemented. Especially, the characters of the classifier with three typical weights are discussed. Finally, analysis and experiments on one toy problem and a benchmark dataset show the superiority of EnPCC to PCC in eliminating outliers or noise, learning ability and generalization.
出处 《复旦学报(自然科学版)》 CAS CSCD 北大核心 2004年第5期769-772,共4页 Journal of Fudan University:Natural Science
基金 国家自然科学基金资助项目(60271017) 江苏省自然科学基金资助项目(BK2002092).
关键词 分类器 主分量 推广能力 核方法 野值 鲁棒性 设置 不可分 求解 样本 principle component classifier robustness generalization outlier kernel method
  • 相关文献

参考文献7

  • 1Hu W J,Song Q. Principle component classifier. NIPS'2000[EB/OL].http://svm.first.gmd.de./.2004-02-12.
  • 2Liu Ling, Chen Keke. Visualization of several datasets [EB/OL].http://disl.cc.gatech.edu /VISTA/demo_main.html.2003-12-12.
  • 3Hamza A B,Krim H. Image denoising:A nonlinear robust statistical approach[J]. IEEE Trans on Signal Processing, 2001,49(12):3045-3054.
  • 4Müller K R, Mika S, Ratsch G, et al. An introduction to kernel-based learning algorithms[J].IEEE Trans on Neural Network,2001,12(2):181-202.
  • 5Schlkopf B, Smola A, Müller K R.Nonlinear component analysis as a kernel eigenvalue problem[J]. Neural Compt, 1998,10:1299-1319.
  • 6Ruiz A, López-de-Teruel P E. Nonlinear kernel-based statistical pattern analysis[J]. IEEE Trans on Neural Network, 2001,12(1):16-31.
  • 7Mika S, Rtsch G, Weston J, et al. Fisher discriminant analysis with kernels[A].In: Hu Y H, Larsen J, Wilson E,et al,eds. IEEE Neural Networks for Signal Processing 9 [C]. Piscataway, N J:IEEE,1999.41-48.

同被引文献14

  • 1姜桂艳,温慧敏,杨兆升.高速公路交通事件自动检测系统与算法设计[J].交通运输工程学报,2001,1(1):77-81. 被引量:67
  • 2韩自存,杨绪兵.模糊主分量分类器[J].安徽工程科技学院学报(自然科学版),2007,22(1):45-50. 被引量:1
  • 3Hu W J, Song Q.Principle component classifier[EB/OL]. (2004-02-12 ) .http ://svm.first.gmd.de./.
  • 4Tong Hanghang,Li Chongrong,He Jingrui,et al.Anomaly internet network traffic detection by kernel principle component classifier[C]//Lecture Notes in Computer Science, 2005,3498: 476-481.
  • 5Yuan F, Cheu R L.Incident detection using support vector machines[J].Transportation Research Part C, 2003,11 : 309-328.
  • 6Chen Shuyan, Wang Wei, Qu Gaofeng.Traffic incident detection based on rough sets approach[C]//2007 International Conference on Machine Learning and Cybernetics,2007,7.
  • 7Hu W J,Song Q.Principle component classifier.NIPS.2000 workshop on New Perpectives in Kernel-based Learning Methods in Breckenridge US[EB/OL].[2004-02-12].http://svm.first.gmd.de/.
  • 8Müller K R.Mika S,Ratsch G,Tsuda K,Scholkopf B.An introduction to kernel-based learning algorithms[J].IEEE Transaction on Neural Network,2001,12(2)181-202.
  • 9Ruiz A.López-de-Teruel P.E.Nonlinear kernel-based statistical pattern analysis[J].IEEE Transaction on Neural Network,2001,12(1):16-31.
  • 10Vapnik V N.The nature of statistical learning theory[M].New York:Spinger-Verlag,1995.

引证文献2

二级引证文献3

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