基于边界的最大间隔模糊分类器

刘忠宝; 王士同

doi:10.3788/OPE.20122001.0140

您当前的位置：

首页 >

文章列表页 >

基于边界的最大间隔模糊分类器

信息科学 | 更新时间：2020-08-12

- 基于边界的最大间隔模糊分类器
- Maximum-margin fuzzy classifier based on boundary
- 光学精密工程 2012年20卷第1期页码：140-147
- 作者机构：
  
  1. 江南大学数字媒体学院,江苏无锡,214122
  2. 山西大学商务学院信息学院,山西太原,030031
- 作者简介：
- 基金信息：
  
  国家863高技术研究发展计划资助项目(No.2007AA1Z158, No.2006AA10Z313)();国家自然科学基金资助项目(No.60773206, No.6
- DOI：10.3788/OPE.20122001.0140
  中图分类号： TP391.4
- 收稿日期：2011-07-19，
  
  修回日期：2011-09-19，
  
  网络出版日期：2012-01-25，
  
  纸质出版日期：2012-01-25
- 稿件说明：
移动端阅览
刘忠宝, 王士同. 基于边界的最大间隔模糊分类器[J]. 光学精密工程, 2012,20(1): 140-147

LIU Zhong-bao, WANG Shi-tong. Maximum-margin fuzzy classifier based on boundary[J]. Editorial Office of Optics and Precision Engineering, 2012,20(1): 140-147
刘忠宝, 王士同. 基于边界的最大间隔模糊分类器[J]. 光学精密工程, 2012,20(1): 140-147 DOI： 10.3788/OPE.20122001.0140.

LIU Zhong-bao, WANG Shi-tong. Maximum-margin fuzzy classifier based on boundary[J]. Editorial Office of Optics and Precision Engineering, 2012,20(1): 140-147 DOI： 10.3788/OPE.20122001.0140.

摘要

对利用超平面、超(椭)球等几何形状实现数据分类的基于边界的主流分类方法进行了研究

在此基础上

提出了一种将空间点作为分类依据的最大间隔模糊分类器(MFC)。该方法首先在模式空间中找到一个模糊分类点

点距离两类样本要尽可能近且类间夹角间隔尽可能大。然后

测试样本通过

与训练样本间的最大化夹角间隔实现分类。最后

利用MFC的核化对偶式与最小包含球(MEB)的等价性

将MFC的应用范围从二类推广到单类。与主流分类方法的比较实验表明

MFC具有优良的分类性能和抗噪能力

其分类最高精度可达98.8%。

Abstract

Several kinds of current boundary classification methods based on hyperplane

hypersphere or ellipsoid were studied

and a novel classification method called Maximum-margin Fuzzy Classifier (MFC) was proposed by using a space point as the classification criterion. By the proposed method

a fuzzy classified point

was chosen in the pattern space firstly

which should be as close to two classes as possible. Moreover

the angle between the two classes should be also as large as possible. Then

the testing points could be classified in terms of the maximum angular margin between

and all the training points. Finally

the applications of the MFC were popularized from two-class classification to one-class classification according to the kernel dual of MFC equivalent to the Minimum Enclosed Ball (MEB). Comparative experiments with current classification methods verify that the MFC has good classification performance and noise resistance ability and its classification accuracy has been reached 98.9%.

关键词

Keywords

references

刘红岩,陈剑,陈国青. 数据挖掘中的数据分类算法综述 [J].清华大学学报(自然科学版),2002,42(6):727-730. LIU H Y, CHEN J, CHEN G Q. Review of classification algorithms for data mining [J]. Journal of Tsinghua University(Science and Technology), 2002,42(6):727-730.(in Chinese)[2] SCHOLKOPF B, PLATT J, SHAWE-TAYLOR J, et al.. Estimating the support of high-dimensional distribution [J]. Neural Computation, 2001, 13: 1443-1471.[3] TAX D, DUIN R, Support vector data description [J]. Machine Learning, 2004 (54): 45-66.[4] 冯爱民, 薛晖,刘学军,等. 增强型单类支持向量机 [J]. 计算机研究与发展, 2008, 45(11): 1858-1864. FENG A M, XUE H, LIU X J, et al.. Enhanced one-class SVM [J]. Journal of Computer Research and Development, 2008, 45(11): 1858-1864.(in Chinese)[5] WEI X K, HUANG G B, LI Y H. Mahalanobis ellipsoidal learning machine for one class classification . Proc. of the 6th Int. Conf. on Machine learning and cybernetics. Los Alamitos: IEEE Computer Society, 2007: 3528-3533.[6] VAPNIK V. The Nature of Statistical Learning Theory [M]. New York: Springer-Verlag, 1995.[7] MAHESH P, GILES M. Feature selection for classification of hyper spectral data by SVM [J]. IEEE Trans. on Geoscience and Remote Sensing, 2010, 48 (5): 2297-2307.[8] TSANG I W, KWOK J T, CHEUNG P M. Core vector machines: fast svm training on very large data sets [J]. Journal of Machine Learning Research, 2005, 6: 363-392.[9] 文传军, 詹永照, 陈长军. 最大间隔最小体积球形支持向量机 [J]. 控制与决策, 2010, 25(1): 79-83.(in Chinese) WEN C J, ZHAN Y Z, CHEN C J. Maximal-margin minimal-volume hyper sphere support vector machine [J]. Control and Decision, 2010, 25 (1):79-83.(in Chinese)[10] SHIVASWAMY P, JEBARA T. Maximum relative margin and data-dependent regularization [J]. Journal of Machine Learning Research, 2010 (11): 747-788.[11] JUSZCZAK P. Learning to recognize: A study on one-class classification and active learning . Delft: Delft University of Technology, 2006.[12] DOLIA A, HARRIS C, SHAWE-TAYLOR J. Kernel ellipsoidal trimming [J]. Computational statistics and data analysis, 2007, 52(1): 309-324.[13] LIN C F, WAN S D. Fuzzy support vector machines [J]. IEEE Trans. on Neural Networks, 2002, 13(2):464-471.[14] 孙名松,高庆国,王宣丹. 基于双隶属度模糊支持向量机的邮件过滤 [J]. 计算机工程与应用, 2010, 46(2):93-95. SUN M S, GAO Q G, WANG X D. Mail filtering by dual membership fuzzy support vector machine [J]. Computer Engineering and Application, 2010, 46(2):93-95.(in Chinese)[15] TSANG I W, KWOK J T, ZURADA J M. Generalized core vector machines[J]. IEEE Trans. on Neural Networks, 2006, 17(5): 1126-1140.[16] MULLER K R, MIKA S, RATSCH G, et al.. An introduction to kernel-based learning algorithms [J]. IEEE Trans. on Neural Networks, 2001, 12 (1): 181-201.

浏览量

667

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于监督保局子空间虚假近邻准则的原始特征选择

用于分类的样本保局鉴别分析方法

利用多分辨率直方图特征分类数字X光乳腺图像