[1]曹苏群,王士同,陈晓峰,等.最佳鉴别矢量集在无监督模式下的扩展[J].智能系统学报,2008,3(06):511-522.
 CAO Su-qun,WANG Shi-tong,CHEN Xiao-feng,et al.Extending the optimal set of discriminant vectors for an unsupervised pattern[J].CAAI Transactions on Intelligent Systems,2008,3(06):511-522.
点击复制

最佳鉴别矢量集在无监督模式下的扩展(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第3卷
期数:
2008年06期
页码:
511-522
栏目:
出版日期:
2008-12-25

文章信息/Info

Title:
Extending the optimal set of discriminant vectors for an unsupervised pattern
文章编号:
1673-4785(2008)06-0511-12
作者:
曹苏群1 2王士同1陈晓峰1邓赵红1
1.江南大学信息学院,江苏无锡214122; 2.淮阴工学院机械系,江苏淮安223001
Author(s):
CAO Su-qun12 WANG Shi-tong1 CHEN Xiao-feng1 DENG Zhao-hong1
1.School of Information, Jiangnan University, Wuxi 214122, China;2.Department of Mechanical Engineering, Huaiyin Institute of Technology, Huaian 223001,China
关键词:
最佳鉴别矢量集无监督模式Fisher准则半模糊聚类
Keywords:
optimal set of discriminant vectorsunsupervised patternFisher criterionsemi-fuzzy clustering
分类号:
TP181
文献标志码:
A
摘要:
基于Fisher准则函数的最佳鉴别矢量集是一种重要的有监督特征提取方法,在模式识别领域有着重要的影响.提出一种将最佳鉴别矢量集扩展到无监督模式下的方法,其基本思想是通过定义的模糊Fisher准则函数将Fisher线性判别扩展成一种半模糊聚类算法,通过该算法求得最佳鉴别矢量和模糊散布矩阵,进而构造出最佳鉴别矢量集.实验表明,在聚类有效性、分类准确率均优于无监督模式下常用的主成分分析特征提取算法.
Abstract:
The optimal set of discriminant vectors, based on the Fisher criterion function, is an important supervised feature extraction method and has great influence in the area of pattern recognition. In this paper, an extension of the optimal set of discriminant vectors in unsupervised patterns is presented. The basic idea is to extend Fisher linear discriminants to a novel semifuzzy clustering algorithm through a predefined fuzzy Fisher criterion function. With the proposed algorithm, an optimal discriminant vector and fuzzy scatter matrixes can be figured out and then an unsupervised optimal set of discriminant vectors can be obtained. Experimental results for real datasets, testing clustering validity and correct classification recognition rates, demonstrated that this method is superior to the principal component analysis feature extraction algorithm in unsupervised patterns.

参考文献/References:

[1]FISHER R A. The use of multiple measurements in taxonomic problems[J].Annals of Eugenics, 1936,7: 179-188.
[2]SAMMON J W. An optimal discriminant plane[J]. IEEE Trans on Computers, 1970, 19(9): 826-829.
[3]FOLEY D H,SAMMON J W. An optimal set of discriminant vectors[J]. IEEE Trans on Computers, 1975, 24(3): 281-289.
[4]DUCHENE J,LECLERCQ S. An optimal transformation for discriminant and principal component analysis[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 1988, 10(6): 978-983.
[5]金    忠,杨静宇,陆建峰. 一种具有统计不相关性的最佳鉴别矢量集[J]. 计算机学报, 1999, 22(10): 1105-1108. 
JIN Zhong,YANG Jingyu,LU Jianfeng. An optimal set of uncorrelated discriminant features[J].Chinese J Computers, 1999, 22(10): 1105-1108.
[6]JIN Zhong,YANG Jingyu, HU Zhongshan,et al. Face recognition based on the uncorrelated discriminant transformation[J]. Pattern Recognition, 2001, 34(7): 1405-1416.
[7]束婷婷, 甘   岚, 杨静宇. 求解统计不相关的最佳鉴别矢量的统一算法[J]. 南京理工大学学报:自然科学版 , 2002,26(3): 290-294.
SHU Tingting,GAN Lan,YANG Jingyu. A unified algorithm for the computation of statistically uncorrelated optimal discriminant vectors[J]. Journal of Nanjing University of Science and Technology:Nature Science,2002,26(3): 290-294. 
[8]吴小俊,杨静宇,王士同,等. 改进的统计不相关最优鉴别矢量集[J]. 电子与信息学报, 2005,27(1):47-50.
 WU Xiaojun, YANG Jingyu, WANG Shitong,et al. An improved optimal set of statistical uncorrelated discriminant vectors[J]. Journal of Electronics & Information Technology, 2005, 27(1): 47-50.
[9]ZHENG Wenming. A note on kernel uncorrelated discriminant analysis[J]. Pattern Recognition,2005,38(11): 2185-2187.
[10]LIANG Yixiong,LI Chengrong,GONG Weiguo,et al. Uncorrelated linear discriminant analysis based on weighted pairwise Fisher criterion[J]. Pattern Recognition, 2007, 40(12): 3606-3615.
[11]WU Xiaojun, LU Jieping, YANG Jingyu,et al. An extreme case of the generalized optimal discriminant transformation and its application to face recognition[J]. Neurocomputing, 2007, 70(4): 828-834.
[12]DY J G,BRODLEY C E. Feature selection for unsupervised learning[J]. Journal of Machine Learning Research, 2004, 5: 845-889.
[13]MIRKIN B. Concept learning and feature selection based on square error clustering[J]. Machine Learning, 1999, 35(1): 25-39.
[14]刘   涛, 吴功宜, 陈   正. 一种高效的用于文本聚类的无监督特征选择算法[J]. 计算机研究与发展, 2005, 42(3): 381-386.
LIU Tao, WU Gongyi, CHEN Zheng. An effective unsupervised feature selection method for text clustering[J]. Journal of Computer Research and Development, 2005, 42(3): 381-386. 
[15]WU Kuolung, YU Jian, YANG Minshen. A novel fuzzy clustering algorithm based on a fuzzy scatter matrix with optimality tests[J]. Pattern Recognition Letters, 2005, 26(5): 639-652.
[16]BLAKE C L, MERZ C J. UCI repository of machine learning databases[EB/OL].(2008-03-24)[2008-04-20]. http://www.ics.uci.edu/~mlearn/MLRepository.html.
[17]RAND W M.Objective criteria for the evaluation of clustering methods[J]. Journal of the American Statistical Association, 1971, 66(336): 846-850.
[18]CHANG Chihchung,LIN Chihjen. LIBSVM : a library for〖LL〗support vector machines[EB/OL].[2008-04-15].http://www.csie.ntu.edu.tw/~cjlin/libsvm.

备注/Memo

备注/Memo:
收稿日期:2008-05-12.
基金项目:教育部优秀人才支持计划资助项目(NCET-04-0496);教育部重点科学研究资助项目(105087).
作者简介:
曹苏群,男,1976年生,博士研究生,主要研究方向为模式识别、图像处理.
王士同,男,1964年生,教授,博士生导师,主要研究方向为模糊人工智能、模式识别、图像处理和生物信息学等,先后十多次留学英国、日本和香港地区,发表学术论文数十篇.
陈晓峰,男,1977年生,博士研究生,主要研究方向为机器学习、模式识别.
更新日期/Last Update: 2009-04-03