稀疏判别分析

doi:10.3724/SP.J.1087.2012.01017

计算机应用 ›› 2012, Vol. 32 ›› Issue (04): 1017-1021.DOI: 10.3724/SP.J.1087.2012.01017

稀疏判别分析

陈小冬¹,林焕祥²

1. 浙江广播电视大学信息与工程学院，杭州 310030
2. 浙江科技学院信息与电子工程学院，杭州 310023

收稿日期:2011-09-13 修回日期:2011-11-12 发布日期:2012-04-20 出版日期:2012-04-01
通讯作者: 陈小冬
作者简介:陈小冬(1978-)，女，浙江温州人，讲师，硕士，主要研究方向：模式识别、神经计算；
林焕祥(1975-)，男，浙江温州人，讲师，硕士，主要研究方向：模式识别、神经计算。
基金资助:
浙江省自然科学基金资助项目;浙江省教育厅2011年度科研计划项目;中央广播电视大学资助项目;浙江广播电视大学资助项目;2010年浙江省高校优秀青年教师资助计划项目

Sparse discriminant analysis

CHEN Xiao-dong¹,LIN Huan-xiang²

1. School of Information and Engineering, Zhejiang Radio and Television University, Hangzhou Zhejiang 310030, China
2. School of Information and Electronic Engineering,Zhejiang University of Science and Technology, Hangzhou Zhejiang 310023, China

Received:2011-09-13 Revised:2011-11-12 Online:2012-04-20 Published:2012-04-01
Contact: CHEN Xiao-dong

摘要/Abstract

摘要： 针对流形嵌入降维方法中在高维空间构建近邻图无益于后续工作，以及不容易给近邻大小和热核参数赋合适值的问题，提出一种稀疏判别分析算法（SEDA）。首先使用稀疏表示构建稀疏图保持数据的全局信息和几何结构，以克服流形嵌入方法的不足；其次，将稀疏保持作为正则化项使用Fisher判别准则，能够得到最优的投影。在一组高维数据集上的实验结果表明，SEDA是非常有效的半监督降维方法。

关键词: 判别分析, 稀疏表示, 近邻图, 稀疏图

Abstract: Methods for manifold embedding have the following issues: on one hand, neighborhood graph is constructed in such high-dimensionality of original space that it tends to work poorly; on the other hand, appropriate values for the neighborhood size and heat kernel parameter involved in graph construction are generally difficult to be assigned. To address these problems, a new semi-supervised dimensionality reduction algorithm called SparsE Discriminant Analysis (SEDA) was proposed. Firstly, SEDA set up a sparse graph to preserve the global information and geometric structure of the data based on sparse representation. Secondly, it applied both sparse graph and Fisher criterion to seek the optimal projection. The experimental results on a broad range of data sets show that SEDA is superior to many popular dimensionality reduction methods.

Key words: discriminant analysis, sparse representation, neighborhood graph, sparse graph

陈小冬林焕祥. 稀疏判别分析[J]. 计算机应用, 2012, 32(04): 1017-1021.

CHEN Xiao-dong LIN Huan-xiang. Sparse discriminant analysis[J]. Journal of Computer Applications, 2012, 32(04): 1017-1021.

参考文献

［1］ YE J, ZHAO Z, WU M. Discriminative K-Means for clustering［EB/OL］.[2011-05-01].http://www.kyb.mpg.de/publications/attachments/NIPS2007-Ye_4710[0].pdf. ［2］ CHEN H T, CHANG H W, LIU T L. Local discriminant embedding and its variants［C］// CVPR05: Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 2005:846-853. ［3］尹学松, 胡恩良, 陈松灿. 基于成对约束的半监督判别分析［J］. 软件学报, 2008, 19(11): 2791-2802. ［4］ QIAO L, CHEN S, TAN X. Sparsity preserving projections with applications to face recognition［J］. Pattern Recognition,2010,43(1):331-341. ［5］ YIN X, HU E. Distance metric learning guided adaptive subspace semi-supervised clustering［J］. Frontiers of Computer Science in China, 2011, 5(1): 100-108. ［6］ HOI S C H, LIU W, LYU M R, et al. Learning distance metrics with contextual constraints for image retrieval［C］// CVPR06: Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society,2006:2072-2078. ［7］陈小冬, 尹学松, 林焕祥. 基于判别分析的半监督聚类方法［J］. 计算机工程与应用, 2010, 46(6): 139-143. ［8］ YAN S, XU D, ZHANG B, et al. Graph embedding and extensions: A general framework for dimensionality reduction［EB/OL］.[2011-08-01].http://www.ntu.edu.sg/home/dongxu/TPAMI-GE.pdf . ［9］ HE XIAO-FEI, NIYOGI P. Locality preserving projections［EB/OL］.[2011-08-01]. http://people.cs.uchicago.edu/～xiaofei/conference-24.pdf. ［10］ CAI D, HE X, HAN J. Semi-supervised discriminant analysis［EB/OL］.[2011-08-01]. http://www.cs.uiuc.edu/～hanj/pdf/iccv07_dengcai_SDA.pdf. ［11］ CAI DENG, HE XIAO-FEI, HAN JIA-WEI. Sparse projections over graph［EB/OL］.[2011-09-01]. http:// www.aaai.org/Papers/AAAI/2008/AAAI08-097.pdf . ［12］ SUGIYAMA M. Dimensionality reduction of multimodal labeled data by local fisher discriminant analysis［J］.The Journal of Machine Learning Research, 2007,8(5):1027-1061. ［13］尹学松, 胡恩良. 半监督局部维数约减［J］. 中国图象图形学报, 2011, 16(9): 2121-2131. ［14］ SUGIYAMA M, NAKAJIMA T, SESE J. Semi-supervised local Fisher discriminant analysis for dimensionality reduction［J］. Machine Learning, 2010:78(1/2):35-61. ［15］尹学松, 胡恩良. 半监督正则化学习［J］.小型微型计算机系统, 2010, 31(12):2389-2393. ［16］ BELHUMEUR P, HSSPANHA J, KRIEGMAN D. Eigenfaces vs. Fisherfaces: Recognition using class specific linear projection［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997,19(7): 711-720. ［17］ LIU W, CHANG S-F. Robust multi-class transductive learning with graphs［C］// Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. [S.l.]:IEEE, 2009:8. ［18］ BELKIN M, NIYOGI P. Laplacian eigenmaps for dimensionality reduction and data representation[J]. Neural Computation, 2003,15 (6):1373-1396. ［19］ ZHANG L, QIAO L, CHEN S. Graph-optimized locality preserving projections［J］. Pattern Recognition, 2010, 43(6):1993-2002. ［20］ TANG W, XIONG H, ZHONG S, et al.Enhancing semi-supervised clustering: A feature projection perspective［C］// KDD07: Proceedings of the 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM,2007:707-716. ［21］ XIANG S, NIE F, ZHANG C. Learning a Mahalanobis distance metric for data clustering and classification［J］. Pattern Recognition, 2008,41(12):3600-3612. ［22］ SONG Y, NIE F, ZHANG C, et al.A unified framework for semi-supervised dimensionality reduction［J］. Pattern Recognition, 2008,41(9): 2789-2799. ［23］ CHATPATANASIRI R, KIJSIRIKUL B. A unified semi-supervised dimensionality reduction framework for manifold learning［J］. Neurocomputing, 2010, 73(3): 1631-1640. ［24］ JOLLIFFE I. Principal component analysis［M］. 2nd. Berlin: Springer,2002. ［25］ WRIGHT J, YANG A, SASTRY S, et al. Robust face recognition via sparse representation［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(2):210-227. ［26］ LIU J, YE J. Efficient euclidean projections in linear time［EB/OL］.[2011-06-01].http://machinelearning.org/archive/icml2009/papers/123.pdf. ［27］ ZHANG K, KWOK J T. Density-weighted Nystrm method for computing large kernel eigensystems［J］.Neural Computation,2009, 21(1):121-146.

[1]	裴春阳, 樊宽刚, 马政. 基于边缘保留分解和改进稀疏表示的医学图像融合[J]. 计算机应用, 2021, 41(7): 2092-2099.
[2]	任晓奎, 刘鹏飞, 陶志勇, 刘影, 白立春. 基于单快拍信号到达角估计算法的室内入侵检测[J]. 计算机应用, 2021, 41(4): 1153-1159.
[3]	王丽娟, 陈少敏, 尹明, 许跃颖, 郝志峰, 蔡瑞初, 温雯. 基于近邻图改进的块对角子空间聚类算法[J]. 计算机应用, 2021, 41(1): 36-42.
[4]	高彦彦, 李莉, 张晶, 贾英茜. 结合梯度投影稀疏重构和复数小波的图像重构[J]. 计算机应用, 2020, 40(2): 486-490.
[5]	宗春梅, 张月琴, 曹建芳, 赵青杉. 基于深度先验及非局部相似性的压缩感知核磁共振成像[J]. 计算机应用, 2020, 40(10): 3054-3059.
[6]	吴宗骏, 吴炜, 杨晓敏, 刘凯, Gwanggil Jeon, 袁皓. 改进的基于稀疏表示的全色锐化算法[J]. 计算机应用, 2019, 39(2): 540-545.
[7]	陶永鹏, 景雨, 顼聪. 基于分组字典与变分模型的图像去噪算法[J]. 计算机应用, 2019, 39(2): 551-555.
[8]	杜凯敏, 康宝生. 基于图像块分类的图像超分辨率重建[J]. 计算机应用, 2019, 39(2): 577-581.
[9]	丁建立, 穆涛, 王怀超. 基于谱回归核判别分析的候机楼室内快速定位算法[J]. 计算机应用, 2019, 39(1): 256-261.
[10]	周立军, 刘凯, 吕海燕. 基于竞争学习的稀疏受限玻尔兹曼机机制[J]. 计算机应用, 2018, 38(7): 1872-1876.
[11]	王丽芳, 董侠, 秦品乐, 高媛. 基于自适应联合字典学习的脑部多模态图像融合方法[J]. 计算机应用, 2018, 38(4): 1134-1140.
[12]	邹佳彬, 孙伟. 基于提升静态小波变换与联合结构组稀疏表示的多聚焦图像融合[J]. 计算机应用, 2018, 38(3): 859-865.
[13]	王鑫, 周韵, 宁晨, 石爱业. 自适应融合局部和全局稀疏表示的图像显著性检测[J]. 计算机应用, 2018, 38(3): 866-872.
[14]	孙念, 张毅, 林海波, 黄超. 基于多特征i-vector的短语音说话人识别算法[J]. 计算机应用, 2018, 38(10): 2839-2843.
[15]	贾旭, 孙福明, 李豪杰, 曹玉东. 具有普适性的改进非负矩阵分解图像特征提取方法[J]. 计算机应用, 2018, 38(1): 233-237.

稀疏判别分析

Sparse discriminant analysis

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics