基于全局距离和类别信息的邻域保持嵌入算法

doi:10.6040/j.issn.1672-3961.0.2015.296

山东大学学报(工学版) ›› 2016, Vol. 46 ›› Issue (1): 10-14.doi: 10.6040/j.issn.1672-3961.0.2015.296

基于全局距离和类别信息的邻域保持嵌入算法

梅清琳^1,2,张化祥^1,2*

1. 山东师范大学信息科学与工程学院, 山东济南 250014;
2. 山东省分布式计算机软件新技术重点实验室, 山东济南 250014

收稿日期:2015-09-10 出版日期:2016-02-20 发布日期:2015-09-10
通讯作者: 张化祥(1966- ),男,山东济宁人,教授,博士生导师,博士,主要研究方向为机器学习,模式识别及Web挖掘等. ;E-mail: huaxzhang@163.com E-mail:meiqinglinkf@163.com
作者简介:梅清琳(1991- ),女,山东淄博人,硕士研究生,主要研究方向为机器学习与数据挖掘等. E-mail:meiqinglinkf@163.com
基金资助:
国家自然科学基金资助项目(61170145,61373081);教育部博士点基金资助项目(20113704110001);山东省自然科学基金资助项目(ZR2010FM021);山东省科技攻关计划资助项目(2013GGX10125)

A neighborhood preserving embedding algorithm based on global distance and label information

MEI Qinglin^1,2, ZHANG Huaxiang^1,2*

1. School of Information Science and Engineering, Shandong Normal University, Jinan 250014, Shandong, China;
2. Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology, Jinan 250014, Shandong, China

Received:2015-09-10 Online:2016-02-20 Published:2015-09-10

摘要/Abstract

摘要： 提出一种基于全局距离和类别信息的邻域保持嵌入算法。该方法在使用欧氏距离构造邻域图中,加入表征全局距离的全局因子和表示类别信息的函数项,全局因子可以使分布不均匀的样本变得平滑均匀,类别信息可以使同类样本点紧凑异类样本点疏离,通过提高所选邻近点的质量,优化数据的局部邻域,使降维后的数据具有更好的可分性。试验结果表明,该算法具有较高的准确率,优于传统的邻域保持嵌入算法。

关键词: 全局距离, 类别信息, 降维, 邻域保持嵌入算法, 邻域优化

Abstract: An algorithm of neighborhood preserving embedding based on global distance and label information was proposed. A global factor that characterized the global distance and a function term that characterized the label information were added in the traditional Euclidean distance formula of adjacent graph. Global factor could make unevenly dirtibuted samples smooth and uniform, label information could make intra-class compact and inter-class separable, which improved quality of neighborhood and constructed an optimal adjacency graph, and improved classification accuracy. Experimental results showed that the proposed algorithm had higher accuracy and performed more effective than traditional neighborhood preserving embedding algorithm.

Key words: label information, neighborhood optimization, neighborhood preserving embedding algorithm, dimension reduction, global distance

中图分类号:

TP391

梅清琳,张化祥. 基于全局距离和类别信息的邻域保持嵌入算法[J]. 山东大学学报(工学版), 2016, 46(1): 10-14.

MEI Qinglin, ZHANG Huaxiang. A neighborhood preserving embedding algorithm based on global distance and label information[J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2016, 46(1): 10-14.

参考文献

[1] 周志华, 杨强. 机器学习及其应用[M].北京:清华大学出版社, 2011:87-95.
[2] EGECIOGLU O, FERHATOAMANOGLU H, OGRAS U. Dimensionality reduction and similarity computation by inner-product approximations[J].IEEE Transactions on Knowledge and Data Engineering, 2004, 16(6):714-726.
[3] BELKIN M, NIYOGI P. Laplacian eigenmaps for dimensionality reduction and data representation[J]. Neural Computation, 2003, 15(6):1373-1396.
[4] 赵连伟, 罗四维, 赵艳敞, 等. 高维数据流形的低维嵌入及嵌入维数研究[J]. 软件学报, 2005, 16(8):1423-1430. ZHAO Lianwei, LUO Siwei, ZHAO Yanchang, et al. Study on the low-dimensional embedding and the embedding dimensionality of manifold of high-dimensional data[J].Journal of Software, 2005, 16(8):1423-1430.
[5] TENENBAUMe J B, DE SILVA V, LANGFORD J C. A global geometric framework for nonlinear dimensionality reduction[J].Science, 2000, 290(5500):2319-2323.
[6] HUANG Hong, HUANG Yunbiao. Improved discriminant sparsity neighborhood preserving embedding for hyperspectral image classification[J].Neurocomputing, 2014, 136(2014):224-234.
[7] JOLLIFFE I T. Principle component analysis[M]. Berlin: Springer-Verlag, 1986: 384-389.
[8] WANG Fei, WANG Xin, ZHANG Daoqiang, et al. MarginFace: A novel face recognition method by average neighborhood margin maximization[J]. Pattern Recognition, 2009, 42(11):2863-2875.
[9] BELHUMEUR P N, HESPANDA J P, KRIEGMAN D J. Eigenfaces vs. fisherfaces: Recognition using class specific linear projection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(7):711-720.
[10] HE Xiaofei, NIYOGI P. Locality preserving projections[J]. Advances in Neural Information Processing Systems, 2005, 45(1):186-197.
[11] HAM J, LEE D D, SAUL L K. Semi-supervised alignment of manifolds[J]. International Workshop on Articial Intelligence & Statistics, 2005:120-127.
[12] ROWEIS S T, SAUL L K. Nonlinear dimensionality reduction by locally linear embedding[J]. Science, 2000, 290(5500):2323-2326.
[13] HE Xiaofei, CAI Deng, YAN Shuicheng, et al. Neighborhood preserving embedding[C] //Proceedings of the Tenth IEEE International Conference on Computer Vision Workshops. New York, USA: IEEE, 2005:1208-1213.
[14] YIN Fei, JIAO L C, SHANG Fanhua, et al. Sparse regularization discriminant analysis for face recognition[J]. Neurocomputing, 2014, 128:341-362.
[15] ZHANG Wei, XUE Xiangyang, LU Hong, et al. Discriminant neighborhood embedding for classification[J]. Pattern Recognition, 2006, 39(11):2240-2243.
[16] GUI Jie, SUN Zhenan, JIA Wei, et al. Discriminant sparse neighborhood preserving embedding for face recognition[J]. Pattern Recognition, 2012, 45(8):2884-2893.
[17] CHENG Bin, YANG Jianchao, YAN Shuicheng, et al. Learning with l1-graph for image analysis[J]. IEEE Transactions on Image Processing, 2010, 19(4):858-866.
[18] QIAO Lishan, CHEN Songcan, TAN Xiaoyan. Sparsity preserving projections with applications to face recognition[J]. Pattern Recognition, 2010, 43(1):331-341.
[19] 包兴, 张莉, 赵梦梦, 等. 基于类别信息的邻域保持嵌入算法[J]. 计算机科学, 2015, 42(5):94-97. BAO Xing, ZHANG Li, ZHAO Mengmeng, et al. Label information-based neighbourhood preserving embedding[J]. Computer Science, 2015, 42(5):94-97.
[20] WANG Yong, WU Yi. Complete neighborhood preserving embedding for face recognition[J]. Pattern Recognition, 2010, 43(3):1008-1015.
[21] SAMARIA F S, HARTER A C. Parameterisation of a stochastic model for human face identification[C] //Proceedings of the Second IEEE Workshop on Applications of Computer Vision. New York, USA: IEEE, 1994:138-142.
[22] LEE K C, HO J, KRIEGMAN D J. Acquiring linear subspaces for face recognition under variable lighting[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(5):684-698.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于全局距离和类别信息的邻域保持嵌入算法

A neighborhood preserving embedding algorithm based on global distance and label information

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 10

多维度评价

本文评价

推荐阅读 10

[1]	钱文光,李会民. 一种相似子空间嵌入算法[J]. 山东大学学报(工学版), 2018, 48(1): 8-14.
[2]	张玉玲,尹传环. 基于SVM的安卓恶意软件检测[J]. 山东大学学报(工学版), 2017, 47(1): 42-47.
[3]	文志强,朱文球,胡永祥. 半调图像的分类方法[J]. 山东大学学报(工学版), 2013, 43(4): 7-12.
[4]	张永军1,刘金岭2,于长辉3. 基于词贡献度的垃圾短信分类方法[J]. 山东大学学报(工学版), 2012, 42(5): 87-90.
[5]	王熙照,白丽杰*,花强,刘玉超. null[J]. 山东大学学报(工学版), 2011, 41(4): 1-6.
[6]	崔燕,范丽亚. 高维数据正定核与不定核的KPCA变换阵比较[J]. 山东大学学报(工学版), 2011, 41(1): 17-23.
[7]	贺广南，杨育彬*. 基于流形学习的图像检索算法研究[J]. 山东大学学报(工学版), 2010, 40(5): 129-136.
[8]	曾雪强1,李国正2. 基于偏最小二乘降维的分类模型比较[J]. 山东大学学报(工学版), 2010, 40(5): 41-47.
[9]	张道强. 知识保持的嵌入方法[J]. 山东大学学报(工学版), 2010, 40(2): 1-10.
[10]	张丽梅1,2 ,乔立山1,2 ,陈松灿1 . 基于张量模式的特征提取及分类器设计综述[J]. 山东大学学报(工学版), 2009, 39(1): 6-14.