| 1,796 | 44 | 402 |
| 下载次数 | 被引频次 | 阅读次数 |
数据之间的相关性分析是大数据处理的重要组成部分,典型相关分析及其扩展方法在多个领域得到了广泛应用.主要有用于解决多数据集特征融合的多集合典型相关分析,用于处理特征之间非线性关系的核典型相关分析,用于处理有类别特征数据时的判别典型相关分析,用于处理有噪声数据时的稀疏典型相关分析等扩展方法.本文全面综述了典型相关分析原理及其各种扩展方法,最后对这一方法的研究前景给出讨论和展望.
Abstract：Correlation analysis between data has become an important part of large data processing.The canonical correlation analysis method and its extensions have been widely used in various fields.The multiple canonical correlation analysis is used to solve the feature fusion for multi-data sets.The kernel canonical correlation analysis is used to find out the non-linear relationship between the data.The discriminant canonical correlation analysis is used to analyze the data which carry category information.The sparse canonical correlation analysis is used to solve the data with too many characteristics.In this paper,the principles of the canonical correlation analysis method and its various extensions are introduced.At the end of this paper,the prospects and outlook of the canonical correlation analysis are discussed.
[1]HOTELLING H.Relations between two sets of variates[J].Biometrika,1936,28:321-377.
[2]RICHARD A J,DEAN W W.实用多元统计分析[M].陆璇,叶俊,译.6版.北京:清华大学出版社,2008:420-440.
[3]AKAHO S.A kernel method for canonical correlation analysis[J].In Proceedings of the International Meeting of the Psychometric Society,2006,40(2):263-269.
[4]YAMANISHI Y,VERT J P,NAKAYA A,et al.Extraction of correlated gene clusters from multiple genomic data by generalized kernel canonical correlation analysis[J].Bioinformatics,2003,19(Suppl1):323-330.
[5]PARHJOMENKO E,TRITCHLER D,BEYENE J.Genome-wide sparse canonical correlation of gene expression with genotypes[J].BMC Proceedings,2007,1(Suppl1):S119.
[6]SUN T K,CHEN S G,YANG J Y,et al.A novel method of combined feature extraction for recognition[C]//2008Eighth IEEE International Conference on Data Mining.Portugal:[s.n.],2008:1043-1048.
[7]WANG C.Variational Bayesian approach to canonical correlation analysis[J].IEEE Transactions on Neural Networks,2007,18(3):905-910.
[8]FRANCIS R B,MICHAEL I J.A probabilistic interpretation of canonical correlation analysis[R].Berkeley:Department of Statistics,University of California,2005.
[9]VIRTANEN S,KLAMI A,KASKI S.Bayesian CCA via group sparsity[C]//International Conference on Machine Learning.Washington:DBLP,2011:457-464.
[10]ZHANG L H,LIAO L Z,SUN L M.Towards the global solution of the maximal correlation problem[J].J Glob Optim,2011,49(1):91-107.
[11]KETTENRING J R.Canonical analysis of several sets of variables[J].Biometrika,1969(3):433-451.
[12]AKAHO S.A kernel method for canonical correlation analysis[J].In Proceedings of the International Meeting of the Psychometric Society,2006,40(2):263-269.
[13]NICHOLAS B L,GREGORY D J,MELISSA C L,et al.Kernel canonical correlation analysis for assessing genegene interactions and application to ovarian cancer[J].European Journal of Human Genetics,2014,22,126-131.
[14]SUN T K,CHEN S G,YANG J Y,et al.Discriminative canonical correlation analysis with missing samples[C]//Wri World Congress on Computer Science and Information Engineering.Portugal:[s.n.],2009:95-99.
[15]PENG Y,ZHANG D Q,ZHANG J C.A new canonical correlation snalysis slgorithm with local discrimination[J].Neural Processing Letters,2010,31(1):1-15.
[16]王磊,史亚,姬红兵.基于多集典型相关分析的雷达辐射源指纹识别[J].西安电子科技大学学报(自然科学版),2013,40(2):164-171.WANG L,SHI Y,JI H B.Specific radar emitter identification using multiset canonical correlation analysis[J].Journal of Xidian University(Natural Science Edition),2013,40(2):164-171.
[17]SRIPERUMBUDUR B K,TORRES D A,LANCKRIET G R G.Sparse eigen methods by D.C.programming[C]//International Conference on Machine Learning.Portugal:[s.n.],2007:831-838.
[18]WAAIJENBORG S,PC V D W H,ZWINCLERMAN A H.Quantifying the association between gene expressions and DNA-markers by penalized canonical correlation analysis[J].Statistical Applications in Genetics&Molecular Biology,2008,7(1):1-29.
[19]WITTEN D M,ROBERT T,TREVOR H.A penalized matrix decomposition,with applications to sparse principal components and canonical correlation analysis[J].Biostatistics,2009,10(10):515-34.
[20]TORRES D A,TURNBULL D,SRIPERUMBUDUR B K,et al.Finding musically meaningful words by dparse CCA[C]//Neural Information Processing Systems.Portugal:[s.n.],2007:1-8.
[21]YAN J J,ZHENG W M,ZHOU X Y,et al.Sparse 2-D canonical correlation analysis via low rank matrix approximation for feature extraction[J].IEEE Signal Processing Letters,2012,19(1):51-54.
[22]KITAJIMA M,KITAGAWA Y,OHMORI T,et al.A greedy approach to sparse canonical correlation analysis[J].Fems Microbio-logy Letters,1991,66(2):203-208.
[23]COLIN F,GAYEL L.Two Methods for sparsifying probabilistic canonical correlation analysis[C]//Neural Information Processing,International Conference.Portugal:[s.n.],2006:361-367.
[24]ZHOU Z H,ZHAN D C,YANG Q.Semisupervised learning with very few labeled training examples[C]//AAAI Conference on Artificial Intelligence.Vancouver,Canada:DBLP,2007:675-680.
[25]李雪,林和平,李迎斌.灰典型相关分析研究与应用[J].计算机工程与科学,2009,31(6):121-125.LI X,LIN H P,LI Y B.Research and application of grey canonical correlation analysis[J].Computer Engineering and Science,2009,31(6):121-125.
[26]KIM T K,WONG K Y K,CIPOLLA R.Tensor canonical correlation analysis for action classification[C]//IEEE Conference on Computer Vision&Pattern Recognition.Portugal:[s.n.],2007:1-8.
[27]AN L,YANG S F,BHANU B.Person re-identification by robust canonical correlation analysis[J].Signal Processing Letters IEEE,2015,22(8):1103-1107.
[28]YIN X R.Canonical correlation analysis based on information theory[J].Journal of Multivariate Analysis,2004,91(2):161-176.
基本信息:
DOI：
中图分类号:TP311.13
引用信息:
[1]李有梅,梁珣.典型相关分析综述[J],2017,28(01):113-118.
基金信息:
国家自然科学基金资助项目(No.11301494)