Independent component analysis: A statistical perspective

被引:46
作者
Nordhausen, Klaus [1 ]
Oja, Hannu [2 ]
机构
[1] Vienna Univ Technol, Inst Stat & Math Methods Econ, Vienna, Austria
[2] Univ Turku, Dept Math & Stat, FIN-20014 Turku, Finland
来源
WILEY INTERDISCIPLINARY REVIEWS-COMPUTATIONAL STATISTICS | 2018年 / 10卷 / 05期
关键词
asymptotic distribution; blind source separation (BSS); fastICA; fourth-order blind identification (FOBI); joint approximate diagonalization of eigenmatrices (JADE); minimum distance index; projection pursuit (PP);
D O I
10.1002/wics.1440
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
Independent component analysis (ICA) is a data analysis tool that can be seen as a refinement of principal component analysis or factor analysis. ICA recovers the structures in the data which stay hidden if only the covariance matrix is used in the analysis. The ICA problem is formulated as a latent variable model where the observed variables are linear combinations of unobserved mutually independent non-Gaussian variables. The goal is to recover linear transformations back to these latent independent components (ICs). As a statistical tool, the unmixing procedure is expressed as a functional in a relevant semiparametric model which further allows a careful formulation of the inference problem and the comparison of competing estimation procedures. For most approaches, the ICs are found in two steps, (a) by standardizing the random vector and then (b) by rotating the standardized vector to the ICs. In the projection pursuit, the ICs can be found either one-by-one or simultaneously and this is discussed in detail when the convex combination of the squared third and fourth cumulants is used as a projection index. Alternative projection indices and their use are also explained. The classical fourth-order blind identification (FOBI) and joint approximate diagonalization of eigenmatrices (JADE) are described as well. The statistical tools for the comparison of consistent and asymptotically multivariate normal unmixing matrix estimates are discussed. Finally, recent extensions for times series, matrix- and tensor-valued and functional data are reviewed. This article is categorized under: Statistical and Graphical Methods of Data Analysis > Modeling Methods and Algorithms Statistical Models > Multivariate Models Statistical and Graphical Methods of Data Analysis > Dimension Reduction Statistical and Graphical Methods of Data Analysis > Information Theoretic Methods
引用
收藏
页数:23
相关论文
共 50 条
  • [31] Data partitioning and independent component analysis techniques applied to fMRI
    Wismüller, A
    Meyer-Bäse, A
    Lange, O
    Otto, T
    Auer, D
    [J]. INDEPENDENT COMPONENT ANALYSES, WAVELETS, UNSUPERVISED SMART SENSORS, AND NEURAL NETWORKS II, 2004, 5439 : 104 - 115
  • [32] An Improved Multiplicative Updating Algorithm for Nonnegative Independent Component Analysis
    Li, Hui
    Shen, Yue-hong
    Wang, Jian-gong
    [J]. ETRI JOURNAL, 2013, 35 (02) : 193 - 199
  • [34] Determining Fetal Heart Rate Using Independent Component Analysis
    Szalai, Janos
    Mozes, Ferenc Emil
    [J]. 2014 IEEE INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTER COMMUNICATION AND PROCESSING (ICCP), 2014, : 11 - +
  • [35] Independent Component Analysis Over Galois Fields of Prime Order
    Yeredor, Arie
    [J]. IEEE TRANSACTIONS ON INFORMATION THEORY, 2011, 57 (08) : 5342 - 5359
  • [36] Human Voice Sample Separation Using Independent Component Analysis
    Sudhakara, Sweekar
    Ahmed, Syed Raehan
    Sagar, B. M. Veerendra
    Swamy, P. M. Shivakumara
    [J]. 2018 4TH INTERNATIONAL CONFERENCE FOR CONVERGENCE IN TECHNOLOGY (I2CT), 2018,
  • [37] Research of Blind Image Separation Based on Independent Component Analysis
    Tian, Qi-chong
    Zheng, Wei-guo
    Feng, Shao-huai
    Zhang, Li-dong
    [J]. ACC 2009: ETP/IITA WORLD CONGRESS IN APPLIED COMPUTING, COMPUTER SCIENCE, AND COMPUTER ENGINEERING, 2009, : 430 - 433
  • [38] A Contrast Function for Independent Component Analysis Without Permutation Ambiguity
    Zarzoso, Vicente
    Comon, Pierre
    Phlypo, Ronald
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 2010, 21 (05): : 863 - 868
  • [39] Automated EEG Artifact Detection Using Independent Component Analysis
    Echtioui, Amira
    Zouch, Wassim
    Ghorbel, Mohamed
    Ben Slima, Mohamed
    Ben Hamida, Ahmed
    Mhiri, Chokri
    [J]. 2020 5TH INTERNATIONAL CONFERENCE ON ADVANCED TECHNOLOGIES FOR SIGNAL AND IMAGE PROCESSING (ATSIP'2020), 2020,
  • [40] Independent component analysis applied to the P600 component of event-related potentials
    Ventouras, E
    Moatsos, M
    Papageorgiou, C
    Rabavilas, A
    Uzunoglu, N
    [J]. PROCEEDINGS OF THE 26TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY, VOLS 1-7, 2004, 26 : 80 - 83