The Experts below are selected from a list of 23928 Experts worldwide ranked by ideXlab platform

Yoshio Takane - One of the best experts on this subject based on the ideXlab platform.

  • Functional Multiple-Set Canonical Correlation Analysis
    Psychometrika, 2011
    Co-Authors: Heungsun Hwang, Kwanghee Jung, Yoshio Takane, Todd S Woodward
    Abstract:

    We propose functional multiple-set Canonical Correlation Analysis for exploring associations among multiple sets of functions. The proposed method includes functional Canonical Correlation Analysis as a special case when only two sets of functions are considered. As in classical multiple-set Canonical Correlation Analysis, computationally, the method solves a matrix eigen-Analysis problem through the adoption of a basis expansion approach to approximating data and weight functions. We apply the proposed method to functional magnetic resonance imaging (fMRI) data to identify networks of neural activity that are commonly activated across subjects while carrying out a working memory task.

  • Generalized Canonical Correlation Analysis with missing values
    Computational Statistics, 2011
    Co-Authors: Michel Van De Velden, Yoshio Takane
    Abstract:

    Generalized Canonical Correlation Analysis is a versatile technique that allows the joint Analysis of several sets of data matrices. The generalized Canonical Correlation Analysis solution can be obtained through an eigenequation and distributional assumptions are not required. When dealing with multiple set data, the situation frequently occurs that some values are missing. In this paper, two new methods for dealing with missing values in generalized Canonical Correlation Analysis are introduced. The first approach, which does not require iterations, is a generalization of the Test Equating method available for principal component Analysis. In the second approach, missing values are imputed in such a way that the generalized Canonical Correlation Analysis objective function does not increase in subsequent steps. Convergence is achieved when the value of the objective function remains constant. By means of a simulation study, we assess the performance of the new methods. We compare the results with those of two available methods; the missing-data passive method, introduced in Gifi’s homogeneity Analysis framework, and the GENCOM algorithm developed by Green and Carroll. An application using world bank data is used to illustrate the proposed methods.

  • Generalized Canonical Correlation Analysis with missing values
    2009
    Co-Authors: Michel Van De Velden, Yoshio Takane
    Abstract:

    Two new methods for dealing with missing values in generalized Canonical Correlation Analysis are introduced. The first approach, which does not require iterations, is a generalization of the Test Equating method available for principal component Analysis. In the second approach, missing values are imputed in such a way that the generalized Canonical Correlation Analysis objective function does not increase in subsequent steps. Convergence is achieved when the value of the objective function remains constant. By means of a simulation study, we assess the performance of the new methods. We compare the results with those of two available methods; the missing-data passive method, introduced Gifi's homogeneity Analysis framework, and the GENCOM algorithm developed by Green and Carroll.

  • Generalized constrained Canonical Correlation Analysis
    Multivariate Behavioral Research, 2002
    Co-Authors: Yoshio Takane, Heungsun Hwang
    Abstract:

    A method for generalized constrained Canonical Correlation Analysis (GCCANO) is proposed that incorporates external information on both rows and columns of data matrices. In this method each set of variables is first decomposed into the sum of several submatrices according to the external information, and then Canonical Correlation Analysis is applied to pairs of derived submatrices, one from each set, to explore linear relationships between them. Technically, the former amounts to projections of the data matrix onto the spaces spanned by matrices of external information, while the latter involves the generalized singular value decomposition of a matrix with certain metric matrices. GCCANO subsumes a number of existing methods as special cases. It generalizes various kinds of linearly constrained correspondence Analysis as well as multivariate Analysis of variance/Canonical discriminant Analysis. Permutation tests are applied to test the significance of Canonical Correlations obtained from GCCANO. Example...

  • Canonical Correlation Analysis with linear constraints
    Linear Algebra and its Applications, 1992
    Co-Authors: Haruo Yanai, Yoshio Takane
    Abstract:

    AbstractWe develop Canonical Correlation Analysis by imposing linear constraints upon parameters corresponding to two sets of variables. The results of our method, which we call canolc, are shown in terms of projection operators both orthogonal and oblique. Further, calc (correspondence Analysis with linear constraints) turns out to be a special case of canolc

Colin Fyfe - One of the best experts on this subject based on the ideXlab platform.

  • Sparsiflcation of Probabilistic Canonical Correlation Analysis
    2006
    Co-Authors: Daniel Livingstone, Colin Fyfe
    Abstract:

    We have recently developed several ways of performing Canonical Correlation Analysis (1, 5, 7, 4) with probabilistic methods rather than the standard statistical tools. How- ever, the computational demands of training such methods scales with the square of the number of samples, making these methods uncompetitive with e.g. artiflcial neural network methods (3, 2). In this paper, we examine a recent development which sparsifles a probabilistic method of performing principal component Analysis and then use this method to sparsify a new proba- bilistic method of performing Canonical Correlation Analysis.

  • ICONIP (1) - Two methods for sparsifying probabilistic Canonical Correlation Analysis
    Neural Information Processing, 2006
    Co-Authors: Colin Fyfe, Gayle Leen
    Abstract:

    We have recently developed several ways of performing Canonical Correlation Analysis [1,5,7,4] with probabilistic methods rather than the standard statistical tools. However, the computational demands of training such methods scales with the square of the number of samples, making these methods uncompetitive with e.g. artificial neural network methods [3,2]. In this paper, we examine two recent developments which sparsify probabilistic methods of performing Canonical Correlation Analysis.

  • The Sphere-Concatenate Method for Gaussian Process Canonical Correlation Analysis
    Lecture Notes in Computer Science, 2006
    Co-Authors: Pei Ling Lai, Gayle Leen, Colin Fyfe
    Abstract:

    We have recently developed several ways of using Gaussian Processes to perform Canonical Correlation Analysis. We review several of these methods, introduce a new way to perform Canonical Correlation Analysis with Gaussian Processes which involves sphering each data stream separately with probabilistic principal component Analysis (PCA), concatenating the sphered data and re-performing probabilistic PCA. We also investigate the effect of sparsifying this last method. We perform a comparative study of these methods.

  • kernel and nonlinear Canonical Correlation Analysis
    International Journal of Neural Systems, 2000
    Co-Authors: Colin Fyfe
    Abstract:

    We have previously [4] derived a neural network implementation of the statistical technique of Canonical Correlation Analysis (CCA). We extend this to nonlinear CCA either by adding a nonlinearity to our neural method or by nonlinearly transforming the data to a feature space and then performing linear CCA in this feature space. We give comparative results on both artificial and real data sets.

  • kernel and nonlinear Canonical Correlation Analysis
    International Journal of Neural Systems, 2000
    Co-Authors: Pei Ling Lai, Colin Fyfe
    Abstract:

    We review a neural implementation of the statistical technique of Canonical Correlation Analysis (CCA) and extend it to nonlinear CCA. We then derive the method of kernel-based CCA and compare these two methods on real and artificial data sets before using both on the Blind Separation of Sources.

Ling Guan - One of the best experts on this subject based on the ideXlab platform.

  • CCECE - A Discriminant Two-Dimensional Canonical Correlation Analysis
    2019 IEEE Canadian Conference of Electrical and Computer Engineering (CCECE), 2019
    Co-Authors: Lei Gao, Ling Guan
    Abstract:

    Two-dimensional Canonical Correlation Analysis (2D-CCA) is an effective method for two-view feature extraction and fusion. It is able to reduce the computational complexity while reserving local data structure of a two-dimensional signal, e.g., image. However, since 2D-CCA only reveals the structure of the input data set without discriminatory information, it cannot effectively extract and represent discriminant representations for recognition and classification. Aiming at providing a method for discriminant feature extraction and fusion, this paper proposes a discriminant 2D Canonical Correlation Analysis (D2DCCA), utilizing descriptor of 2DCCA and scatter information of different classes to improve recognition performance. We conduct experiments on AR face database to evaluate the performance of the proposed method. Experimental results show that the proposed D2DCCA outperforms other related algorithms.

  • Discriminative Multiple Canonical Correlation Analysis for Information Fusion
    IEEE Transactions on Image Processing, 2018
    Co-Authors: Lin Qi, Enqing Chen, Ling Guan
    Abstract:

    In this paper, we propose the discriminative multiple Canonical Correlation Analysis (DMCCA) for multimodal information Analysis and fusion. DMCCA is capable of extracting more discriminative characteristics from multimodal information representations. Specifically, it finds the projected directions, which simultaneously maximize the within-class Correlation and minimize the between-class Correlation, leading to better utilization of the multimodal information. In the process, we analytically demonstrate that the optimally projected dimension by DMCCA can be quite accurately predicted, leading to both superior performance and substantial reduction in computational cost. We further verify that Canonical Correlation Analysis (CCA), multiple Canonical Correlation Analysis (MCCA) and discriminative Canonical Correlation Analysis (DCCA) are special cases of DMCCA, thus establishing a unified framework for Canonical Correlation Analysis. We implement a prototype of DMCCA to demonstrate its performance in handwritten digit recognition and human emotion recognition. Extensive experiments show that DMCCA outperforms the traditional methods of serial fusion, CCA, MCCA, and DCCA.

  • BIOSIG - Selecting discriminative features with discriminative multiple Canonical Correlation Analysis for multi-feature information fusion
    2013
    Co-Authors: Lei Gao, Ling Guan
    Abstract:

    In this paper, it presents a novel approach for selecting discriminative features in multimodal information fusion based discriminative multiple Canonical Correlation Analysis (DMCCA), which is the generalized form of Canonical Correlation Analysis (CCA), multiple Canonical Correlation Analysis (MCCA) and discriminative Canonical Correlation Analysis (DCCA). The proposed approach identifies the discriminative features from the multi-feature in Fractional Fourier Transform (FRFT) domain, which are capable of simultaneously maximizing the within-class Correlation and minimizing the between-class Correlation, leading to better utilization of the multi-feature information and producing more effective pattern recognition results. The effectiveness of the introduced solution is demonstrated through extensive experimentation on a visual based emotion recognition problem.

Xiaoqing Ding - One of the best experts on this subject based on the ideXlab platform.

  • Sufficient Canonical Correlation Analysis
    IEEE Transactions on Image Processing, 2016
    Co-Authors: Xiaoqing Ding
    Abstract:

    Canonical Correlation Analysis (CCA) is an effective way to find two appropriate subspaces in which Pearson's Correlation coefficients are maximized between projected random vectors. Due to its well-established theoretical support and relatively efficient computation, CCA is widely used as a joint dimension reduction tool and has been successfully applied to many image processing and computer vision tasks. However, as reported, the traditional CCA suffers from overfitting in many practical cases. In this paper, we propose sufficient CCA (S-CCA) to relieve CCA's overfitting problem, which is inspired by the theory of sufficient dimension reduction. The effectiveness of S-CCA is verified both theoretically and experimentally. Experimental results also demonstrate that our S-CCA outperforms some of CCA's popular extensions during the prediction phase, especially when severe overfitting occurs.

Michel Van De Velden - One of the best experts on this subject based on the ideXlab platform.

  • Generalized Canonical Correlation Analysis with missing values
    Computational Statistics, 2011
    Co-Authors: Michel Van De Velden, Yoshio Takane
    Abstract:

    Generalized Canonical Correlation Analysis is a versatile technique that allows the joint Analysis of several sets of data matrices. The generalized Canonical Correlation Analysis solution can be obtained through an eigenequation and distributional assumptions are not required. When dealing with multiple set data, the situation frequently occurs that some values are missing. In this paper, two new methods for dealing with missing values in generalized Canonical Correlation Analysis are introduced. The first approach, which does not require iterations, is a generalization of the Test Equating method available for principal component Analysis. In the second approach, missing values are imputed in such a way that the generalized Canonical Correlation Analysis objective function does not increase in subsequent steps. Convergence is achieved when the value of the objective function remains constant. By means of a simulation study, we assess the performance of the new methods. We compare the results with those of two available methods; the missing-data passive method, introduced in Gifi’s homogeneity Analysis framework, and the GENCOM algorithm developed by Green and Carroll. An application using world bank data is used to illustrate the proposed methods.

  • Generalized Canonical Correlation Analysis with missing values
    2009
    Co-Authors: Michel Van De Velden, Yoshio Takane
    Abstract:

    Two new methods for dealing with missing values in generalized Canonical Correlation Analysis are introduced. The first approach, which does not require iterations, is a generalization of the Test Equating method available for principal component Analysis. In the second approach, missing values are imputed in such a way that the generalized Canonical Correlation Analysis objective function does not increase in subsequent steps. Convergence is achieved when the value of the objective function remains constant. By means of a simulation study, we assess the performance of the new methods. We compare the results with those of two available methods; the missing-data passive method, introduced Gifi's homogeneity Analysis framework, and the GENCOM algorithm developed by Green and Carroll.