A fundamental problem in neural network research, as well as in many other disciplines, is finding a suitable representation of multivariate data, i.e. random vectors. For reasons of computational and conceptual simplicity, the representation is often sought as a linear transformation of the original data. In other words, each component of the representation is a linear combination of the origi...

Indexing terms: Adaptive signal processing, independent component analysis, adaptive noise cancelling A method for adaptive noise cancelling based on independent component analysis (ICA) is presented. Although conventional least-mean-squares (LMS) algorithm removes noise components based on second-order correlation, the proposed algorithm can utilize higher-order statistics. Experimental result...

This discussion presents a new perspective of subspace independent component analysis (ICA). The notion of a function of cumulants (kurtosis) is generalized to vector kurtosis. This vector kurtosis is utilized in the subspace ICA algorithm to estimate subspace independent components. One of the main advantages of the presented approach is its computational simplicity. The experiments have shown...

Abstract—What matrix factorization methods do is reduce the dimensionality of data without losing any important information. In this work, we present Non-negative Matrix Factorization (NMF) method, focusing on its advantages concerning other factorization. We discuss main optimization algorithms, used to solve NMF problem, and their convergence. The paper also contains a comparative study betwe...

This talk is an introduction to Independent Component Analysis (ICA) and Parallel Factor Analysis (PARAFAC), the way they are related and their links with Principal Component Analysis (PCA). PCA is now a standard technique for the analysis of two-way multivariate data, i.e., data available in matrix format. However, principal components are subject to rotational in-variance. By imposing statist...

In this work, an attempt has been made to analyze human femur radiographic bone images using sharpness features and learning models. The sharpness features are derived for the neck of the femur bone images to characterize the trabecular structure. The significant parameters are found using Independent component analysis (ICA) and Principal Component Analysis (PCA). The first three most signific...

A fundamental problem in neural network research, as well as in many other disciplines, is finding a suitable representation of multivariate data, i.e. random vectors. For reasons of computational and conceptual simplicity, the representation is often sought as a linear transformation of the original data. In other words, each component of the representation is a linear combination of the origi...

Matrix factorizations and their extensions to tensor factorizations and decompositions have become prominent techniques for linear and multilinear blind source separation (BSS), especially multiway Independent Component Analysis (ICA), Nonnegative Matrix and Tensor Factorization (NMF/NTF), Smooth Component Analysis (SmoCA) and Sparse Component Analysis (SCA). Moreover, tensor decompositions hav...

Dynamic contrast-enhanced (DCE) imaging is widely used for in vivo assessment of the cerebral blood perfusion. In this work, we investigate the use of independent component analysis (ICA) on DCE imaging data for assessment of cerebral blood perfusion, without any prior knowledge of the underlying tissue vasculature and arterial input function. The minimum description length (MDL) criterion and ...

Independent component analysis (ICA) is a new effective technique for separation of statistically independent sources existing simultaneously in observations. Generally, ICA requires that the number of sensors should be no less than the number of independent sources to ensure enough information for separation of all sources. In some practical applications, this requirement of ICA is not met and...