- Independent component analysis
Independent component analysis (ICA) is a computational method for separating a
multivariatesignal into additive subcomponents supposing the mutual statistical independenceof the non-Gaussian source signals. It is a special case of blind source separation.
When the independence assumption is correct, blind ICA separation of a mixed signal gives very good results. It is also used for signals that are not supposed to be generated by a mixing for analysis purposes. A simple application of ICA is the “
cocktail party problem”, where the underlying speech signals are separated from a sample data consisting of people talking simultaneously in a room. Usually the problem is simplified by assuming no time delays and echoes. An important note to consider is that if "N" sources are present, at least "N" observations (i.e., microphones) are needed to get the original signals. This constitutes the square ("J" = "D", where "D" is the input dimension of the data and "J" is the dimension of the model). Other cases of underdetermined ("J" < "D") and overdetermined ("J" > "D") have been investigated.
The statistical method finds the independent components (aka factors, latent variables or sources) by maximizing the statistical independence of the estimated components. Non-Gaussianity, motivated by the
central limit theorem, is one method for measuring the independence of the components. Non-Gaussianity can be measured, for instance, by kurtosisor approximations of negentropy. Mutual informationis another popular criterion for measuring statistical independence of signals.
Typical algorithms for ICA use
centering, whitening (usually with the eigenvalue decomposition), and dimensionality reductionas preprocessing steps in order to simplify and reduce the complexity of the problem for the actual iterative algorithm. Whitening and dimension reductioncan be achieved with principal component analysisor singular value decomposition. Whitening ensures that all dimensions are treated equally "a priori" before the algorithm is run. Algorithms for ICA include infomax, FastICA, and JADE, but there are many others also.
Most ICA methods are not able to extract the actual number of source signals, the order of the source signals, nor the signs or the scales of the sources.
ICA is important to
blind signal separationand has many practical applications. It is closely related to (or even a special case of) the search for a factorial codeof the data, i.e., a new vector-valued representation of each data vector such that it gets uniquely encoded by the resulting code vector (loss-free coding), but the code components are statistically independent.
Linear independent component analysis can be divided into noiseless and noisy cases,where noiseless ICA is a special case of noisy ICA. Nonlinear ICA should be considered as a separate case.
The data is represented by the
random vectorand the components as the random vector . The task is to transform the observed data , using a linear static transformation "W" as:,into maximally independent components measured by some function of independence.
Linear noiseless ICA
The components of the observed random vector are generated as a sum of the independent components , :
weighted by the mixing weights .
The same generative model can be written in vectorial form as ,where the observed random vector is represented by the basis vectors .The basis vectors form the columns of the mixing matrix and the generative formula can be writtenas , where .
Given the model and realizations (samples) of the random vector , the task is to estimate both the mixing matrix and the sources . This is done by adaptively calculating the vectors and setting up a cost function which either maximizes the nongaussianity of the calculated or minimizes the mutual information. In some cases, a priori knowledge of the probability distributions of the sources can be used in the cost function.
The original sources can be recovered by multiplying the observed signals with the inverse of the mixing matrix , also known as the unmixing matrix. Here it is assumed that the mixing matrix is square (). If the number of basis vectors is greater than the dimensionality of the observed vectors,
Wikimedia Foundation. 2010.
Look at other dictionaries:
Independent Component Analysis — (ICA) löst das Blind Source Separation Problem (BSS), indem angenommen wird, dass die Quellen einer Datenmischung statistisch unabhängig sind. Inhaltsverzeichnis 1 Problemstellung 2 Vorgehensweise 2.1 Normierung der Varianz 2.2 Bestimmung der… … Deutsch Wikipedia
Component analysis — may refer to: Principal component analysis Kernel principal component analysis Independent component analysis Neighbourhood components analysis ANOVA simultaneous component analysis Connected Component Analysis This disambiguation pag … Wikipedia
Principal component analysis — PCA of a multivariate Gaussian distribution centered at (1,3) with a standard deviation of 3 in roughly the (0.878, 0.478) direction and of 1 in the orthogonal direction. The vectors shown are the eigenvectors of the covariance matrix scaled by… … Wikipedia
Analysis — (from Greek ἀνάλυσις , a breaking up ) is the process of breaking a complex topic or substance into smaller parts to gain a better understanding of it. The technique has been applied in the study of mathematics and logic since before Aristotle,… … Wikipedia
Analysis of variance — In statistics, analysis of variance (ANOVA) is a collection of statistical models, and their associated procedures, in which the observed variance in a particular variable is partitioned into components attributable to different sources of… … Wikipedia
Component-based software engineering — A simple example of two components expressed in UML 2.0. The checkout component, responsible for facilitating the customer s order, requires the card processing component to charge the customer s credit/debit card (functionality that the latter… … Wikipedia
Component-based usability testing — (CBUT) is a testing approach which aims at empirically testing the usability of an interaction component. The latter is defined as an elementary unit of an interactive system, on which behaviour based evaluation is possible. For this, a component … Wikipedia
analysis — /euh nal euh sis/, n., pl. analyses / seez /. 1. the separating of any material or abstract entity into its constituent elements (opposed to synthesis). 2. this process as a method of studying the nature of something or of determining its… … Universalium
Analysis — A psychology term for processes used to gain understanding of complex emotional or behavioral issues. * * * 1. The breaking up of a chemical compound or mixture into simpler elements; a process by which the composition of a substance is… … Medical dictionary
Factor analysis — is a statistical method used to describe variability among observed, correlated variables in terms of a potentially lower number of unobserved, uncorrelated variables called factors. In other words, it is possible, for example, that variations in … Wikipedia