What is Independent Component Analysis?

Abstract

This article describes a relatively new research topic called independent component analysis (ICA), which is becoming very popular in the signal processing literature and amongst those working in machine learning and data mining. The primary focus of ICA is to resolve the classical problem of blind source separation (BSS), in which an unknown mixture of nonGaussian signals is decomposed into its independent component signals. The classical example of BSS is the so-called cocktail-party problem, where the mixture consists of simultaneous speech signals recorded by a number of microphones. Important applications include biomedical signal processing (usually brain wave activity in the form of EEG and MEG tracings), audio signal separation (mixed speech and music signals), telecommunications (a confusion of signals transmitted by multiple users of mobile phones), financial time series (portfolios of stocks), and data mining (text document analysis). The ICA methodology has much in common with that of projection pursuit (PP).

Multichannel Source Separation Using Time-Deconvolutive CNMF

“…This is inspired by a LASSO [19] regression, aiming to enforce the selectivity of signatures B k and, consequently, produce a sparser representation, suitable to pitched audio signals. 3 We extract a factor 2 from α B for convenience.…”

“…Blind source separation (BSS) is an extensively researched topic with a wide variety of applications [2]. A celebrated example is the use of independent component analysis (ICA) [3,4,5] to separate muscular activity interference from brain activity in encephalographic scans [6]. Another interesting example is the use of BSS in speech enhancement for hearing aid devices [7].…”

Classification in hyperspectral images by independent component analysis, segmented cross-validation and uncertainty estimates

“…The ICA algorithm used was the so-called joint approximate diagonalisation of eigenmatrices (JADE). 34 The critical limits based on the Hotelling's T 2 statistics were applied for the classification of all pixels in the mosaic image of four types of plastics. 10…”