The Projection Approximation Subspace Tracking Algorithm Applied to Whitening and Independent Component Analysis in Wireless Communications

Document type: Researchreports
Full text:
Author(s): Ronnie Landqvist, Abbas Mohammed
Title: The Projection Approximation Subspace Tracking Algorithm Applied to Whitening and Independent Component Analysis in Wireless Communications
Series: Research Report
Year: 2005
Issue: 1
ISSN: 1103-1581
Organization: Blekinge Institute of Technology
Department: School of Engineering - Dept. of Signal Processing (Sektionen för teknik – avd. för signalbehandling)
School of Engineering S- 372 25 Ronneby
+46 455 38 50 00
http://www.tek.bth.se/
Authors e-mail: rla@bth.se, amo@bth.se
Language: English
Abstract: In Blind Source Separation (BSS) the objective is to extract source signals from their linear mixtures. Algorithms developed for Independent Component Analysis (ICA) have proven useful in the field of BSS. The Projection Approximation Subspace Tracking with Deflation (PASTD) algorithm, originally developed for subspace tracking, has been extended by using a nonlinear cost function so that it may be used for ICA/BSS. Such algorithms most often require the input signals to be white. In this report we extend the PASTD algorithm so that it can be used to whiten signals as a pre-processing step before ICA. The performance of the ICA-algorithm is then evaluated for different choices of whitening algorithms. The algorithms are also evaluated for Binary Phase Shift Keying (BPSK) modulated data over Rayleigh fading channels usually encountered in wireless communications.
Subject: Signal Processing\General
Telecommunications\General
Keywords: Blind signal processing, blind source separation, independent component analysis, nonlinear principal component analysis, projection approximation, subspace tracking, recursive least squares, wireless communications, Rayleigh fading channels, whitening, decorrelation.
URN: urn:nbn:se:bth-00301
Edit