Independent Component Analysis: Algorithms, Applications and Extensions

one day discussion meeting

            

Supported by the IEE, NCAF and

20th December 2002

Department of Electronic Engineering
Queen Mary, University of London
London, E1 4NS UK

Overview

Independent Component Analysis (ICA) has been one of the recent emerging fields of research from the areas of nonGaussian Signal Processing, Neural Networks and probabilistic modelling. It has been heralded by some as the new Principal Component Analysis (PCA). However, in stark contrast to traditional 2nd order methods, it has been able to effectively solve the Blind Signal Separation Problem (BSS).

The purpose of this one day discussion meeting was to bring together practitioners from the various different disciplines that are researching ICA and to explore the future directions of this field. The programme comprised a series of seminars on aspects of ICA, its generalisations and emerging applications. The day concluded with a discussion on future research directions.

Around 60 people attended the event from diverse research fields including: signal processing, image processing, audio technology, telecommunications, statistics, neural networks, neurology, medicine and chemistry. Participants were from various UK and European research institutions as well as a sizeable representation from industry.


Abstracts and PDF versions of the presentations are provided by following the links in the programme of talks listed below.


Programme

09:30

Registration and coffee: foyer of Peoples Palace

Chairman

Mike Davies

ICA Theory & Generalizations

10:00

Non-negative ICA

Mark Plumbley, QMUL [pdf]

 

10:30

Extensions of Hebbian Learning which perform ICA

Colin Fyfe, Paisley University [pdf]

 

11:00

Coffee: foyer of Peoples Palace

11:30

Blind Source Separation with convolutive mixtures,

Paul Baxter, John McWhirter, Qinetiq [pdf]

 

12.00

The Generative Topographic Mapping for Nonlinear ICA

Richard Everson, Exeter University [pdf]

 

12:30

Lunch: foyer of Peoples Palace

Chairman

Mark Plumbley

Applications

14:00

Has the permutation problem in Transform Domain BSS been solved?

Wenwu Wang, Jonathon Chambers, Kings College London [pdf]

 

14.30

Audio Source Separation: Solutions & Problems

Mike Davies, QMUL [pdf]

 

15:00

Tea: Foyer of Peoples Palace

15:30

Application of BSS to Space Time Coded Wireless Communications

Darren Ward, Imperial College London [pdf]

 

16:00

Application of BSS to blind identification and equalization of digital communication channels

Vicente Zarzoso, Liverpool University [pdf]

 

16:30

Discussion: "Future Directions for ICA"

17:00

Close


Mark Plumbley Paul Baxter
Mark Plumbley, QMUL
Paul Baxter, Qinetiq
Richard Everson Colin Fyfe
Richard Everson, Exeter University
Colin Fyfe, Paisley University
Mike Davies
Mike Davies, QMUL