Independent Component Analysis

---

Lars Kai Hansen
Department of Mathematical Modelling
Technical University of Denmark B321
DK-2800 Lyngby, DENMARK
email: lkhansen@imm.dtu.dk
http://www.imm.dtu.dk/~lkh

Independent Component Analysis (ICA) is a new signal processing research field

for unsupervised learning of independent effects in multivariate signals.

There are a number of comprehensive Web presentations of ICA research

(See eg.: Terry Sejnowskis / Te-Won Lee's page)

I first became interested in ICA in the mid-90’s and my first work was done

during a San Diego visit (Oct 97 - Mar 98) after discussions with the Sejnowski group.
The ISP-group’s ICA research concerns methods and applications in neuroimaging,

and in text-analysis. We offer two Matlab toolboxes

· ‘lyngby’ for neuroimaging (with ICA based on dynamic decorrelation)

· DTU:Toolbox (Infomax, dynamic decorrelation, ‘mean field ICA’, demo scripts)

ICA Publications

(Note: You can access many of the pdf/ps files

through the publication pages or via citeseer):

Journals

F. Calamante, M. Mørup, L. K. Hansen:

Defining a Local Arterial Input Function for Perfusion MRI

Using Independent Component Analysis.

Accepted Magnetic Resonance in Medicine (2004).

M. McKeown, L.K. Hansen, and T.J. Sejnowski:

Independent Component Analysis for fMRI: What is Signal and What is Noise?

Current Opinion in Neurobiology 13(5): 620-629 (2003).

Pedro A.d.F.R. Højen-Sørensen, Ole Winther and Lars Kai Hansen
Mean Field Approaches to Independent Component Analysis
Neural Computation 14:889-918 (2002).

P.A.d.F.R. Højen-Sørensen, O. Winther and L. K. Hansen
Analysis of Functional Neuroimages Using ICA Adaptive Binary Sources
Neurocomputing 49: 213-225 (2002).

N. Lange, S.C. Strother, J.R. Anderson, F.Å. Nielsen, A.P. Holmes, T. Kolenda, R. Savoy, L.K. Hansen:

Plurality and Resemblance in fMRI Data Analysis.

NeuroImage, 10(3): 282-303 (1999)

Bookchapters

L.K. Hansen, J. Larsen and T. Kolenda
On Independent Component Analysis for Multimedia Signals
in L. Guan, S.Y. Kung and J. Larsen (eds.) Multimedia Image and Video Processing, CRC Press, Ch. 7, pp. 175-199, 2000.

T. Kolenda, L. K. Hansen, S. Sigurdsson
Independent Components in Text
M. Girolami (ed.) Advances in Independent Component Analysis, Springer-Verlag, 2000.

Conferences

Olsson R. K., Hansen L. K.,

A harmonic excitation state-space approach to blind separation of speech.

Advances in Neural Information Processing Systems 2004. [pdf]

Olsson R. K., Hansen L. K.,

Probabilistic blind deconvolution of non-stationary sources.

European signal processing conference 2004 [pdf]

Olsson R. K., Hansen L. K.,

Estimating the number of sources in a noisy convolutive mixture using BIC.

International conference on independent component analysis 2004 [pdf]

Dyrholm, M., Hansen, L. K., Wang, L., Arendt-Nielsen, L., Chen, A. C.,

Convolutive ICA (c-ICA) captures complex spatio-temporal EEG activity,

10th annual meeting of the organization for human brain mapping, 2004 (abstract) [pdf]

Dyrholm, M., Hansen, L. K.,

CICAAR: Convolutive ICA with an Auto-Regressive Inverse Model,

To appear at the 5th International Conference on Independent Component Analysis

and Blind Signal Separation, Granada, Spain 2004 [pdf]

Michael Syskind Pedersen, Lars Kai Hansen, Ulrik Kjems and Karsten Bo Rasmussen,

Semi-blind Source Separation Using Head-Related Transfer Functions,

ICASSP2004, vol. V, pp. 713-716, 2004 [pdf]

V. D. Calhourn, T. Adali, L.K. Hansen, J. Larsen and J.J. Pekar:

ICA of Functional MRI Data: An Overview,

Fourth International Symposium on Independent Component Analysis and

Blind Source Separation, Nara, Japan, April 1-4, pp. 281-288, 2003 [pdf]

J. Larsen, L.K. Hansen, T. Kolenda and F.A. Nielsen:

Independent Component Analysis in Multimedia Modeling,

Fourth International Symposium on Independent Component Analysis and

Blind Source Separation, Nara, Japan, April 1-4, pp. 687-696, 2003. [pdf]

Hansen, L. K., Dyrholm, M.,

A prediction matrix approach to convolutive ICA,

Proceedings of IEEE Workshop on Neural Networks for Signal Processing

XIII Toulouse, France, Sept. 17-19, 2003, pp. 249-258, 2003 [pdf]

Lars Kai Hansen and Kaare Brandt Petersen,

Monaural separetion of White Noise Mixtures is Hard,

Conference Proceedings of ICA2003, Nara, Japan.

T. Kolenda, L.K. Hansen, J. Larsen and O. Winther
Independent Component Analysis for Understanding Multimedia Content
in H. Bourlard, T. Adali, S. Bengio, J. Larsen, and S. Douglas (eds.)

Proceedings of IEEE Workshop on Neural Networks for Signal Processing XII

Matigny, Valais, Switzerland, Sept. 4-6, 2002, pp. 757-766.

P.A.d.F.R. Højen-Sørensen, L. K. Hansen and O. Winther
Mean Field Implementation of Bayesian ICA

In proceedings of 3rd International Conference on Independent Component

Analysis and Blind Signal Separation (ICA2001), Institute of Neural Computation (2001).

T. Kolenda, L.K. Hansen and J. Larsen
Signal Detection using ICA: Application to Chat Room Topic Spotting
in proceedings of ICA'2001, San Diego, USA, December 9-13, 2001, pp. 540-545.

L.K. Hansen, J. Larsen, T. Kolenda
Blind Detection of Independent Dynamic Components
in Proceddings IEEE ICASSP'2001, Salt Lake City, Utah, USA, vol. 5, pp. 3197--3200, 2001.

L.K. Hansen, S. Sigurdsson, T. Kolenda, F.Å. Nielsen, U. Kjems and J. Larsen
Modeling Text with Generalizable Gaussian Mixtures
in proceedings of IEEE ICASSP'2000, Istanbul, Turkey, June 5-9, 2000, vol. VI, pp. 3494-3497.

K.S. Petersen, L.K. Hansen, T. Kolenda, and E. Rostrup

On the independent components of functional neuroimages

in proceedings of ICA'2000, Helsinki, Finland pp. 615-620.

L.K. Hansen & J. Larsen
Source Separation in Short Image Sequences using Delayed Correlation
in Proceedings of NORSIG'98, Vigsø, Denmark, pp. 253-256,

ISBN-87-985750-8-2, June 1998.