Abstract
We consider identifiability and subspace selection for the ICA model with additive Gaussian noise. We discuss a canonical decomposition that allows us to decompose the system into a signal and a noise subspace and show that an unbiased estimate of these can be obtained using a standard ICA algorithm. This can also be used to estimate the relevant subspace dimensions and may often be preferable to PCA dimension reduction. Finally we discuss the identifiability issues for the subsequent ‘square’ noisy ICA model after projection.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Attias, H.: Independent Factor Analysis. Neural Comp. 11, 803–851 (1998)
Bermond, O., Cardoso, J.-F.: Approximate Likelihood for noisy mixtures. In: Proc. ICA 1999 (1999)
Davies, M.E.: Audio Source Separation. In: McWhirter, J., Proudler, I. (eds.) Mathematics in Signal Processing V (2002)
Davies, M.E.: Identifiability Issues in noisy ICA. To appear in IEEE Sig. Proc. Lett. (May 2004)
De Lathauwer, L., De Moor, B., Vandewalle, J.: A technique for higher-order-only blind source separation. In: Proc. ICONIP, Hong Kong (1996)
Cardoso, J.-F.: Blind signal separation: statistical principles. Proceedings of the IEEE 9(10), 2009–2025 (1998)
Comon, P.: Independent Component Analysis: a new concept? Signal Processing 36(3), 287–314 (1994)
Eriksson, J., Koivunen, V.: Identifiability and separability of linear ICA models revisited. In: 4th International Symposium on Independent Component Analysis and Blind Signal Separation (ICA 2003), Nara, Japan (2003)
Hayes, M.H.: Statistical Digital Signal Processing and Modeling. John Wiley & Sons, Chichester (1996)
Hyvarinen, A.: Gaussian Moments for noisy Independent Component Analysis. IEEE Signal Processing Letters 6(6), 145–147 (1999)
Hyvarinen, A., Karhunen, J., Oja, E.: Independent Component Analysis. John Wiley & Sons, inc., Chichester (2001)
ICA mailing list maintained by J-F. Cardoso, at www.tsi.enst.fr/icacentral
Kagan, A.M., Linnik, Y.V., Rao, C.R.: Characterization Problems in Mathematical Statistics. Wiley, New York (1973)
Moulines, E., Cardoso, J.-F., Gassiat, E.: Maximum Likelihood for blind signal separation and deconvolution of noisy signals using mixture models. In: ICASSP 1997 (1997)
Papadias, C.B.: Globally Convergent Blind Source Separation Based on a Mulituser Kurtosis maximization criterion. IEEE Trans. Signal Processing, 48(12) (2000)
Nadal, J.-P., Korutcheva, E., Aires, F.: Blind source processing in the presence of weak sources. Neural Networks 13(6), 589–596 (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Davies, M. (2004). Identifiability, Subspace Selection and Noisy ICA. In: Puntonet, C.G., Prieto, A. (eds) Independent Component Analysis and Blind Signal Separation. ICA 2004. Lecture Notes in Computer Science, vol 3195. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30110-3_20
Download citation
DOI: https://doi.org/10.1007/978-3-540-30110-3_20
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23056-4
Online ISBN: 978-3-540-30110-3
eBook Packages: Springer Book Archive