Abstract
Whereas most blind source separation (BSS) and blind mixture identification (BMI) investigations concern linear mixtures (instantaneous or not), various recent works extended BSS and BMI to nonlinear mixing models. They especially focused on two types of models, namely linear-quadratic ones (including their bilinear and quadratic versions, and some polynomial extensions) and post-nonlinear ones. These works are particularly motivated by the associated application fields, which include remote sensing, processing of scanned images (show-through effect) and design of smart chemical and gas sensor arrays. In this paper, we provide an overview of the above two types of mixing models and of the associated BSS and/or BMI methods and applications.
This work was performed in a project jointly supported by CNRS (France) and FAPESP (Brazil). L.T. Duarte thanks CNPq (Brazil) for funding his research.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abed-Meraim, K., Belouchrani, A., Hua, Y.: Blind identification of a linear-quadratic mixture of independent components based on joint diagonalization procedure. In: Proceedings of ICASSP 1996, Atlanta, GA, 7–10 May 1996, vol. 5, pp. 2718–2721 (1996)
Achard, S., Pham, D.T., Jutten, C.: Quadratic dependence measure for nonlinear blind source separation. In: Proceedings of the Fourth International Workshop on Independent Component Analysis and Blind Signal Separation, ICA 2003 (2003)
Achard, S., Jutten, C.: Identifiability of post-nonlinear mixtures. IEEE Sig. Process. Lett. 12(5), 423–426 (2005)
Achard, S., Pham, D.T., Jutten, C.: Criteria based on mutual information minimization for blind source separation in post nonlinear mixtures. Sig. Process. 85, 965–974 (2005)
Almeida, M.S.C., Almeida, L.B.: Nonlinear separation of show-through image mixtures using a physical model trained with ICA. Sig. Process. 92, 872–884 (2012)
Altmann, Y., Dobigeon, N., Tourneret, J.Y.: Unsupervised post-nonlinear unmixing of hyperspectral images using a Hamiltonian Monte Carlo algorithm. IEEE Trans. Image Process. 23(6), 2663–2675 (2014)
Ando, R.A., Duarte, L.T., Soriano, D.C., Attux, R., Suyama, R., Deville, Y., Jutten, C.: Recurrent source separation structures as iterative methods for solving nonlinear equation systems. In: Proceedings of XXX Simposio Brasileiro de Telecomunicacoes, SBrT 2012, Brasilia, Brazil, 13–16 September 2012
Babaie-Zadeh, M., Jutten, C., Nayebi, K.: A geometric approach for separating post non-linear mixtures. In: Proceedings of the European Signal Processing Conference (EUSIPCO) (2002)
Babaie-Zadeh, M.: On blind source separation in convolutive and nonlinear mixtures. Ph.D. thesis, Institut National Polytechnique de Grenoble (2002)
Bedoya, G.: Non-linear blind signal separation for chemical solid-state sensor arrays. Ph.D. thesis, Universitat Politecnica de Catalunya (2006)
Bermejo, S., Jutten, C., Cabestany, J.: ISFET source separation: foundations and techniques. Sens. Actuators B 113, 222–233 (2006)
Bermejo, S.: A post-non-linear source separation algorithm for bounded magnitude sources and its application to ISFETs. Neurocomputing 148, 477–486 (2015)
Castella, M.: Inversion of polynomial systems and separation of nonlinear mixtures of finite-alphabet sources. IEEE Trans. Sig. Process. 56, 3905–3917 (2008)
Chaouchi, C., Deville, Y., Hosseini, S.: Nonlinear source separation: a quadratic recurrent inversion structure. In: Proceedings of ECMS 2009, Arrasate-Mondragon, Spain, 8–10 July 2009, pp. 91–98 (2009)
Chaouchi, C., Deville, Y., Hosseini, S.: Nonlinear source separation: a maximum likelihood approach for quadratic mixtures. In: Proceedings of MaxEnt 2010, Chamonix, France, 4–9 July 2010
Chaouchi, C., Deville, Y., Hosseini, S.: Cumulant-based estimation of quadratic mixture parameters for blind source separation. In: Proceedings of EUSIPCO 2010, Aalborg, Denmark, 23–27 August 2010, pp. 1826–1830 (2010)
Comon, P., Jutten, C. (eds.): Handbook of Blind Source Separation. Independent Component Analysis and Applications. Academic Press, Oxford (2010)
Deville, Y., Hosseini, S.: Blind identification and separation methods for linear-quadratic mixtures and/or linearly independent non-stationary signals. In: Proceedings of ISSPA 2007, Sharjah, United Arab Emirates, 12–15 February 2007
Deville, Y., Hosseini, S.K.: Stable higher-order recurrent neural network structures for nonlinear blind source separation. In: Davies, M.E., James, C.J., Abdallah, S.A., Plumbley, M.D. (eds.) ICA 2007. LNCS, vol. 4666, pp. 161–168. Springer, Heidelberg (2007). ISSN 0302-9743
Deville, Y., Hosseini, S.: Recurrent networks for separating extractable-target nonlinear mixtures. Part I: non-blind configurations. Sig. Proc. 89, 378–393 (2009)
Deville, Y., Hosseini, S.: Blind operation of a recurrent neural network for linear-quadratic source separation: fixed points, stabilization and adaptation scheme. In: Vigneron, V., Zarzoso, V., Moreau, E., Gribonval, R., Vincent, E. (eds.) LVA/ICA 2010. LNCS, vol. 6365, pp. 237–244. Springer, Heidelberg (2010)
Deville, Y., Hosseini, S., Deville, A.: Effect of indirect dependencies on maximum likelihood and information theoretic blind source separation for nonlinear mixtures. Sig. Process. 91, 793–800 (2011)
Duarte, L.T., Suyama, R., de Faissol Attux, R.R., Von Zuben, F.J., Romano, J.M.T.: Blind source separation of post-nonlinear mixtures using evolutionary computation and order statistics. In: Rosca, J.P., Erdogmus, D., Príncipe, J.C., Haykin, S. (eds.) ICA 2006. LNCS, vol. 3889, pp. 66–73. Springer, Heidelberg (2006)
Duarte, L.T., Jutten, C., Moussaoui, S.: Bayesian source separation of linear-quadratic and linear mixtures through a MCMC method. In: Proceedings of IEEE MLSP, Grenoble, France, 2–4 September 2009
Duarte, L.T., Jutten, C., Moussaoui, S.: A bayesian nonlinear source separation method for smart ion-selective electrode arrays. IEEE Sens. J. 9(12), 1763–1771 (2009)
Duarte, L.T., Suyama, R., Attux, R., Deville, Y., Romano, J.M.T., Jutten, C.: Blind source separation of overdetermined linear-quadratic mixtures. In: Vigneron, V., Zarzoso, V., Moreau, E., Gribonval, R., Vincent, E. (eds.) LVA/ICA 2010. LNCS, vol. 6365, pp. 263–270. Springer, Heidelberg (2010)
Duarte, L.T., Jutten, C., Moussaoui, S.: Bayesian source separation of linear and linear-quadratic mixtures using truncated priors. J. Sig. Process. Syst. 65, 311–323 (2011)
Duarte, L.T., Ando, R.A., Attux, R., Deville, Y., Jutten, C.: Separation of sparse signals in overdetermined linear-quadratic mixtures. In: Theis, F., Cichocki, A., Yeredor, A., Zibulevsky, M. (eds.) LVA/ICA 2012. LNCS, vol. 7191, pp. 239–246. Springer, Heidelberg (2012)
Duarte, L.T., Suyama, R., Attux, R.R.F., Rivet, B., Jutten, C., Romano, J.M.T.: Blind compensation of nonlinear distortions: application to source separation of post-nonlinear mixtures. IEEE Trans. Sig. Process. 60, 5832–5844 (2012)
Duarte, L.T., Suyama, R., Attux, R., Romano, J.M.T., Jutten, C.: A sparsity-based method for blind compensation of a memoryless nonlinear distortion: application to ion-selective electrodes. IEEE Sens. J. 15(4), 2054–2061 (2015)
Duarte, L.T., Pereira, F.O., Attux, R., Suyama, R., Romano, J.M.T.: Source separation in post-nonlinear mixtures by means of monotonic networks. In: Vincent, E. et al. (eds.) LVA/ICA 2015. LNCS, vol. 9237, pp. 176–183. Springer, Heidelberg (2015)
Eches, O., Guillaume, M.: A bilinear-bilinear nonnegative matrix factorization method for hyperspectral unmixing. IEEE Geosci. Remote Sens. Lett. 11, 778–782 (2014)
Georgiev, P.: Blind source separation of bilinearly mixed signals. In: Proceedings of ICA 2001, San Diego, USA, pp. 328–331 (2001)
Halimi, A., Altmann, Y., Dobigeon, N., Tourneret, J.-Y.: Nonlinear unmixing of hyperspectral images using a generalized bilinear model. IEEE Trans. Geosci. Remote Sens. 49, 4153–4162 (2011)
Honkela, A., Valpola, H., Ilin, A., Karhunen, J.: Blind separation of nonlinear mixtures by variational Bayesian learning. Digital Sig. Process. 17(5), 914–934 (2007)
Hosseini, S., Deville, Y.: Blind separation of linear-quadratic mixtures of real sources using a recurrent structure. In: Mira, J., Álvarez, J.R. (eds.) IWANN 2003. LNCS, vol. 2687, pp. 241–248. Springer, Heidelberg (2003)
Hosseini, S., Deville, Y.: Blind maximum likelihood separation of a linear-quadratic mixture. In: Puntonet, C.G., Prieto, A.G. (eds.) ICA 2004. LNCS, vol. 3195, pp. 694–701. Springer, Heidelberg (2004). Erratum: http://arxiv.org/abs/1001.0863
Hosseini, S., Deville, Y.: Recurrent networks for separating extractable-target nonlinear mixtures. Part II: blind configurations. Sig. Process. 93, 671–683 (2013)
Hosseini, S., Deville, Y.: Blind separation of parametric nonlinear mixtures of possibly autocorrelated and non-stationary sources. IEEE Trans. Sig. Process. 62, 6521–6533 (2014)
Jarboui, L., Hosseini, S., Deville, Y., Guidara, R., Ben Hamida, A.: A new unsupervised method for hyperspectral image unmixing using a linear-quadratic model. In: Proceedings of ATSIP 2014, Sousse, Tunisia, 17–19 March 2014, pp. 423–428 (2014)
Koutras, A.: Blind separation of non-linear convolved speech mixtures. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), vol. 1, pp. I-913–I-916 (2002)
Krob, M., Benidir, M.: Blind identification of a linear-quadratic model using higher-order statistics. In: Proceedings of ICASSP 1993, Minneapolis, USA, 27–30 April 1993, pp. 440–443 (1993)
Larue, A., Jutten, C., Hosseini, S.: Markovian source separation in post-nonlinear mixtures. In: Puntonet, C.G., Prieto, A.G. (eds.) ICA 2004. LNCS, vol. 3195, pp. 702–709. Springer, Heidelberg (2004)
Leong, W.Y., Liu, W., Mandic, D.P.: Blind source extraction: standard approaches and extensions to noisy and post-nonlinear mixing. Neurocomputing 71, 2344–2355 (2008)
Liu, Q., Wang, W.: Show-through removal for scanned images using non-linear NMF with adaptive smoothing. In: Proceedings of ChinaSIP, Beijing, pp. 650–654 (2013)
Meganem, I., Déliot, P., Briottet, X., Deville, Y., Hosseini, S.: Physical modelling and non-linear unmixing method for urban hyperspectral images. In: Proceedings of WHISPERS 2011, Lisbon, Portugal, 6–9 June 2011
Meganem, I., Deville, Y., Hosseini, S., Déliot, P., Briottet, X., Duarte, L.T.: Linear-quadratic and polynomial non-negative matrix factorization; application to spectral unmixing. In: Proceedings of EUSIPCO 2011, Barcelona, Spain, 29 August–2 September 2011
Meganem, I., Déliot, P., Briottet, X., Deville, Y., Hosseini, S.: Linear-quadratic mixing model for reflectances in urban environments. IEEE Trans. Geosci. Remote Sens. 52, 544–558 (2014)
Meganem, I., Deville, Y., Hosseini, S., Déliot, P., Briottet, X.: Linear-quadratic blind source separation using NMF to unmix urban hyperspectral images. IEEE Trans. Sig. Process. 62, 1822–1833 (2014)
Merrikh-Bayat, F., Babaie-Zadeh, M., Jutten, C.: Linear-quadratic blind source separating structure for removing show-through in scanned documents. IJDAR 14, 319–333 (2011)
Mokhtari, F., Babaie-Zadeh, M., Jutten, C.: Blind separation of bilinear mixtures using mutual information minimization. In: Proceedings of IEEE MLSP, Grenoble, France, 2–4 September 2009
Nguyen, T.V., Patra, J.C., Emmanuel, S.: gpICA: a novel nonlinear ICA algorithm using geometric linearization. EURASIP J. Adav. Sig. Process. 2007, 1–12 (2007)
Pham, D.T.: Fast algorithms for mutual information based independent component analysis. IEEE Trans. Sig. Process. 52(10), 2690–2700 (2004)
Pham, D.T.: Flexible parametrization of postnonlinear mixtures model in blind sources separation. IEEE Sig. Process. Lett. 11(6), 533–536 (2004)
Puigt, M., Griffin, A., Mouchtaris, A.: Post-nonlinear speech mixture identification using single-source temporal zones and curve clustering. In: Proceedings of the European Signal Processing Conference (EUSIPCO), pp. 1844–1848 (2011)
Rojas, F., Puntonet, C.G., Rodríguez-Álvarez, M., Rojas, I., Martín-Clemente, R.: Blind source separation in post-nonlinear mixtures using competitive learning, simulated annealing, and a genetic algorithm. IEEE Trans. Syst. Man Cybern. Part C: Appl. Rev. 34(4), 407–416 (2004)
Solazzi, M., Uncini, A.: Spline neural networks for blind separation of post-nonlinear-linear mixtures. IEEE Trans. Circuits Syst. I: Regul. Pap. 51(4), 817–829 (2004)
Solé-Casals, J., Jutten, C., Pham, D.T.: Fast approximation of nonlinearities for improving inversion algorithms of PNL mixtures and Wiener systems. Sig. Process. 85, 1780–1786 (2005)
Taleb, A., Jutten, C.: Source separation in post-nonlinear mixtures. IEEE Trans. Sig. Process. 47(10), 2807–2820 (1999)
Theis, F.J., Amari, S.: Postnonlinear overcomplete blind source separation using sparse sources. In: Puntonet, C.G., Prieto, A.G. (eds.) ICA 2004. LNCS, vol. 3195, pp. 718–725. Springer, Heidelberg (2004)
Theis, F.J., Gruber, P.: On model identifiability in analytic postnonlinear ICA. Neurocomputing 64, 223–234 (2005)
Vaerenbergh, S.V., Santamaria, I.: A spectral clustering approach to underdetermined postnonlinear blind source separation of sparse sources. IEEE Trans. Neural Netw. 17(3), 811–814 (2006)
Wei, C., Woo, W., Dlay, S.: Nonlinear underdetermined blind signal separation using bayesian neural network approach. Digital Sig. Process. 17, 50–68 (2007)
White, S.A.: Restoration of nonlinearly distorted audio by histogram equalization. J. Audio Eng. Soc. 30(11), 828–832 (1982)
Zeng, T.-J., Feng, Q.-Y., Yuan, X.-H., Ma, H.-B.: The multi-component signal model and learning algorithm of blind source separation. In: Proceedings of Progress in Electromagnetics Research Symposium, Taipei, 25–28 March 2013, pp. 565–569 (2013)
Zhang, K., Chan, L.W.: Extended gaussianization method for blind separation of post-nonlinear mixtures. Neural Comput. 17, 425–452 (2005)
Ziehe, A., Kawanabe, M., Harmeling, S., Müller, K.R.: Blind separation of post-nonlinear mixtures using gaussianizing transformations and temporal decorrelation. J. Mach. Learn. Res. 4, 1319–1338 (2003)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Deville, Y., Duarte, L.T. (2015). An Overview of Blind Source Separation Methods for Linear-Quadratic and Post-nonlinear Mixtures. In: Vincent, E., Yeredor, A., Koldovský, Z., Tichavský, P. (eds) Latent Variable Analysis and Signal Separation. LVA/ICA 2015. Lecture Notes in Computer Science(), vol 9237. Springer, Cham. https://doi.org/10.1007/978-3-319-22482-4_18
Download citation
DOI: https://doi.org/10.1007/978-3-319-22482-4_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-22481-7
Online ISBN: 978-3-319-22482-4
eBook Packages: Computer ScienceComputer Science (R0)