Abstract
The linear mixing model has been considered previously in most of the researches which are devoted to the blind source separation (BSS) problem. In practice, a more realistic BSS mixing model should be the non-linear one. In this paper, we propose a non-linear BSS method, in which a two-layer perceptron network is employed as the separating system to separate sources from observed non-linear mixture signals. The learning rules for the parameters of the separating system are derived based on the minimum mutual information criterion with conjugate gradient algorithm. Instead of choosing a proper non-linear functions empirically, the adaptive kernel density estimation is used in order to estimate the probability density functions and their derivatives of the separated signals. As a result, the score function of the perceptron’s outputs can be estimated directly. Simulations show good performance of the proposed non-linear BSS algorithm.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
S. Achard, D. Pham, C. Jutten, Blind source separation in post nonlinear mixtures, in: Proceedings of ICA 2001, San Diego, 259–300, (2001)
E. Alan, T. Arias, S. Smith, The geometry of algorithms with orthogonality constraints. SIAM J. Matrix Anal. Appl. 20(2), 303–353 (1998)
L.B. Almeida, MISEP-linear and nonlinear ICA based on mutual information. J. Mach. Learn. Res. 4, 1297–1318 (2003)
L.B. Almeida, Linear and nonlinear ICA based on mutual information-the MISEP method. Signal Process. 84(2), 231–245 (2004)
S. Amari, Natural gradient works efficiently in learning. Neural Comput. 10, 251–276 (1998)
S. Choi, A. Cichocki, H.M. Park, S.Y. Lee, Blind source separation and independent component analysis: A review. Neural Inf. Process. 6(1), 1–57 (2005)
Cichocki A, Amari S, Siwek K, Tanaka T, et al., ICALAB toolboxes, http://www.bsp.brain.riken.jp/ICALAB
Y. Guo, S. Huang, Y. Li, Edge effect elimination in single-mixture blind source separation. Circuits Systems Signal Process. 32(5), 2317–2334 (2013)
A. Honkela, H. Valpola, A. Ilin, J. Karhunen, Blind separation of nonlinear mixtures by variational Bayesian learning. Digit. Signal Process. 17(5), 914–934 (2007)
S. Hosseini, Y. Deville, Recurrent networks for separating extractable-target nonlinear mixtures. Part II. Blind configurations. Signal Processing 93(4), 671–683 (2013)
A. Hyvärinen, J. Karhunen, E. Oja, Independent Component Analysis (John Wiley, New York, 2001)
A. Hyvärinen, P. Pajunen, Nonlinear independent component analysis: existence and uniqueness results. Neural Netw. 12(3), 429–439 (1999)
P. Jia, H.Y. Zhang, X.Z. Shi, Blind source separation based on nonparametric density estimation. Circuits Sys. Signal Process. 22(1), 57–67 (2003)
L.D. Lathauwer, J. Castaing, Tensor-based techniques for the blind separation of DS-CDMA signals. Signal Process. 87(2), 322–336 (2007)
J.K. Lin, D.G. Grier, J.D. Cowan, Source separation and density estimation by faithful equivariant SOM, Advances in Neural Information Processing Systems, vol. 9 (MIT Press, Cambridge, 1997), pp. 536–542
F. Maazouzi, B. Halima, Type-2 Fuzzy Gaussian mixture models for singing voice classification in commercial music production. Int. J. Signal Imaging Syst. Eng. 6(2), 111–118 (2013)
W. Naanaa, J.M. Nuzillard, A geometric approach to blind separation of nonnegative and dependent source signals. Signal Process. 92(11), 2775–2784 (2012)
P. Pajunen, A. Hyvarinen, J. Karhunen, Nonlinear blind source separation by self-organizing maps, in: Proceedings of ICONIP’96, 2, 1207–1210, (1996)
S. Sun, C. Peng, W. Hou, J. Zheng, Y. Jiang, X. Zheng, Blind source separation with time series variational Bayes expectation maximization algorithm. Digit. Signal Process. 22(1), 17–33 (2012)
Y. Sun, C. Ridge, F. del Rio, A.J. Shaka, J. Xin, Postprocessing and sparse blind source separation of positive and partially overlapped data. Signal Process. 91(8), 1838–1851 (2011)
A. Taleb, C. Jutten, S. Olympieff, Source separation in post nonlinear mixtures: an entropy-based algorithm, in: Proceedings of ESANN’98, 2089–2092, (1998)
A. Taleb, C. Jutten, Source separation in post-nonlinear mixtures. IEEE Trans. Signal Process. 47(10), 2807–2820 (1999)
Y. Tan, J. Wang, J. Zurada, Nonlinear blind source separation using a radial basis function network. IEEE Trans. Neural Netw. 12, 124–134 (2001)
F. Wang, H. Li, R. Li, Harmonic signals retrieval approach based on blind source separation. Circuits Sys. Signal Process. 29(4), 669–685 (2010)
H.H. Yang, S. Amari, Adaptive on-line learning algorithms for blind separation: maximum entropy and minimum mutual information. Neural Comput. 9(7), 1457–1482 (1997)
L. Zhang, A. Cichocki, S. Amari, Self-adaptive blind source separation based an activation function adaptation. IEEE Transac. Neural Netw. 15(2), 233–244 (2004)
Acknowledgments
This work was supported by the National Natural Science Foundation of China (61273070), Doctor Candidate Foundation of Jiangnan University (1252050205135130), and a Project Funded by the Priority Academic Program Development (PAPD) of Jiangsu Higher Education Institutions.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Li, W., Yang, H. A Non-Linear Blind Source Separation Method Based on Perceptron Structure and Conjugate Gradient Algorithm. Circuits Syst Signal Process 33, 3573–3590 (2014). https://doi.org/10.1007/s00034-014-9818-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00034-014-9818-1