Geodesic
Fast and accurate methods of independent component analysis: A survey
Kybernetika, Tome 47 (2011) no. 3, pp. 426-438 Cet article a éte moissonné depuis la source Czech Digital Mathematics Library

Voir la notice de l'article

This paper presents a survey of recent successful algorithms for blind separation of determined instantaneous linear mixtures of independent sources such as natural speech or biomedical signals. These algorithms rely either on non-Gaussianity, nonstationarity, spectral diversity, or on a combination of them. Performance of the algorithms will be demonstrated on separation of a linear instantaneous mixture of audio signals (music, speech) and on artifact removal in electroencephalogram (EEG).
This paper presents a survey of recent successful algorithms for blind separation of determined instantaneous linear mixtures of independent sources such as natural speech or biomedical signals. These algorithms rely either on non-Gaussianity, nonstationarity, spectral diversity, or on a combination of them. Performance of the algorithms will be demonstrated on separation of a linear instantaneous mixture of audio signals (music, speech) and on artifact removal in electroencephalogram (EEG).
Classification : 92-02, 92-04, 92-08, 94A12
Keywords: Blind source separation; probability distribution; score function; autoregressive random processes; audio signal processing; electroencephalogram; artifact rejection 
@article{KYB_2011_47_3_a7,
     author = {Tichavsk\'y, Petr and Koldovsk\'y, Zbyn\v{e}k},
     title = {Fast and accurate methods of independent component analysis: {A} survey},
     journal = {Kybernetika},
     pages = {426--438},
     year = {2011},
     volume = {47},
     number = {3},
     language = {en},
     url = {http://geodesic.mathdoc.fr/item/KYB_2011_47_3_a7/}
}
TY  - JOUR
AU  - Tichavský, Petr
AU  - Koldovský, Zbyněk
TI  - Fast and accurate methods of independent component analysis: A survey
JO  - Kybernetika
PY  - 2011
SP  - 426
EP  - 438
VL  - 47
IS  - 3
UR  - http://geodesic.mathdoc.fr/item/KYB_2011_47_3_a7/
LA  - en
ID  - KYB_2011_47_3_a7
ER  - 
%0 Journal Article
%A Tichavský, Petr
%A Koldovský, Zbyněk
%T Fast and accurate methods of independent component analysis: A survey
%J Kybernetika
%D 2011
%P 426-438
%V 47
%N 3
%U http://geodesic.mathdoc.fr/item/KYB_2011_47_3_a7/
%G en
%F KYB_2011_47_3_a7
Tichavský, Petr; Koldovský, Zbyněk. Fast and accurate methods of independent component analysis: A survey. Kybernetika, Tome 47 (2011) no. 3, pp. 426-438. http://geodesic.mathdoc.fr/item/KYB_2011_47_3_a7/

[1] Belouchrani, A., Abed-Meraim, K., Cardoso, J.-F., Moulines, E.: A blind source separation technique using second-order statistics. IEEE Trans. Signal Processing 45 (1997), 434–444. | DOI

[2] Boscolo, R., Pan, H., Roychowdhury, V. P.: Independent component analysis based on nonparametric density estimation. IEEE Trans. Neural Networks 15 (2004), 55–65. | DOI

[3] Cardoso, J.-F.: Blind signal separation: statistical principles. Proc. IEEE 90 (1998), 2009–2026.

[4] Cardoso, J.-F., Pham, D. T.: Separation of non stationary sources. Algorithms and performance., In: Independent Components Analysis: Principles and Practice (S. J. Roberts and R. M. Everson, eds.), Cambridge University Press 2001, pp. 158–180.

[5] Chambers, J., Cleveland, W., Kleiner, B., Tukey, P.: Graphical Methods for Data Analysis. Wadsworth, 1983. | Zbl

[6] Cruces, S., Cichocki, A., Lathauwer, L. De: Thin QR and SVD factorizations for simultaneous blind signal extraction. In: Proc. European Signal Processing Conference (EUSIPCO), Vienna 2004, pp. 217–220.

[7] Dégerine, S., Zaïdi, A.: Separation of an instantaneous mixture of Gaussian autoregressive sources by the exact maximum likelihood approach. IEEE Trans. Signal Processing 52 (2004), 1492–1512. | DOI | MR

[8] Delorme, A., Sejnowski, T., Makeig, S.: Enhanced detection of artifacts in EEG data using higher-order statistics and independent component analysis. Neuroimage 34 (2007) 1443–1449. | DOI

[9] Hyvärinen, A., Oja, E.: A fast fixed-point algorithm for independent component analysis. Neural Computation 9 (1997), 1483–1492. | DOI

[10] Hyvärinen, A., Karhunen, J., Oja, E.: Independent Component Analysis. John Wiley & Sons, 2001.

[11] James, C. J., Hesse, C. W.: Independent component analysis for biomedical signals. Physiol. Meas. 26 (2005), R15–R39. | DOI

[12] Koldovský, Z., Tichavský, P., Oja, E.: Efficient variant of algorithm FastICA for independent component analysis attaining the Cramér–Rao lower bound. IEEE Trans. Neural Networks 17 (2006), 1265–1277. | DOI

[13] Koldovský, Z., Málek, J., Tichavský, P., Deville, Y., Hosseini, S.: Blind separation of piecewise stationary nonGaussian Sources. Signal Process. 89 (2009), 2570–2584.

[14] Koldovský, Z., Tichavský, P.: A comparison of independent component and independent subspace analysis algorithms. In: Proc. European Signal Processing Conference (EUSIPCO), Glasgow 2009, pp. 1447–1451.

[15] Koldovský, Z., Tichavský, P.: Time-domain blind separation of audio sources based on a complete ICA decomposition of an observation space. IEEE Trans. Audio, Speech and Language Processing 19 (2011), 406–416. | DOI

[16] Learned-Miller, E. G., III, J. W. Fisher: ICA using spacings estimates of entropy. J. Machine Learning Research 4 (2004), 1271–1295. | MR

[17] Lee, Te-Won: Independent Component Analysis, Theory and Applications. Kluwer Academic Publishers, 1998. | Zbl

[18] Pham, D. T., Garat, P.: Blind separation of mixture of independent sources through a quasi-maximum likelihood approach, IEEE Trans. Signal Process. 45 (1997), 1712–1725. | DOI

[19] Pham, D.-T.: Joint approximate diagonalization of positive definite Hermitian matrices. SIAM J. Matrix Anal. Appl. 22 (2001), 1136–1152. | DOI | MR | Zbl

[20] Pham, D.-T.: Blind separation of instantaneous mixture of sources via the Gaussian mutual information criterion. Signal Process. 81 (2001), 855–870. | DOI | Zbl

[21] Pham, D.-T., Cardoso, J.-F.: Blind separation of instantaneous mixtures of nonstationary sources. IEEE Trans. Signal Process. 49 (2001), 1837–1848. | DOI | MR

[22] Tichavský, P., Koldovský, Z., Oja, E.: Performance analysis of the FastICA algorithm and Cramér-Rao bounds for linear independent component analysis. IEEE Trans. Signal Process. 54 (2006), 1189–1203. | DOI

[23] Tichavský, P., Koldovský, Z., Oja, E.: Corrections to “Performance analysis of the FastICA algorithm and Cramér–Rao Bounds for linear independent component analysis, TSP 04/06". IEEE Tran. Signal Process. 56 (2008), 1715–1716. | DOI | MR

[24] Tichavský, P., Koldovský, Z., Oja, E.: Speed and accuracy enhancement of linear ICA techniques using rational nonlinear functions. Lecture Notes in Comput. Sci. 4666 (2007), 285–292. | Zbl

[25] Tichavský, P., Koldovský, Z., Yeredor, A., Gomez-Herrero, G., Doron, E.: A hybrid technique for blind non-Gaussian and time-correlated sources using a multicomponent approach. IEEE Trans. Neural Networks 19 (2008), 421–430. | DOI

[26] Tichavský, P., Yeredor, A.: Fast approximate joint diagonalization incorporating weight matrices. IEEE Trans. Signal Process. 57 (2009), 878–891. | DOI | MR