×

Joint blind source separation by generalized joint diagonalization of cumulant matrices. (English) Zbl 1219.94037

Summary: We show that the joint blind source separation (JBSS) problem can be solved by jointly diagonalizing cumulant matrices of any order higher than one, including the correlation matrices and the fourth-order cumulant matrices. We introduce an efficient iterative generalized joint diagonalization algorithm such that a series of orthogonal procrustes problems are solved. We present simulation results to show that the new algorithms can reliably solve the permutation ambiguity in JBSS and that they offer superior performance compared with existing multiset canonical correlation analysis (MCCA) and independent vector analysis (IVA) approaches. Experiment on real-world data for separation of fetal heartbeat in electrocardiogram (ECG) data demonstrates a new application of JBSS, and the success of the new algorithms for a real-world problem.

MSC:

94A12 Signal theory (characterization, reconstruction, filtering, etc.)

Software:

Daisy; FastICA
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Li, Y. O.; Adalı, T.; Wang, W.; Calhoun, V. D.: Joint blind source separation by multiset canonical correlation analysis, IEEE trans. Signal process. 57, No. 10, 3918-3929 (2009) · Zbl 1391.94299
[2] Correa, N. M.; Adali, T.; Li, Y. O.; Calhoun, V. D.: Canonical correlation analysis for data fusion and group inferences, IEEE signal process. Mag. 27, No. 4, 39-50 (2010)
[3] Nielsen, A. A.: Multiset canonical correlation analysis and multispectral, truly multitemporal remote sensing data, IEEE trans. Image process. 11, No. 3, 293-305 (2002)
[4] Rustandi, I.; Just, M. A.; Mitchell, T. M.: Integrating multiple-study multiple-subject fMRI datasets using canonical correlation analysis, (2009)
[5] Kim, T.; Lee, I.; Lee, T. W.: Independent vector analysis: definition and algorithms, , 1393-1396 (2006)
[6] Kim, T.; Attias, H. T.; Lee, S. Y.; Lee, T. W.: Blind source separation exploiting higher-order frequency dependencies, IEEE trans. Speech audio process. 15, No. 1, 70-79 (2007)
[7] Lee, I.; Kim, T.; Lee, T. W.: Independent vector analysis for convolutive blind speech separation, Blind speech separation (2007) · Zbl 1186.94196
[8] Lee, J. H.; Lee, T. W.; Jolesz, F. A.; Yoo, S. S.: Independent vector analysis (IVA): multivariate approach for fMRI group study, Neuroimage 40, No. 1, 86-109 (2008)
[9] Anderson, M.; Li, X. L.; Adalı, T.: Nonorthogonal independent vector analysis using multivariate Gaussian model, (2010)
[10] Hotelling, H.: Relation between two sets of variables, Biometrika 28, No. 3/4, 321-377 (1936) · Zbl 0015.40705
[11] Kettenring, J. R.: Canonical analysis of several sets of variables, Biometrika 58, No. 3, 433-451 (1971) · Zbl 0225.62072 · doi:10.1093/biomet/58.3.433
[12] Eltoft, T.; Kim, T.; Lee, T. W.: On the multivariate Laplace distribution, IEEE signal process. Lett. 13, No. 5, 300-303 (2006)
[13] Comon, P.: Independent component analysis: a new concept?, Signal process. 36, No. 3, 287-314 (1994) · Zbl 0791.62004 · doi:10.1016/0165-1684(94)90029-9
[14] Belouchrani, A.; Meraim, K. Abed; Cardoso, J. F.; Moulines, E.: A blind source separation technique based on second order statistics, IEEE trans. Signal process. 45, No. 2, 434-444 (1997)
[15] Cardoso, J. F.; Souloumiac, A.: Blind beamforming for non-Gaussian signals, IEE proc. F 140, No. 6, 362-370 (1993)
[16] Hyvärinen, A.; Karhunen, J.; Oja, E.: Independent component analysis, (2001)
[17] Yeredor, A.: Non-orthogonal joint diagonalization in the least-squares sense with application in blind source separation, IEEE trans. Signal process. 50, No. 7, 1545-1553 (2002) · Zbl 1369.15005
[18] Li, X. L.; Zhang, X. D.: Nonorthogonal joint diagonalization free of degenerate solution, IEEE trans. Signal process. 55, No. 5, 1803-1814 (2007) · Zbl 1391.94295
[19] Hurley, J. R.; Cattell, R. B.: Producing direct rotation to test a hypothesized factor structure, Behav. sci. 7, 258-262 (1962)
[20] Golub, G. H.; Van Loan, C. F.: Matrix computations, (1989) · Zbl 0733.65016
[21] Loesch, B.; Nesta, F.; Yang, B.: On the robustness of the multidimensional state coherence transform for solving the permutation problem of frequency-domain ICA, (2010)
[22] Li, X. L.; Anderson, M.; Adalı, T.: Second and higher-order correlation analysis of multiple multidimensional variables by joint diagonalization, (2010)
[23] D. De Moor (Ed.), Daisy: Database for the Identification of Systems. Available online at: \langlehttp://www.esat.kuleuven.ac.be/sista/daisy angle.
[24] Zarzoso, V.; Nandi, A. K.: Noninvasive fetal electrocardiogram extraction: blind source separation versus adaptive noise cancellation, IEEE trans. Biomed. eng. 48, No. 1, 12-17 (2001)
[25] Cardoso, J. F.: Multidimensional independent component analysis, , 1941-1944 (1998)
[26] Barros, A. K.; Cichocki, A.: Extraction of specific signals with temporal structure, Neural comput. 13, No. 9, 1995-2003 (2001) · Zbl 1003.94505 · doi:10.1162/089976601750399272
[27] Li, X. L.; Zhang, X. D.: Sequential blind extraction adopting second-order statistics, IEEE signal process. Lett. 14, No. 1, 58-61 (2007)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.