An Algebraic Algorithm for Joint Independent Subspace Analysis

  • Jia-Xing YangEmail author
  • Xiao-Feng Gong
  • Gui-Chen Yu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11554)


In this work, we propose an algebraic algorithm called coupled exact joint block decomposition (CE-JBD) for joint independent subspace analysis (JISA), an extension to joint blind source separation. In JISA, tensors admitting coupled rank-\((L_m,L_n,\cdot )\) Block Term Decomposition (BTD) can be constructed using second order statistics of non-stationary signals. And the loading matrices to be estimated will be computed from these tensors via coupled rank-\((L_m,L_n,\cdot )\) BTD based algorithms. However, most of the existing algorithms resort to iterative techniques. They heavily rely on a good starting point. Capable of providing such a point, our proposed CE-JBD, based on coupled rank-\((L_m,L_n,\cdot )\) BTD, achieves JISA only by employing generalized eigenvalue decomposition followed by a clustering step and singular value decomposition. To validate its efficacy, as well as its ability to serve its iterative counterparts, we present some experiment results in the end.


Coupled rank-\({{(}}L_m, L_n , \cdot {{)}}\) block term decomposition Second order statistics Joint independent subspace analysis Coupled exact joint block decomposition 



This research is funded by national natural science foundation of China (Grant nos. 61331019 and 61379012).


  1. 1.
    Kim, T., Attias, H.T., Lee, S.Y.: Blind source separation exploiting higher-order frequency dependencies. IEEE Trans. Audio Speech Lang. Proc. 15(1), 70–79 (2006)Google Scholar
  2. 2.
    Li, Y.O., Adali, T., Wang, W.: Joint blind source separation by multiset canonical correlation analysis. IEEE Trans. Signal Proc. 57(10), 3918–3929 (2009)Google Scholar
  3. 3.
    Correa, N.M., Eichele, T., Adali, T.: Multi-set canonical correlation analysis for the fusion of concurrent single trial ERP and functional MRI. Neuroimage 50(4), 1438–1445 (2010)Google Scholar
  4. 4.
    Correa, N.M., Adali, T., Li, Y.O.: Canonical correlation analysis for data fusion and group inferences. Signal Proc. Mag. IEEE 27(4), 39–50 (2010)Google Scholar
  5. 5.
    Chatel-Goldman, J., Congedo, M., Phlypo, R.: Joint BSS as a natural analysis framework for EEG-hyperscanning. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 1212–1216. IEEE Press, Vancouver (2013)Google Scholar
  6. 6.
    Gong, X.F., Wang, X.L., Lin, Q.H.: Generalized non-orthgonal joint diagonalization with LU decomposition and successive rotation. IEEE Trans. Signal Proc. 63(5), 1322–1334 (2015)Google Scholar
  7. 7.
    Gong, X.F., Lin, Q.H., Cong, F.Y., De Lathauwer, L.: Double coupled canonical polyadic decomposition for joint blind source separation. IEEE Trans. Signal Proc. 66(13), 3475–3490 (2018)Google Scholar
  8. 8.
    Lahat, D., Jutten, C.: Joint independent subspace analysis using second-order statistics. IEEE Trans. Signal Proc. 64(18), 4891–4904 (2016)Google Scholar
  9. 9.
    Lahat, D., Jutten, C.: Joint blind source separation of multidimensional components: model and algorithm. In: European Signal Processing Conference, pp. 1417–1421. IEEE Press, Lisbonne (2014)Google Scholar
  10. 10.
    Lahat, D., Jutten, C.: Joint independent subspace analysis: a quasi-Newton algorithm. In: Vincent, E., Yeredor, A., Koldovský, Z., Tichavský, P. (eds.) LVA/ICA 2015. LNCS, vol. 9237, pp. 111–118. Springer, Cham (2015). Scholar
  11. 11.
    Sorber, L., Barel, M.V., De Lathauwer, L.: Structured data fusion. IEEE J. Sel. Top. Signal Proc. 9(4), 586–600 (2015)Google Scholar
  12. 12.
    Gong, X.F., Lin, Q.H., et al.: Coupled rank-\((Lm, Ln, \cdot )\) block term decomposition by coupled block simultaneous generalized schur decomposition. In: International Conference on Acoustics, Speech and Signal Processing, pp. 2554–2558. IEEE Press, Shanghai (2016)Google Scholar
  13. 13.
    Lahat, D., Jutten, C.: Joint independent subspace analysis: uniqueness and identifiability. IEEE Trans. Signal Proc. 67(3), 684–699 (2019)Google Scholar
  14. 14.
    De Lathauwer, L.: Decompositions of a higher-order tensor in block terms-part I: lemmas for partitioned matrices. SIAM J. Matrix Anal. Appl. 30(3), 1022–1032 (2008)Google Scholar
  15. 15.
    Nion, D.: A tensor framework for nonunitary joint block diagonalization. IEEE Trans. Signal Proc. 59(10), 4585–4594 (2011)Google Scholar
  16. 16.
    Anderson, T.W.: An Introduction to Multivariate Statistical Analysis, New York (2003)Google Scholar
  17. 17.
    Tensorlab 3.0 - numerical optimization strategies for large-scale constrained and coupled matrix/tensor factorization.

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.School of Information and Communication EngineeringDalian University of TechnologyDalianChina

Personalised recommendations