INDEPENDENT SUBSPACE ANALYSIS FOR BLIND SIGNAL SEPARATION: MODELS AND ALGORITHMS

R. Li and F. Wang

References

  1. [1] A. Hyvarinen, J. Karhunen, & E. Oja, Independent componentanalysis (New York: John Wiley & Sons, 2001).
  2. [2] A. Cichocki & S. Amari, Adaptive blind signal and imageprocessing: learning algorithms and applications (New York:John Wiley & Sons, 2002).
  3. [3] A. Hyvarinena & P. Hoyer, Emergence of phase and shiftinvariant features by decomposition of natural images intoindependent feature subspaces, Neural Computation, 12 (7),2000, 1705–1720.
  4. [4] J.F. Cardoso, Multidimensional independent component anal-ysis, Proc. IEEE 1998 Int. Conf. on Acoustics, Speech, andSignal Processing (ICASSP’98), Seattle, WA, USA, IEEE,1998, 1941–1944.
  5. [5] F.J. Theis, Blind signal separation into groups of dependentsignals using joint block diagonalization, Proc. ISCAS 2005,Kobe, Japan, 2005, 5875–5881.
  6. [6] B. Poczos & A. Lorincz, Independent subspace analysis usingk-nearest neighborhood distances, Lecture Notes in ComputerScience, 3697, Part II, 2005, 163–168.
  7. [7] A. Hyvarinen, U. Koster, FastISA: A fast fixed-point algorithmfor independent subspace analysis, Proc. European Symposiumon Artificial Neural Networks, Bruges, Belgium, 2006.
  8. [8] H. Choi & S. Choi, Relative gradient learning for independentsubspace analysis, Proc. Int. Joint Conf. Neural Networks(IJCNN), Vancouver, BC, Canada, 2006, 3,919–3,924.
  9. [9] F.R. Bach & M.I. Jordan, Kernel independent componentanalysis, Journal of Machine Learning Research, 3, 2002, 1–48.
  10. [10] C.F. Caiafa & A.N. Proto, Separation of statistically dependentsources using an L2-distance non-Gaussianity measure, SignalProcessing, 86 (11), 2006, 3,404–3,420.
  11. [11] F.S. Wang, H.W. Li, & R. Li, Novel nongaussianity measurebased bss algorithm for dependent signals, Lecture Notes inComputer Science, 4505, 2007, 837–844.
  12. [12] C.F. Caiafa, E. Salerno, A.N. Protoa, & L. Fiumi, Blindspectral unmixing by local maximization of non-Gaussianity,Signal Processing, 88 (1), 2008, 50–68.
  13. [13] K. Zhang & L.W. Chan, An adaptive method for subbanddecomposition ICA, Neural Computation, 18 (1), 2006, 191–223.
  14. [14] F. Abrard & Y. Deville, A time-frequency blind signal sep-aration method applicable to underdetermined mixtures ofdependent sources, Signal Processing, 85 (7), 2005, 1389–1403.
  15. [15] F.J. Theis, Uniqueness of complex and multidimensional inde-pendent component analysis, Signal Processing, 84 (5), 2004,951–956.
  16. [16] F. J. Theis, Towards a general independent subspace analysis,Proc. NIPS 2006, 2007.
  17. [17] M.R. Aghabozorgi & A.M. Doost-Hoseini, Blind separation ofjointly stationary correlated sources, Signal Processing, 84 (2),2004, 317–325.
  18. [18] G. Blanchard, M. Kawanabe, M. Sugiyama, V. Spokoiny,& K.-R. Muller, In search of non-gaussian components of a137high-dimensional distribution, Journal of Machine LearningResearch, 7, 2006, 247–282.
  19. [19] H. Shen & K. Huper, Generalized FastICA for independentsubspace analysis, Proc. ICASSP, 4, 2007, 1409–1412.
  20. [20] K. Abed-Meraim & A. Belouchrani, Algorithms for joint blockdiagonalization, Proc. EUSIPCO 2004, Vienna, Austria, 2004,209–212.
  21. [21] Z. Szabo, B. Poczos, & A. Lorincz, Auto-regressive independentprocess analysis without combinatorial efforts, Pattern Analysisand Applications manuscript, considering for publishing, 2008.
  22. [22] Z. Szabo, B. Poczos, & A. Lorincz, Undercomplete blind sub-space deconvolution, Journal of Machine Learning Research,8, 2007, 1063–1095.

Important Links:

Go Back