An Improved Blind Source Extraction Algorithm

Abstract:

One-unit independent component analysis with reference (ICA-R) is an efficient method capable of extracting a desired source signal by using reference signal. In this paper, a new fast one-unit ICA-R algorithm is derived by using kurtosis contrast function based on new constrained independent component analysis (cICA) theory. The proposed algorithm has lower computational complexity and accurate extraction. Experiments with synthetic signals demonstrate the efficacy and accuracy of the proposed algorithm.

• Periodical: Advanced Materials Research (Volumes 926-930)
• Pages: 2964-2967
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.926-930.2964
• Online since: May 2014
• Authors: Shou Cheng Zhang*
• Keywords: Blind Source Extraction, Contrast Function, ICA with Reference (ICA-R), Kurtosis

References

[1] A. Hyva rinen, E. Oja: Neural Computation, Vol. 9(1997) No. 7, pp.1483-1492.

[2] A. Hyva rinen: IEEE Transactions on Neural Networks, Vol. 10(1999) No. 3, pp.626-634.

[3] A.J. Bell, T. J. Sejnowski: Neural Computation, Vol. 7(1995), pp.1129-1159.

[4] D.S. Huang, J.X. Mi: IEEE Transactions on Neural Networks, Vol. 18(2007) No. 5, pp.1532-1535.

[5] H.M. Park, H.Y. Jeong, T.W. Lee and S.Y. Lee: Electronics Letters, Vol. 35(1999), No. 23, p.2011-(2012).

[6] J.F. Cardoso, B.H. Laheld: IEEE Transactions on Signal, Processing, Vol. 44 (1996) No. 12, pp.3017-3030.

DOI: 10.1109/78.553476

[7] Nathalie Delfosse, Philippe Loubaton: Signal Processing, Vol. 45(1995), No. 1, pp.59-83.

[8] P. Comon: Signal Processing, Vol. 36(1994), No. 3, pp.287-314.

[9] Q.H. Lin, Y.R. Z, F.L. Yin, H.L. Liang, Vince D. Calhoun: Information Sciences, Vol. 177(2007), No. 5, pp.1265-1275.

[10] W. Lu, J.C. Rajapakse: Neurocomputing, Vol. 69(2006) pp.2244-2257.