Summary

Proceedings of the 2013 International Symposium on Nonlinear Theory and its Applications

2013

Session Number:B2L-B

Session:

Number:244

Performance of Nonlinear BSS by PSO structure

Takuya Kurihara,  Kenya Jin'no,  

pp.244-247

Publication Date:

Online ISSN:2188-5079

DOI:10.15248/proc.2.244

PDF download (418.9KB)

Summary:
Blind source separation (BSS) is a technique for recovering an original source signal from mixing signals without the aid of information of the source signal. In this study, we consider the case where the original signals are nonlinearly mixed. In order to solve such problem, we apply a radial basis function (RBF) network to the nonlinear BSS system. The inverse mapping of the nonlinear mixture system is approximated by the RBF network. For the system to be able to approximate the inverse mapping, it is necessary to learn the parameter of the RBF network. We suppose the original source signals are independent. In this case, if the mixture signals can be separated, the higher order cross-moment of the output signals are decreased. Particle swarm optimization is used for the learning algorithm. By using a numerical simulation, we conform the performance of the signal separation ability of the proposed system. Simulation results indicate that the proposed approach has good performance.

References:

[1] P. Comon, IEEE Signal Processing, vol. 36, pp.287-314, 1994.

[2] R. Vigaaário, J. Särekä, V. Jousmäki, M. Hämäläinen, and E. Oja, IEEE Trans. Biomed. Eng. , vol. 47, pp. 589-593, 2000.

[3] P. Pajunen, A. Hyvärinen, and J. Karhunen, Proc. Int. Conf. on Neural Information Processing, pp. 1207-1210, Hong Kong, 1996.

[4] H. Lappalainen, and X. Giannakopoulos, Proc. Int. Conf. Artificial Neural Networks, pp. 19-24, 1999

[5] Y. Tan, J. Wang, and J. M. Zurada, IEEE Trans. Neural Networks, vol. 12, pp. 124-134, 2001.

[6] A. Hyvarinen and P. Pajunen, Neural Networks, vol. 12, pp. 429-439, 1999.

[7] S. Sirayanone and R. L. Hardy, Journal of Applied Sciences and Computations Vol. 1, pp. 437-475, 1995.

[8] J. Kennedy, Proc. of IEEE International Conference on Evolutionary Computation, pp. 303-308, 1997.

[9] T. Tsujimoto, T. Shindo, T. Kimura and K. Jin'no, Proc. 2012 IEEE World Congress on Evolutionary Computation, pp. 1526-1531, 2012.