OS-CMA for blind channel equalization and signal extraction

The optimal step-size constant modulus algorithm (OS-CMA) is based on a computationally efficient iterative technique to minimize the CM cost function. This technique computes algebraically the step size (adaption coefficient) globally minimizing the CM contrast in the search direction at each iteration.

OS-CMA's optimization technique is similar to that used in RobustICA. As a result, the OS-CMA shares many advantages of RobustICA, including high convergence speed and the ability to avoid spurious local extrema.

More details about the OS-CMA and its comparative performance analysis can be found in the references below.

References

[1] V. Zarzoso, P. Comon and D. Slock, "Semi-Blind Methods for Communications", in: P. Comon and C. Jutten (Eds.), Handbook of Blind Source Separation, Independent Component Analysis and Applications, Oxford, UK: Academic Press, 2010, chapter 15, pp. 593-638.

[2] V. Zarzoso and P. Comon, "Optimal Step-Size Constant Modulus Algorithm", IEEE Transactions on Communications, Vol. 56, No. 1, January 2008, pp. 10-13. (119KB)

[3] V. Zarzoso et P. Comon, "Méthodes semi-aveugles pour les télécommunications", dans : C. Jutten et P. Comon, Séparation de sources 2 : au-delà de l'aveugle et applications, Paris : Hermes, 2007, chapitre 8, pp. 303-353.

[4] V. Zarzoso and P. Comon, "Semi-Blind Constant Modulus Equalization with Optimal Step Size", in: Proceedings ICASSP-2005, 30th IEEE International Conference on Acoustics, Speech and Signal Processing, Philadelphia, PA, March 18-23, 2005, Vol. III, pp. 577-580. (127KB)

[5] V. Zarzoso and P. Comon, "Blind Channel Equalization with Algebraic Optimal Step Size", in: Proceedings EUSIPCO-2005, XIII European Signal Processing Conference, Antalya, Turkey, September 4-8, 2005. (229KB)

Download and installation instructions:
• Download the zip-file by clicking on the above link.

• Extract the files into oscma_package directory.

• From Matlab's command line, set current directory to oscma_package.

• Type help oscma_package or doc oscma_package for details about the algorithm and the different functions contained in the package.

• Type os_cma_demo to run a simple demo.

Conditions of use:
This is open-source code. Please, feel free to edit the M-files and modify them as you wish. It is only requested that original authorship be acknowledged and modifications be clearly indicated in the code (history section and elsewhere as appropriate).

If you use this package to generate results in your publications, please cite at least reference [2] above.


The OS-CMA by Vicente Zarzoso and Pierre Comon is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Compatibility:
The package has been tested on Matlab 7.14.

Feedback:
Please, report any bugs, comments or suggestions to <>.