Blind source separation based on minimum description length. Elena G. Revunova. IWIM, Prague, 2007.

 Article (in pdf)

Abstract. Separation of signal mixtures using blind source separation (BSS) approach is considered. Objective function for BSS based on minimum description length principle is developed. Testing has shown a better robustness to additive noise than that of PCA and FastICA.

Keywords. Blind source separation, minimum description length, sparse approximation.

References.

1. Comon P.: Independent component analysis: a new concept. Signal Processing, 36:287-314, 1994.

2. Hyvarinen A., Oja E.: Independent component analysis: algorithms and applications. Neural Networks, 13(4-5):411–430, 2000.

3. Zibulevsky M., Pearlmutter B.A.: Blind source separation by sparse decomposition in a signal dictionary. Neural Computations, 13(4):863-882, 2001.

4. Cichocki A., Amari S.: Adaptive Blind Signal and Image Processing. New York: Wiley, 586 pp, 2002.

5. Revunova E.G.: Two approaches to separation of signal mixtures based on linear models. System Technologies 6(41):142-148, 2005 (in Russian).

6. Rissanen J.: Lectures on statistical modeling theory.  http://www.cs.tut.fi/~rissanen/, 2002.

7. Li M., Vitanyi P.M.B.: An Introduction to Kolmogorov Complexity and Its Applications, 2nd Edition. New York: Springer-Verlag, 637 pp, 1997.

8. Hansen M., Yu B.: Model selection and minimum description length principle. J. Amer. Statist. Assoc., 96: 746-774, 2001.

9. Gribonval R., Figueras i Ventura R. M., Vandergheynst P.: A simple test to check the optimality of sparse signal approximations. Tech. Rep., IRISA: PI-1661, 2004.

1. Shirman J.D.: Radio-electronic systems: bases of construction and the theory. Moscow: MAKVIS, 826 pp, 1998 (in Russian).