On neural blind separation with noise suppression and redundancy reduction.
作者： J. Karhunen , A. Cichocki , W. Kasprzak , P. Pajunen
DOI: 10.1142/S0129065797000239
关键词:
摘要: Noise is an unavoidable factor in real sensor signals. We study how additive and convolutive noise can be reduced or even eliminated the blind source separation (BSS) problem. Particular attention paid to cases which number of sensors larger than sources. propose various methods associated adaptive learning algorithms for such extended BSS Performance validity proposed approaches are demonstrated by extensive computer simulations.
sci-hub.se 参考文章(2)
A. Cichocki, R. Unbehauen, Robust estimation of principal components by using neural network learning algorithms Electronics Letters. ,vol. 29, pp. 1869- 1870 ,(1993) , 10.1049/EL:19931244
A. Cichocki, E. Rummert, R. Unbehauen, Robust learning algorithm for blind separation of signals Electronics Letters. ,vol. 30, pp. 1386- 1387 ,(1994) , 10.1049/EL:19940956