Format: HTML | BibTeX | DC | EndNote | NLM | MARC | MARCXML
000000063 001__ 63
000000063 037__ $$aENY-ARTICLE-2008-054
000000063 041__ $$aeng
000000063 088__ $$aI07/96/I-278
000000063 100__ $$aCichocki, A$$uFRP Riken - ABS Laboratory, Institute of Physical and Chemical Research, Japan
000000063 245__ $$aAdaptive Neural Networks for Robust Estimation of parameters of Noisy Harmonic Signals
000000063 260__ $$c1996-07-11
000000063 300__ $$a4p
000000063 500__ $$aEUSIPCO 1996  VIII. Eight European Signal Processing Conference. Proceedings of Eusipco-96, Trieste, Italy, 10-13 September 1996 / Ed. by G. Ramponi [i in.] Triest : Edizioni LINT, 1996. s. 220-223
000000063 520__ $$aIn many applications, very fast methods are required for estimating and measurement of parameters of harmonic signals distorted by noise. This follows from the fact that signals have often time varying amplitudes. Most of the known digital algorithms are not fully parallel, so that the speed of processing is quite limited. In this paper we propose new parallel algorithms, which can be implemented by analogue adaptive circuits employing some neural network principles. The problem of estimation is formulated as an optimization problem and solved by using the gradient descent method. Algorithms based on the least-squares (LS), the total least-squares (TLS) and the robust TLS criteria are developed and compared. The networks process samples of observed noisy signals and give as a solution the desired parameters of signal components. Extensive computer simulations confirm the validity and performance of the proposed algorithm.
000000063 6531_ $$aneural networks
000000063 6531_ $$aharmonic signals
000000063 6531_ $$aTLS
000000063 6531_ $$aRTLS
000000063 700__ $$aKostyla, P$$uWroclaw University of Technology, Poland
000000063 700__ $$aLobos, T$$uWroclaw University of Technology
000000063 700__ $$aWaclawek, Z$$uWroclaw University of Technology
000000063 8560_ $$
000000063 8564_ $$u$$zAccess to Fulltext
000000063 909CO $$$$pglobal
000000063 980__ $$aARTICLE