| Paper: | SPTM-L5.2 | ||
| Session: | LMS-type Adaptive Filters | ||
| Time: | Wednesday, May 17, 14:20 - 14:40 | ||
| Presentation: | Lecture | ||
| Topic: | Signal Processing Theory and Methods: Adaptive Systems and Filtering | ||
| Title: | Modeling Finite Precision LMS Behavior Using Markov Chains | ||
| Authors: | Yasmín Montenegro, University of Antofagasta, Chile; José Carlos Bermudez, Federal University of Santa Catarina, Brazil; Vítor Nascimento, University of São Paulo, Brazil | ||
| Abstract: | We propose a new model for the behavior of the Least Mean Square (LMS) algorithm when implemented in nite precision. We model the adaptive lter coef cients as a Markov chain and determine its transition probability matrix for the one-dimensional case. We also determine conditions to avoid the so-called stopping phenomenon. The proposed model eliminates the linearizations used in previous models, accounts for saturation effects and leads to accurate estimations of the mean-square error behavior. Monte Carlo simulation results illustrate the quality of the proposed model. | ||
©2018 Conference Management Services, Inc. -||- email: webmaster@icassp2006.org -||- Last updated Friday, August 17, 2012