Share Email Print

Proceedings Paper

On the performance of variable forgetting factor recursive least-squares algorithms
Author(s): Camelia Elisei-Iliescu; Constantin Paleologu; Răzvan Tamaş
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The recursive least-squares (RLS) is a very popular adaptive algorithm, which is widely used in many system identification problems. The parameter that crucially influences the performance of the RLS algorithm is the forgetting factor. The value of this parameter leads to a compromise between tracking, misadjustment, and stability. In this paper, we present some insights on the performance of variable forgetting factor RLS (VFF-RLS) algorithms, in the context of system identification. Besides the classical RLS algorithm, we mainly focus on two recently proposed VFF-RLS algorithms. The novelty of the experimental setup is that we use real-world signals provided by Romanian Air Traffic Services Administration, i.e., voice and noise signals corresponding to real communication channels. In this context, the Air Traffic Control (ATC) communication represents a challenging task, usually involving non-stationary environments and stability issues.

Paper Details

Date Published: 14 December 2016
PDF: 7 pages
Proc. SPIE 10010, Advanced Topics in Optoelectronics, Microelectronics, and Nanotechnologies VIII, 1001023 (14 December 2016); doi: 10.1117/12.2242960
Show Author Affiliations
Camelia Elisei-Iliescu, Univ. Politehnica of Bucharest (Romania)
Constantin Paleologu, Univ. Politehnica of Bucharest (Romania)
Răzvan Tamaş, Maritime Univ. of Constanta (Romania)

Published in SPIE Proceedings Vol. 10010:
Advanced Topics in Optoelectronics, Microelectronics, and Nanotechnologies VIII
Marian Vladescu; Cornel T. Panait; Razvan Tamas; George Caruntu; Ionica Cristea, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?