Fast adaptive identification of autoregressive signals subject to noise

Research output: Contribution to journalConference articlepeer-review

1 Citation (Scopus)

Abstract

Adaptive identification of autoregressive (AR) signals subject to white measurement noise is studied. A fast adaptive algorithm, which is based on the recently proposed improved least-squares (LS) method, is developed. The variance of the white measurement noise, which specifies the source of the noise-induced bias in the standard LS estimate, is calculated by means of extra noisy measurements of the AR signal. With a good estimate of the measurement noise variance being attained more quickly, the convergence speed of the developed adaptive identification algorithm can be accelerated. Numerical results are presented to demonstrate the promising performance of the new fast adaptive identification algorithm.

Original languageEnglish
Pages (from-to)III313-III316
JournalProceedings - IEEE International Symposium on Circuits and Systems
Volume3
Publication statusPublished - 2004
Event2004 IEEE International Symposium on Cirquits and Systems - Proceedings - Vancouver, BC, Canada
Duration: 23 May 200426 May 2004

Fingerprint

Dive into the research topics of 'Fast adaptive identification of autoregressive signals subject to noise'. Together they form a unique fingerprint.

Cite this