Efficient algorithm for parameter estimation of noisy AR processes

Research output: Contribution to journalConference articlepeer-review

8 Citations (Scopus)

Abstract

The problem of estimating the unknown parameters of an autoregressive (AR) signal observed in white noise, including signal power and noise variance, is studied. A new method is developed for parameter estimation, which is based on a simple technique of estimating the measurement noise variance by increasing the underlying AR model by one dimension. The advantage of the presented methods is that consistent estimates can be directly achieved without prefiltering of noisy data and without making any parameter transformation.

Original languageEnglish
Pages (from-to)2509-2512
Number of pages4
JournalProceedings - IEEE International Symposium on Circuits and Systems
Volume4
Publication statusPublished - 1997
EventProceedings of the 1997 IEEE International Symposium on Circuits and Systems, ISCAS'97. Part 4 (of 4) - Hong Kong, Hong Kong
Duration: 9 Jun 199712 Jun 1997

Fingerprint

Dive into the research topics of 'Efficient algorithm for parameter estimation of noisy AR processes'. Together they form a unique fingerprint.

Cite this