On filtering of Markov chains in strong noise

Pavel Chigansky*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

The filtering problem for finite-state Markov chains is revisited in the low signal-to-noise regime. We give a description of conditional measure concentration around the invariant distribution of the signal and derive asymptotic expressions for the performance indices of the minimum mean square error (MMSE) and minimum a posteriori probability (MAP) filtering estimates.

Original languageAmerican English
Pages (from-to)4267-4272
Number of pages6
JournalIEEE Transactions on Information Theory
Volume52
Issue number9
DOIs
StatePublished - Sep 2006
Externally publishedYes

Bibliographical note

Funding Information:
Manuscript received September 23, 2005; revised May 18, 2006. The research was supported by a grant from the Israel Science Foundation. The author is with the Department of Mathematics, The Weizmann Institute of Science, Rehovot 76100, Israel (e-mail: pavel.chigansky@weizmann.ac.il). Communicated by X. Wang, Associate Editor for Detection and Estimation. Digital Object Identifier 10.1109/TIT.2006.880042

Keywords

  • Error asymptotic
  • Hidden Markov models
  • Nonlinear filtering

Fingerprint

Dive into the research topics of 'On filtering of Markov chains in strong noise'. Together they form a unique fingerprint.

Cite this