Consistent HMM parameter estimation using Kerridge inaccuracy rates

Timothy L. Molloy, Jason J. Ford

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Citations (Scopus)

Abstract

In this paper, we propose a novel online hidden Markov model (HMM) parameter estimator based on Kerridge inaccuracy rate (KIR) concepts. Under mild identifiability conditions, we prove that our online KIR-based estimator is strongly consistent. In simulation studies, we illustrate the convergence behaviour of our proposed online KIR-based estimator and provide a counter-example illustrating the local convergence properties of the well known recursive maximum likelihood estimator (arguably the best existing solution).

Original languageEnglish
Title of host publication2013 3rd Australian Control Conference, AUCC 2013
Pages73-78
Number of pages6
DOIs
Publication statusPublished - 2013
Externally publishedYes
Event2013 3rd Australian Control Conference, AUCC 2013 - Fremantle, WA, Australia
Duration: 4 Nov 20135 Nov 2013

Publication series

Name2013 3rd Australian Control Conference, AUCC 2013

Conference

Conference2013 3rd Australian Control Conference, AUCC 2013
Country/TerritoryAustralia
CityFremantle, WA
Period4/11/135/11/13

Fingerprint

Dive into the research topics of 'Consistent HMM parameter estimation using Kerridge inaccuracy rates'. Together they form a unique fingerprint.

Cite this