The Marginal Enumeration Bayesian Cramer-Rao Bound for Jump Markov Systems


Creative Commons License

FRITSCHE C., ORGUNER U. , Svensson L., Gustafsson F.

IEEE SIGNAL PROCESSING LETTERS, vol.21, no.4, pp.464-468, 2014 (Journal Indexed in SCI) identifier identifier

  • Publication Type: Article / Article
  • Volume: 21 Issue: 4
  • Publication Date: 2014
  • Doi Number: 10.1109/lsp.2014.2305115
  • Title of Journal : IEEE SIGNAL PROCESSING LETTERS
  • Page Numbers: pp.464-468

Abstract

A marginal version of the enumeration Bayesian Cramer-Rao Bound (EBCRB) for jump Markov systems is proposed. It is shown that the proposed bound is at least as tight as EBCRB and the improvement stems from better handling of the nonlinearities. The new bound is illustrated to yield tighter results than BCRB and EBCRB on a benchmark example.