### Skapa referens, olika format (klipp och klistra)

**Harvard**

Svensson, L. (2010) *On the Bayesian Cramér-Rao Bound for Markovian Switching Systems*.

** BibTeX **

@article{

Svensson2010,

author={Svensson, Lennart},

title={On the Bayesian Cramér-Rao Bound for Markovian Switching Systems},

journal={IEEE Transactions of Signal Processing},

issn={1053-587X},

volume={58},

issue={9},

pages={4507-4516},

abstract={We propose a numerical algorithm to evaluate the
Bayesian Cramér–Rao bound (BCRB) for multiple model filtering problems. It is assumed that the individual models have additive Gaussian noise and that the measurement model is linear. The algorithm is also given in a recursive form, making it applicable for sequences of arbitrary length. Previous attempts to calculate the BCRB for multiple model filtering problems are based on rough approximations which usually make them simple to calculate. In this paper, we propose an algorithm which is based on Monte Carlo sampling, and which is hence more computationally demanding, but yields accurate approximations of the BCRB. An important observation from the simulations is that the BCRB is more overoptimistic than previously suggested bounds, which we motivate using theoretical results.},

year={2010},

keywords={Cramér–Rao bound, jump Markov system, maneuvering target, multiple model filtering, non-linear filtering, performance bounds.},

}

** RefWorks **

RT Journal Article

SR Electronic

ID 124667

A1 Svensson, Lennart

T1 On the Bayesian Cramér-Rao Bound for Markovian Switching Systems

YR 2010

JF IEEE Transactions of Signal Processing

SN 1053-587X

VO 58

IS 9

SP 4507

OP 4516

AB We propose a numerical algorithm to evaluate the
Bayesian Cramér–Rao bound (BCRB) for multiple model filtering problems. It is assumed that the individual models have additive Gaussian noise and that the measurement model is linear. The algorithm is also given in a recursive form, making it applicable for sequences of arbitrary length. Previous attempts to calculate the BCRB for multiple model filtering problems are based on rough approximations which usually make them simple to calculate. In this paper, we propose an algorithm which is based on Monte Carlo sampling, and which is hence more computationally demanding, but yields accurate approximations of the BCRB. An important observation from the simulations is that the BCRB is more overoptimistic than previously suggested bounds, which we motivate using theoretical results.

LA eng

DO 10.1109/TSP.2010.2051153

LK http://dx.doi.org/10.1109/TSP.2010.2051153

OL 30