On the Cramér-Rao lower bound under model mismatch

Download

index.pdf

Date

2014-04-24

Author

Fritsche, Carsten
Orguner, Umut
Özkan, Emre
Gustafsson, Fredrik

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

282
views

0
downloads

Cram´er-Rao lower bounds (CRLBs) are proposed for deterministic parameter estimation under model mismatch conditions where the assumed data model used in the design of the estimators differs from the true data model. The proposed CRLBs are defined for the family of estimators that may have a specified bias (gradient) with respect to the assumed model. The resulting CRLBs are calculated for a linear Gaussian measurement model and compared to the performance of the maximum likelihood estimator for the corresponding estimation problem.

Subject Keywords

Statistical Signal Processing, CramerRao Lower bound, Parameter Estimation, Model mismatch

URI

https://hdl.handle.net/11511/37264

DOI

https://doi.org/10.1109/icassp.2015.7178719

Collections

Department of Electrical and Electronics Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

Analysis Window Length Selection For Linear Signal Models Yazar, Alper; Candan, Çağatay (2015-05-19) A method is presented for the selection of analysis window length, or the number of input samples, for linear signal modeling without compromising the model assumptions. It is assumed that the signal of interest lies in a known linear space and noisy samples of the signal is provided. The goal is to use as many signal samples as possible to mitigate the effect of noise without violating the assumptions on the model. An application example is provided to illustrate the suggested method.
On localization and tracking using received signal strength measurements / Yılmaz, Alptekin; Yılmaz, Ali Özgür; Orguner, Umut; Department of Electrical and Electronics Engineering (2015) In this study, first, some received signal strength (RSS) based localization techniques, including maximum likelihood estimation (MLE), multidimensional scaling (MDS) and weighted least squares (WLS), are investigated and compared to each other via a simulation study within the perspective of a collaborative localization scenario. MLE using RSS measurement model, called RSS-MLE is known in the literature to be significantly biased. An important observation of this work is that the aforementioned bias can be...
Guaranteed Exponential Convergence without Persistent Excitation in Adaptive Control Yayla, Metehan; Kutay, Ali Türker (2016-09-02) In this paper, a new adaptive control framework for linear systems in which the matched uncertainty can be linearly parameterized is introduced to guarantee the global exponential stability of reference tracking error and parameter convergence error without requiring restrictive persistent excitation condition. The framework uses time histories of control input and system signals to construct least-squares problem based on recorded data. Then, unique solution to least-squares problem is computed, and assign...
ON PARAMETRIC LOWER BOUNDS FOR DISCRETE-TIME FILTERING Fritsche, Carsten; Orguner, Umut; Gustafsson, Fredrik (2016-03-25) Parametric Cramer-Rao lower bounds (CRLBs) are given for discrete-time systems with non-zero process noise. Recursive expressions for the conditional bias and mean-square-error (MSE) (given a specific state sequence) are obtained for Kalman filter estimating the states of a linear Gaussian system. It is discussed that Kalman filter is conditionally biased with a non-zero process noise realization in the given state sequence. Recursive parametric CRLBs are obtained for biased estimators for linear state esti...
Maximum likelihood autoregressive model parameter estimation with noise corrupted independent snapshots Çayır, Ömer; Candan, Çağatay (2021-09-01) Maximum likelihood autoregressive (AR) model parameter estimation problem with independent snapshots observed under white Gaussian measurement noise is studied. In addition to the AR model parameters, the measurement noise variance is also included among the unknowns of the problem to develop a general solution covering several special cases such as the case of known noise variance, noise-free snapshots, the single snapshot operation etc. The presented solution is based on the expectation-maximization metho...

Citation Formats

C. Fritsche, U. Orguner, E. Özkan, and F. Gustafsson, “On the Cramér-Rao lower bound under model mismatch,” 2014, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/37264.