Maximum Likelihood Parameter Estimation Under Signal Intermittency

Date

2023-12-25

Author

Bilgi Akdemir, Şafak

Metadata

Show full item record

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

Item Usage Stats

120
views

141
downloads

Cite This

In this thesis, the parameter estimation problem under signal intermittency is explored. Firstly, the maximum-likelihood (ML) direction of arrival (DOA) estimation problem is studied for the intermittent jamming scenario. The intermittent jamming modality is based on the assumption that only a subset of the collected snapshots are contaminated by the jammer while the other snapshots are jammer-free; but the receiver does not know which is which. Solving problem analytically using maximum likelihood approach is intractable and for this reason an expectation maximization (EM) method based solution is developed. Secondly, complex exponential frequency estimation of an intermittent signal problem is addressed. As a reason for this intermittency in the signal, one may assert the operational state of frequency measuring sensor, say healthy and unhealthy state. In the healthy state, the sensor produces high quality output meaning that the signal to noise ratio is high; whereas in the faulty state the exact opposite of this situation is true. This phenomena is represented by an additive noise which is modeled as a correlated mixture of two Gaussian distributions. A computationally efficient method for the frequency estimation under this setting is proposed by utilizing again EM method. Cramer-Rao type performance lower bounds are also derived to compare the performance of the suggested estimators. Finally, the performance improvement achieved by the proposed methods over the competing methods are shown by numerical simulations.

Subject Keywords

Direction of arrival estimation, Jamming, Intermittent interference, Mixture of Gaussians, Frequency estimation, Maximum-likelihood estimation, Expectation-maximization algorithm, Cramer-Rao bound

URI

https://hdl.handle.net/11511/107827

Collections

Graduate School of Natural and Applied Sciences, Thesis