Dr Murat Uney is a lecturer in signal processing at The University of Edinburgh. His research interests are in the theory of signal processing and machine learning; probabilistic models and Bayesian computations for applications in sensor fusion, signal and information processing and data sciences. Previously, he was a Research Fellow at the University of Edinburgh (2013-18), a Research Scientist at the Centre for Maritime Research and Experimentation (2018-21), and a lecturer at the University of Liverpool (2021-25).
Murat is a member of the IEEE Signal Processing Society, IEEE Aerospace and Electronic Systems Society, and a fellow of the Higher Education Academy.
He is an Associate Editor for Elsevier Digital Signal Processing and a reviewer for several journals and conferences.
Recent research outcome “Tree Reparameterized Belief Propagation for Gaussian Markov Random Fields” is submitted to ICASSP 2026. The paper provides explicit formulae and an algorithmic framework for TRP-BP on GMRFs and, through experiments, demonstrates that TRP-BP converges faster than loopy BP in the case of certain pairwise Gaussian MRFs.
The code used in the submission is in the Tree-Reparameterized-Belief-Propagation github repository.
Previously, I was the Liverpool principal investigator (PI) in a collaborative project with Prof James Hopgood that addressed radar signal processing problems using advanced Bayesian computations. This project investigated a novel approach to coherent long-time integration, namely, coherent track-before-detect. The Liverpool team had Prof Simon Maskell and Dr Paul Horridge onboard.
Ongoing work aims to complete publications from the outcomes.
Graduated:
Murat holds a Post-graduate Certificate in Academic Practice (PGCAP) from the University of Liverpool.
