Sara El Bouch

Office 04.012

J.-L. Lagrange

28 Av. Valrose

Nice, 06000

I am currently an assitant professor at the Laboratoire J.-L. Lagrange since Septembre 2024, a joint laboratory between Université Côte d’Azur, CNRS and Observatoire de la Côte d’Azur. My research is centered around Estimation and Detection theory, array processing and Machine Learning.

I was a post-doctoral researcher at ISAE-Supaero from January 2023 to August 2024, contributing to the Navigation, Radar and Remote Sensing team. I pursued my doctoral studies at University of Grenoble-Alpes (UGA), in an interdisciplinary field involving two laboratories Gipsa-lab and ISTerre. Under the guidance of Olivier Michel, Pierre Comon and Michel Campillo, my doctoral research delved into a diverse range of topics: Higher-order statistics, Machine Learning Algorithms and real-world applications in Geoscience.

news

Sep 2, 2024	I joined the Signal & Image team at J.-L. Lagrange.
Dec 16, 2022	PhD Defense !

selected publications

Filtering and machine learning on Riemannian manifolds and Lie groups

Samy Labsir, Sara El Bouch, Claudio J Bordin Jr, and 1 more author

Signal Processing, 2025
New Insights into Lower Bound for Lie Groups and their Applications

Sara El Bouch, Samy Labsir, Alexandre Renaux, and 2 more authors

In 2025 59th Annual Conference on Information Sciences and Systems (CISS), 2025
Cramér-Rao Bound for Lie Group Parameter Estimation with Euclidean Observations and Unknown Covariance Matrix

Samy Labsir, Sara El Bouch, Alexandre Renaux, and 2 more authors

IEEE Transactions on Signal Processing, 2024
A normality test for multivariate dependent samples

Sara El Bouch, Olivier Michel, and Pierre Comon

Signal Processing, 2022

Abs

Most normality tests in the literature are performed for scalar and independent samples. Thus, they become unreliable when applied to colored processes, hampering their use in realistic scenarios. We focus on Mardia’s multivariate kurtosis, derive closed-form expressions of its asymptotic distribution for statistically dependent samples, under the null hypothesis of normality and a mixing condition. The calculus is long and tedious but the final result is simple and is implemented with a low computational burden. The proposed expression of the test exhibits good properties on various scenarios; this is illustrated by computer experiments by means of copulas.
Joint Maximum a Posteriori-Maximum Likelihood Estimator for Linear Discrete-Time Systems

Sara ElBouch, Eric Chaumette, and Jordi Vilà-Valls

In CAMSAP 2023 - 2023 IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), 2023
Joint Normality Test Via Two-Dimensional Projection

Sara ElBouch, Olivier J. J Michel, and Pierre Comon

In ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022