Publications

Machine Learning

Graph Cuts with Arbitrary Size Constraints Through Optimal Transport

A common way of partitioning graphs is through minimum cuts. One drawback of classical minimum cut methods is that they tend to produce small groups, which is why more balanced variants such as normalized and ratio cuts have seen more success…

Chakib Fettal, Lazhar Labiod, Mohamed Nadif

Transactions on Machine Learning Research Journal - 2024

Electromagnetism

Exact and asymptotic reductions of surface radiation integrals with complex phases to contour integrals

We develop here an efficient method for the reduction of surface radiation integrals to non-singular contour integrals, when we suppose known, as in Physical Optics (PO), the analytic expression of surface currents whose electromagnetic radiation is…

J.M.L. Bernard

Electromagnetism

New insights in integral representation theory for the solution of complex canonical diffraction problems

The problem of scattering by 2D and 3D canonical objects with imperfectly conducting surfaces requires some particular efforts on the representation of scattered and incident fields, and we present here some remarkable aspects of them in complex…

J.M.L. Bernard

Mathematics

SPSO-Pruner: a network pruning method on YOLOv5 for fewer categories scenarios

Yifei Zhang, Xinchen Liu, Yan Chen, Linyao Xie, Hongbo Wang, Osman Salem

Multimedia Tools and Applications - 2023

Life Sciences

Interplay of early negative life events, development of orbitofrontal cortical thickness and depression in young adulthood

Abstract Background Early negative life events (NLE) have long‐lasting influences on neurodevelopment and psychopathology. Reduced orbitofrontal cortex (OFC) thickness was frequently associated with NLE and depressive symptoms. OFC thinning might…

Lea Backhausen, Jonas Granzow, Juliane Fröhner, Eric Artiges, Marie‐laure Paillère-Martinot, Hervé Lemaître, Fabio Sticca, Tobias Banaschewski, Sylvane Desrivières, Antoine Grigis, Andreas Heinz, Rüdiger Brühl, Dimitri Papadopoulos-Orfanos, Luise Poustka, Sarah Hohmann, Lauren Robinson, Henrik Walter, Jeanne Winterer, Gunter Schumann, Jean‐luc Martinot, Michael Smolka, Nora Vetter

JCPP Advances - 2023

Engineering Sciences

Numerical analysis and optimization of a vertical axis wind turbine with a flapped blade

Alaeddine Zereg, Nadhir Lebaal, Mounir Aksas, David Bassir

MODERN MATERIALS AND MANUFACTURING 2023 - 2023

Signal and Image processing

Multi-Snapshot Inversion Technique for an Interferometric Earth-Observation Satellite

Antenna arrays for passive microwave remote sensing of Earth produce images contaminated by aliasing due to insufficient sampling of the u-v plane: engineering constraints often preclude the deployment of arrays with antennas spaced sufficiently…

Max Dunitz

Mathematics

Analyse et équations aux dérivées partielles

Thomas Alazard

Artificial Intelligence

Statistical background modeling and applications in remote sensing

This thesis addresses some problems in remote sensing and statistical background modeling using the a-contrario theory and artificial neural network models. The work is motivated by two applications in remote sensing where the control of false…

Antoine Tadros

Computer Science

Data Augmentation by Adaptative Targeted Zoom for MRI Brain Tumor Segmentation

This study presents a novel data augmentation methodology to enhance the scientific outcomes achieved during the Brats 2023 challenge. The 3D-UNet neural network, initially proposed by Ronneberger et al. in 2015 for biomedical image segmentation, is…

José Armando Hernández

Latin American Workshop on Computational Neuroscience - 2023