Consulter le flux RSS

Publications

Affichage des publications 191 à 200 sur 4003 au total

Embedded Systems

A practical HW-aware NAS flow for AI vision applications on embedded heterogeneous SoCs

Implementing efficient Deep Neural Networks (DNNs) for dense-prediction vision applications on embedded heterogeneous SoCs comes with many challenges, such as latency and energy constraints. To tackle them, we propose a novel and practical multi…

Agathe Archet, Nicolas Ventroux, Nicolas Gac, François Orieux

18th Workshop on Design and Architectures for Signal and Image Processing (DASIP 2025) -

Electronics

Z-SpecNNet: A Real-Time Embedded NN-Based Parameters Estimation for WPT Systems

This article proposes a fully embedded real-time mutual inductance and load estimation technique (Z-SpecNNet) applicable to wireless power transfer (WPT) systems. The technique consists of a three-step process, starting with online noise injection…

Thomas Boulanger, Vincenzo Cirimele, Mattia Ricco, Eric Monmasson

IEEE Transactions on Industrial Electronics -

Signal and Image processing

Transfer Learning for Data Fusion for Electromagnetic and Ultrasound Breast Imaging

Aiming at improved breast imaging, this contribu- tion explores several scenarios for segmenting and estimating the distribution of electromagnetic (EM) and/or ultrasonic (US) parameters within breast tissue. A two-fold approach is adopted,…

Valentin Noël, Thomas Rodet, Dominique Lesselier

IEEE Transactions on Computational Imaging -

Electromagnetism

Tuning the coercive field of strontium M-type hexaferrite nanopowders via pH control

Single-phase strontium M-type hexaferrite (SrFe12O19) nanopowders were successfully synthesized via a citrate precursor sol–gel method. This study investigates the effect of pH variation in the precursor solution on the structural, morphological,…

Adel Sassi, Khalil Moussi, Meng Tang, Alexandre Pasko, Selma Amara, Camelia-Florina Florica, Gianluca Setti, Frédéric Mazaleyrat

Mechanics of materials

Ellipsometry of surface acoustic waves using 3D vibrometry for viscoelastic material characterization by the estimation of complex Lamé coefficients versus the frequency

Surface acoustic waves (SAW) are adequate regarding material characterization because they have low geometric attenuation compared to bulk waves. SAW can be generated easily by normal excitation using contact transducers or power lasers and have…

Aziz Bouzzit, Loïc Martinez, Andrés Arciniegas, Stephane Serfaty, Nicolas Wilkie-Chancellier

Applied Acoustics -

Acoustics

An innovative method for the objective comparison of the performance of active control devices

In the active control literature, the question of how to objectively and comprehensively compare system performance has received little attention. In most cases, comparisons are only made on a paper-specific application and cannot be extended to new…

Loïc Forma, Henri Boutin, Nicolas Wilkie-Chancellier, Sandie Le Conte, Marguerite Jossic

Journal of Sound and Vibration -

Electric power

Analysis of the Timetable Impact on Energy Consumption of a Subway Line

This paper analyzes the timetable impact on the energy consumption of a subway line. In most timetable studies, simplified models are used and can lead to misestimation of the braking energy and thus the energy transfer between braking vehicles and…

Ryan Berriel, Philippe Delarue, Clément Mayet, Alain Bouscayrol, Charles Brocart

IEEE Transactions on Vehicular Technology -

Computer Vision and Pattern Recognition

Robust classification with noisy labels using Venn-Abers predictors

The advent of deep learning methods has led to impressive advances in computer vision tasks over the past decades, largely due to their ability to extract non-linear features that are well adapted to the task at hand. For supervised approaches, data…

Ichraq Lemghari, Sylvie Le Hégarat-Mascle, Emanuel Aldea, Jennifer Vandoni

Journal of Electronic Imaging -