Consulter le flux RSS

Publications

Affichage des publications 471 à 480 sur 3858 au total

Robotics

Real-time embedded large-scale place recognition for autonomous ground vehicles using a spatial descriptor

Place recognition is a key task in an autonomous vehicle’s Simultaneous Localization and Mapping (SLAM). The motion estimation is bound to drift over time due to cumulative errors. Fortunately, the correct identification of a revisited area provided…

Mohammed Chghaf, Sergio Alberto Rodriguez Florez, Abdelhafid Elouardi, Samir Bouaziz

Real-time Processing of Image, Depth and Video Information 2023 -

Neural and Evolutionary Computing

Efficient GEMM Implementation for Vision-Based Object Detection in Autonomous Driving Applications

Convolutional Neural Networks (CNNs) have been incredibly effective for object detection tasks. YOLOv4 is a state-of-the-art object detection algorithm designed for embedded systems. It is based on YOLOv3 and has improved accuracy, speed, and…

Fatima Zahra Guerrouj, Sergio Rodríguez Flórez, Mohamed Abouzahir, Abdelhafid El Ouardi, Mustapha Ramzi

Journal of Low Power Electronics and Applications -

Electromagnetism

Optimal Design of High-Speed Electric Machines for Electric Vehicles: A Case Study of 100 kW V-Shaped Interior PMSM

The need of compact machines increased in recent years due to increases in raw materials’ price. Hence, many studies are currently being conducted on high-speed challenges to propose an optimal design methodology. AC losses in windings are often not…

Taha El Hajji, S Hlioui, François Louf, Mohamed Gabsi, Guillaume Mermaz-Rollet, M’hamed Belhadi

Machines -

Life Sciences

Electromagnetic Breast Imaging and Uncertainty Quantification with Bayesian Neural Networks

Different scenarios of breast imaging segmentation and estimation of its electromagnetic (EM) or/and ultrasonic (US) parameters are presented, part of a two-pronged dynamic using Bayesian Neural Networks, the first being to continue obtaining more…

Valentin Noël, Thomas Rodet, Dominique Lesselier

Progress In Electromagnetics Research Symposium -

Engineering Sciences

Identification and characterization of damaged fiber-reinforced laminates in a Bayesian framework

Non-destructive testing of damaged composite laminates modeled from the homogenization of fiber-reinforced polymers has always been and still is a challenge, both by underlying complexity and the difficulties encountered in the quantification of…

Valentin Noël, Thomas Rodet, Dominique Lesselier

26th International Workshop on Electromagnetic Nondestructive Evaluation (ENDE) 2023 -

Materials Science

Grain size and piezoelectric effect on magnetoelectric coupling in BFO/PZT perovskite-perovskite composites

Magnetoelectric multiferroics are provoking much research activity for their potential applications in novel multifunctional devices. Compared with single-phase multiferroics, magnetoelectric composites have competitive advantages. The…

Minghai Yao, Arij Marzouki, Shenglan Hao, Samir Salmanov, Mojca Otonicar, Vincent Loyau, Brahim Dkhil

Journal of Alloys and Compounds -

Materials Science

Great multiferroic properties in BiFeO 3 /BaTiO 3 system with composite-like structure

Multiferroic materials have attracted significant research attention due to their technological potential for applications as multifunctional devices. The scarcity of single-phase multiferroics and their low inherent coupling between multiferroic…

Minghai Yao, Long Cheng, Shenglan Hao, Samir Salmanov, Mojca Otonicar, Frédéric Mazaleyrat, Brahim Dkhil

Applied Physics Letters -

Electric power

A new isolated topology of DC-DC converter based on piezoelectric resonators

This article presents a new isolated topology of dc–dc converter based on piezoelectric resonators. Contrary to most existing topologies, the proposed one uses the natural isolation of piezoelectric resonators to isolate the converter's output from…

Valentin Breton, Emile Bigot, Ghislain Despesse, François Costa

IEEE Transactions on Power Electronics -