Multiple sclerosis (MS) patients often present hyper-intense T2-w lesions in the spinal cord. The severe imbalance between background and lesion classes poses a major challenge to Deep Learning segmentation approaches, requiring for ad hoc strategies. Careful selection of the loss function and adjustment of the conventional 0.5-thresholding may hel...
Object pre-localization from computer-generated holograms is still an open problem in the current state of the art. In this work, we propose the use of the hologram phase space representation to determine a set of regions of interest where the searched object can be located. The extracted regions can be used to pre-locate the object in 3D space and...
SUMMARY In the recent years, the seismological community has adopted deep learning (DL) models for many diverse tasks such as discrimination and classification of seismic events, identification of P- and S-phase wave arrivals or earthquake early warning systems. Numerous models recently developed are showing high accuracy values, and it has been at...
La réverbération artificielle consiste à ajouter à un signal sonore un effet qui émule les phénomènes de réverbération acoustique d’un espace. Cette technique est une composante essentielle dans les domaines de la production audiovisuelle, de la réalité virtuelle, ou des jeux vidéo, puisqu’elle contribue à la création d'un espace sonore convaincant...
Glazed ceramics are a common material analyzed through geochemistry, whether in the form of tableware collected during excavations or tiles observed as part of architectural features. Within the framework of these studies, measuring the thickness of the transparent glaze is one of the useful variables available for the characterization of the ceram...
This work explores the use of constant-Q transform based modulation spectral features (CQT-MSF) for speech emotion recognition (SER). The human perception and analysis of sound comprise of two important cognitive parts: early auditory analysis and cortex-based processing. The early auditory analysis considers spectrogram-based representation wherea...
Purpose: To evaluate the benefits of SPARKLING, a stochastic k-space sampling approach over the deterministic sampling scheme TPI (Twisted Projection Imaging) in the context of accelerated cerebral $^{23}$Na MRI and assessing its impact on tissue sodium concentration (TSC) estimation.Methods: Guided by simulation results, in vitro and in vitro UTE ...
Published in Sensors (Basel, Switzerland)
For a task-oriented dialogue system to provide appropriate answers to and services for users' questions, it is necessary for it to be able to utilize knowledge related to the topic of the conversation. Therefore, the system should be able to select the most appropriate knowledge snippet from the knowledge base, where external unstructured knowledge...
Imaging the structure of major fault zones is essential for our understanding of crustal deformations and their implications on seismic hazards. Investigating such complex regions presents several issues, including the variation of seismic velocity due to the diversity of geological units and the cumulative damage caused by earthquakes. Conventiona...
Recovering the scene depth map from a computer-generated hologram is a problem that remains unsolved, despite the growing interest in the subject. In this article, we propose to study the application of depth-from-focus (DFF) methods to retrieve the depth information from the hologram. We discuss the different hyperparameters that are required for ...
