Software Bug Detection using Federated Learning Models: A Comparative Study

This research aims to advance the field of federated learning by addressing privacy, domain shifts, and personalization challenges, particularly in the context of mobile and digital healthcare. By developing robust and scalable solutions, the proposed framework has the potential to significantly enhance patient care, diagnostics, and personalized treatment while maintaining stringent privacy standards

Read More
Cooperative Real-Time Direct-to- Satellite IoT Connectivity

This research project aims to establish cost-effective and reliable internet connectivity for critical applications in remote areas through Low Earth Orbit (LEO) satellites, leveraging innovative cooperative resource-sharing and optimization techniques to improve connectivity and response times.

Read More
Édition critique numérique de la Sylloge Parisina

Ce projet de recherche porte sur la Sylloge Parisina, une collection (dite « mineure ») d’épigrammes grecques – ces courts poèmes conçus à l’origine pour être gravés sur des tombes, des objets ou des monuments. Conservée dans un manuscrit du XIIe-XIIIe siècle (le Parisinus supplementum graecum 352), la Sylloge Parisina regroupe 115 épigrammes et offre des éléments […]

Read More
CMQuébec : Segmentation sémantique d’infrastructures sur images aériennes

La Communauté Métropolitaine de Québec (CMQuébec) a pour mission de coordonner le développement de la région métropolitaine en matière d’aménagement du territoire, d’environnement, de transport et mobilité, d’économie, et de gestion des risques naturels. La CMQuébec fournit également des services de production de données géospatiales de haute qualité générées par l’intelligence artificielle (segmentation, classification, etc.) […]

Read More
Enhancing User Interaction in VR Striking Sport Games through Haptic Feedback and Visual Immersion

Our project addresses challenges in VR striking sports games, where the lack of accurate physical feedback limits VR’s ability to promote physical activity. Building on an existing NAIST project, we propose to enhance their haptic device into a sport-universal tool that improves realism and immersion by replicating real-world sports interactions (e.g., striking a ball) across […]

Read More
Bentley : Découpage intelligent de plans d’ingénierie

Le design de grands projets de génie civil (routes, ponts, complexes résidentiels, usines, etc.) requiert plusieurs décisions techniques dont les résultats sont consignés dans divers types de plans d’ingénierie. Tout projet d’envergure ne peut être imprimé/affiché sur une seule feuille, même de grand format en raison de l’étendue du projet et de la quantité d’informations […]

Read More
Distributed Quantum Algorithms

Quantum advantages designate situations where processing qubits of information solves a task significantly more efficiently than processing classical bits of information in some basic abstract scenario. Our understanding of quantum advantages for distributed computing is limited. In particular, it is not well understood whether quantum information can deal with issues inherent to networks such as […]

Read More
Enhancing Wildfire Detection and Prediction with Deep Learning and Quantum Machine Learning

Wildland fires in Canada pose significant risks, causing extensive damage to ecosystems, property, and human life. The record-breaking 2023 wildfire season, which devastated 18 million hectares, underscores the urgent need for improved detection and mitigation strategies. Recent advancements in deep learning have demonstrated strong potential in early wildfire detection and fire spread prediction, providing critical […]

Read More
Integrating Shape Grammar and Transformer Architectures for Automated Text-to-BRep Conversion in Design Automation

This project aims to create a system that can turn simple text descriptions of designs into detailed 3D models automatically. By combining shape grammar rules (which act like guidelines for building shapes) with advanced language-processing AI models called transformers, the system will understand natural language inputs and generate precise 3D representations known as Boundary Representation […]

Read More
RTL Implemetation of an HDC accelerator

This project aims to develop an RTL model for a programmable accelerator for hyperdimensional computing (HDC), a brain-inspired approach that uses high-dimensional vectors for data processing. HDC is particularly suitable for resource-constrained environments because it avoids complex matrix multiplications, relying instead on efficient bitwise operations that can be implemented on hardware like FPGAs or ASICs. […]

Read More