Projets novateurs réalisés

Développement d’outils de formation destinés aux producteurs agricoles sur les risques à la santé et les moyens de prévention des risques associés aux phénomènes climatiques extrêmes

Ce projet vise à développer des outils de formation sur les risques à la santé et les mesures de prévention prometteuses à l’intention des producteurs agricoles et des intervenants en santé au travail. Les risques à la santé considérés dans ce projet sont de diverses natures : physiques, chimiques, biologiques et psychosociaux. Pour la réalisation de ce projet de recherche, des outils seront développés à partir d’une recension des écrits scientifiques. L’exploitation des scénarios climatiques régionaux servira à identifier les risques les plus fréquents à survenir et la consultation des parties prenantes du milieu agricole permettra de valider les résultats et les outils développés.

L2M-Shipping rate forecasting using deep learning solutions

In the complex and ever-evolving realm of shipping investments and operations, informed decision-making stands
as a cornerstone of success. Within Soshianest Inc., the primary focus lies in providing precise and reliable
freight rate forecasts. Through the utilization of state-of-the-art AI models, the company aims to enhance
shipping strategies, enable data-driven decision-making, and adeptly maneuver through market variations with
assurance .

Our objective is to implement advanced Time Series Forecasting (TSF) methodologies to forecast shipping rates
within the dynamic shipping markets. Leveraging historical shipping feature datasets and supplementary
resources such as up-to-date economic news, our goal is to meticulously analyze the historical trends and
harness generative AI techniques to achieve precise and reliable predictions of shipping freight rates.

A critical gap in our project lies in the limited interaction with individuals employed in maritime-related enterprises.
This absence necessitates the formulation of various assumptions to address issues such as missing data.
Leveraging this invaluable wellspring of firsthand experience, rooted in human interactions with the available
data, has the potential to introduce significant value and enhancements to the framework’s design.

L2M-Sustainable Wastepaper Cushioning Foam and its Commercialization

We propose the development and commercialization of biodegradable wastepaper foam as a viable alternative to traditional synthetic materials. Our solution aims to address the environmental challenges posed by non-biodegradable packaging materials while providing effective cushioning protection for a wide range of products, spanning from lightweight to heavyweight products.

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 uniques pour comprendre la transmission de certains poèmes. Lucia Floridi (Université de Bologne), experte en épigrammatique grecque, a produit une édition critique de ce texte, c’est-à-dire une version établie après une analyse comparative des manuscrits, accompagnée d’une traduction en italien.

Le projet vise à réaliser une édition double format : un livre imprimé et une version numérique interactive, enrichie d’une traduction française des épigrammes. Pour cela, des outils spécialisés comme LaTeX (un système de composition de documents), Ekdosis (un paquet LaTeX adapté à l’édition critique), XML-TEI (un format structurant les textes pour des usages numériques) et XSLT (des feuilles de style transformant le XML en pages HTML) seront utilisés. La version numérique intégrera des visualisations interactives, comme l’affichage des images du manuscrit ou personnalisation de l’affichage des variantes textuelles.

Ce travail sera publié aux Presses universitaires de Rouen et du Havre fin 2025.

Dermoscopy Imaging and automated analysis for skin cancer screening

The research focuses on development and implementation of advanced software algorithms designed for the automated analysis of skin lesion images. The algorithms will be designed to run on mobile computing devices such as smartphones and tablets, and could be used by the general users as well as doctors for computer-assisted screening and diagnosis of skin cancer. For users, our computer program will automatically compute the risk score for skin lesions based on the previously diagnosed cases, and for doctors, it will use machine learning to assist in making the best diagnostic decision. This technology offers many benefits that include skin cancer prevention by self-screening, increased access to dermatologic services, and potential reduction in healthcare costs in Canada. It improves access to specialist services, and enables more efficient healthcare service delivery, particularly for people living in remote areas where skin specialists may be unavailable.

Mortiers à retrait compensé avec des sables de recyclage

Afin de limiter l’impact environnemental de l’industrie de la construction, le recyclage des bétons sous forme de granulats recyclés pour la production de nouveau béton est une pratique de plus en plus courante. Néanmoins, il n’existe pas de marché pour les particules les plus fines, notamment en raison des réglementations strictes en vigueur. L’option proposée ici vise à étudier la possibilité d’utiliser des sables de recyclage dans la composition de mortiers avec agents compensateurs de retrait. Le travail consistera en l’étude de l’influence de ces sables sur l’effet des agents (chaux, magnésie ou C3A) au travers de mesures de retrait (endogène et de séchage) mais aussi :
• Caractérisation physico-mécanique des fines de recyclage ;
• Réalisation de mélanges (mortiers) et évaluation des retraits et des propriétés rhéologiques ;
• Mesures des propriétés mécaniques à échéances.

QuantumOptics

The project focuses on enhancing optical imaging using quantum sensing and optical neural networks (ONNs). Prof. Lvovsky’s research group uses a method called Spatial Demultiplexing (SpaDe), which breaks light into Hermite-Gaussian (HG) modes. By measuring these modes, we can acheive better image resolution than traditional methods allow. The challenge is that experimental setups can have imperfections. To overcome those imperfections, a neural network will be used. By training it, we can adjust for errors and optimize the imaging process.

L’O-GlcNAcylation est un régulateur clé dans la survie des nourrissons souffrant d’une malformation cardiaque congénitale

Intérêt de la recherche : L’oxygène est un élément essentiel à la vie et au bon développement des organes, cependant certains enfants, présentant une malformation cardiaque congénitale appelée tétralogie de Fallot, ont un faible taux d’oxygène dans leur sang (hypoxie) et malgré cela, survivent. Le but de ce projet est de mieux comprendre les mécanismes qui expliquent cette survie. Objectifs : Evaluer à l’échelle de la cellule, l’effet d’une modification post-traductionnelle (hyper O-GlcNAcylation) sur l’adaptation à un manque en oxygène. Pour cela, nous validerons la technique d’isolement de cellules cardiaques à partir de résections cardiaques chez des enfants présentant une saturation en oxygène basse et ceux n’en présentant pas. Puis, nous évaluerons l’impact de cette modification post-traductionnelle sur la fonction des cellules cardiaques. Bénéfices attendus : Grâce à ces analyses, le développement d’un traitement pharmacologique pour cibler un senseur métabolique impliqué dans ces mécanismes de survie sera développé afin d’améliorer la prise en charge de ces patients et permettra également, de mieux comprendre le remodelage cardiaque.

Advanced Auditory Brain–Computer Interfaces for Enhanced Speech Therapy in Children with Developmental Language Disorders

Developmental language disorders (DLDs) are among the most common early-childhood disorders, affecting between 8-12% of children worldwide. If left untreated, DLD can lead to significant professional and interpersonal difficulties later in life. While speech therapy is highly effective, the barrier-to-access is high with regards to cost, availability of speech therapists, and the delay between detection and intervention. There is therefore a significant unmet clinical need for the development of novel, easy-to-deploy interventions to alleviate the disease burden of DLD on healthcare and educational institutions, while maintaining a high standard of compassionate and personalized care. Leveraging advances in large language models (LLMs), it is possible to partially automate the delivery of auditory stimuli that caters to the individual deficits for each child, in the form of custom-made audiobooks. The efficacy of this proposed therapy will be examined by tracking the neural signatures of good speech perception using a non-invasive magnetoencephalography-based brain-computer interface. Furthermore, subjects will receive real-time neurofeedback in the form of gamified rewards on their performance (animated gold stars, points counter) while listening to these audiobooks, to enhance motivation and task engagement, with the goal of improving the efficacy of the therapy.

Development of a Versatile 3-Degree-of-Freedom Seamless Welding System for Helmet Pads and Wearable Protective Gear

The proposed research focuses on developing a welding system that can be used to create helmet pads and other protective gear, like knee and shin pads. This system will use ultrasonic welding or soldering techniques, making the process more efficient than current methods. The goal is to reduce the time and labour involved in manufacturing while improving the quality of the final products. By creating a flexible welding system, both home and industrial manufacturers can benefit. The partner organization will gain a cutting-edge solution to improve its production process, making it more cost-effective and scalable for different types of protective gear.

Quantitative Digital Pathology Algorithm for an Automated Cancer Slide Imaging System

Digital Pathology provides a great reliable source for cancer diagnosis; however, this relatively new technique lacks an appropriate method of regulation and standardization. As a result the information obtained from cancer imaging system might suffer from inconsistency of the results (repeatability and reproducibility issues). Working with the BC Cancer Research Center, Logipath Medical Inc. has developed a number of quantitative pathology systems some of which have been spun off to commercial entities. However the wide spread use of these systems is hampered by the cost of the specialized instruments and experts needed to calibrate the imaging system .The proposed project will alleviate this problem and will be translated into industry programs to use images acquired from readily available WSS that already exist in many clinical pathology laboratories

L2M-Market Evaluation and Commercialization Strategy for APOBEC3-Targeted Therapies in Oncology

This project aims to assist a partner organization in evaluating the market potential of a novel APOBEC3 inhibitor as a cancer treatment. The focus will be on conducting comprehensive market research to understand the demand for this innovative therapy, explore its commercial viability, and identify potential partners in the biopharmaceutical industry. The project will assess the competitive landscape by analyzing existing therapies and identifying opportunities for differentiation, positioning the APOBEC3 inhibitor as a unique and valuable solution in oncology.
One key aspect of the project is identifying potential commercial partners, such as pharmaceutical companies, biotech firms, and investors, who may be interested in licensing or co-developing the APOBEC3 inhibitor. Additionally, the project will evaluate various business models, revenue generation opportunities, and market access strategies to ensure the therapy’s successful commercialization. This will include assessing the regulatory landscape, identifying key approval requirements, and mapping out pathways for efficient product approval.
The project will also explore the broader economic and healthcare impacts of the APOBEC3 inhibitor, including its potential to reduce healthcare costs and improve patient outcomes compared to existing cancer therapies. This research will contribute to a deeper understanding of how this therapy can meet unmet needs in cancer treatment.
Ultimately, the expected benefit to the partner organization is the creation of a clear and actionable strategy for bringing the APOBEC3 inhibitor to market. This will include identifying key stakeholders, building relationships with potential partners, and refining the product’s positioning in the competitive oncology landscape. The organization will be better equipped to secure funding, attract investments, and navigate the complex commercialization process to successfully introduce the therapy into the market.