Integrated multi-omics approach for glycosylation-based breast cancer subtyping

This project will utilise an integrated multi-omics approach for glycosylation-based breast cancer subtype discovery. Glycosylation is the process whereby carbohydrate structures are conjugated to cellular proteins and lipids, and in doing so, determines their functionality. Glycosylation is dysregulated in cancer and incorporating the glycome in cancer research has led to deeper mechanistic insight. Combining glycomic […]

Read More
Affective Automation: A Cross-Cultural Exploration of Emotion in Artificial Intelligence Development

This project explores the emotional and cultural dynamics of artificial intelligence (AI) development across four global sites—Canada, the UK, India, and the US—by examining how emotions shape decision-making, productivity, and well-being within distributed teams. Focusing on the workplace processes of a leading transnational AI firm, the research addresses critical industry challenges in managing intercultural collaboration […]

Read More
Développement d’un Modèle d’Analyse Automatique des Angiographies Coronaires pour la Génération de Rapports Cliniques

L’objectif de cette recherche est de développer un modèle capable d’analyser automatiquement les vidéos d’angiographies coronaires pour générer un rapport textuel contenant la gravité des sténoses ainsi que la fonction du ventricule gauche et du ventricule droit (VG / VD). Ce modèle repose sur l’intégration d’un encodeur vidéo pour extraire des caractéristiques spatio-temporelles, un tokenizer […]

Read More
L2M – Deep Learning-Based Detection and Classification of Biofouling on Marine Surfaces

The maritime industry faces significant challenges from biofouling—the buildup of marine organisms on vessel hulls—which leads to higher fuel costs, increased carbon emissions, and frequent maintenance. Traditionally, biofouling inspections are manual, costly, and time-consuming, offering limited real-time insights. Our project seeks to address these inefficiencies by developing an AI-powered model to automate the detection and […]

Read More
L2M – AI-Powered Real-Time Detection: Revolutionizing Harmful Algae Bloom (HAB) Monitoring

The proposal introduces a cutting-edge, real-time solution for detecting and mitigating harmful algal blooms (HABs) using advanced computer vision and AI models integrated with autonomous systems. By leveraging state-of-the-art AI-powered imaging technology, this solution delivers precise species identification and real-time monitoring capabilities that drastically improve response times. Unlike traditional manual sampling methods, this system utilizes […]

Read More
Building AbilityGPT – A GPT model to create novel biological therapeutics

Antibody therapeutics are a fast-growing class of treatments for many significant unmet medical needs. Ability biologics is a Montréal-based startup company that has significant unique proprietary data, sequences and activities for over 40 targets, for training deep-learning models, combined with laboratory facilities to create and test antibodies proposed by computer models. Ability Biologics will use […]

Read More
An Automatic Approach to Transfer Function Tuning Using Reinforcement Learning

Optimizing an interaction to achieve the highest possible performance is desirable for many applications. For instance, even minor improvements in the mapping between a computer mouse’s movement and a cursor on a screen can significantly enhance comfort and usability. Similarly, better mapping an operator’s joystick inputs to crane movements could boost productivity. Both examples emphasize […]

Read More
Exploring the automation of animal health surveillance through natural language processing: A comparative analysis of supervised and unsupervised approaches for canine gastroenteritis

Canine gastroenteritis is a syndrome characterized by inflammation of the stomach and intestines, resulting in acute onset diarrhea, vomiting, and anorexia. As no prophylactic treatment exists, veterinary health preparedness based on surveillance is a key preventive strategy. We propose a comparative empirical study applying various language modeling approaches to identify gastroenteritis outbreaks in UK dogs […]

Read More
L2M – PoseidonPulse

The proposed project focuses on developing a business and go-to-market strategy for PoseidonPulse, an advanced AI-powered water quality monitoring system designed to improve sustainability and operational efficiency in Canada’s aquaculture industry. By continuously tracking essential water parameters, this system enables aquaculture farms to proactively manage water quality, supporting healthier fish populations and optimized farm performance. […]

Read More
L2M – Integrated 3D Reconstruction and SLAM for precise 3D visualization and localization of underwater assets

Our project integrates AI-driven Simultaneous Localization and Mapping (SLAM) with cutting-edge 3D reconstruction techniques to provide precise localization and high-fidelity 3D visualizations of underwater features. This fusion enables accurate measurement of size, depth, and spatial orientation of anomalies, enhancing inspection precision. By adopting this technology, industries can improve inspection accuracy, streamline maintenance, and reduce operational […]

Read More