L2M–SOASIS

Mental health remains a significant concern in North America, youth mental health is a particular focus due to academic pressure, social media use, and bullying. SOASIS offers a physical meditation pod and a cellphone application for users to take a short break or customized self care experience, combining AI technology to simulate a holistic user-friendly […]

Read More
Impact assessment of delineated management zones and variable nitrogen application rates in potato production using artificial intelligence techniques

Prince Edward Island (PEI) potato production represents 23% of the total production in Canada, contributes 6.6% in the local provincial economy, therefore maintaining higher potato yield is the main goal of local farmers. This can be achieved through proper management practices including nutrients supply such as nitrogen. Nitrogen (N) is the one of the most […]

Read More
“Improving Flexural Strength Predictions in Composite Materials using Image Processing and Machine Learning”

This project aims to improve the way we assess the strength of short fiber reinforced composites, focusing on sustainability. By exploiting the distinct visibility traits of PEEK and carbon fibers in CT scans, the study will utilize non-destructive testing and computer algorithms to analyze and measure factors critical to the material’s strength directly from scan […]

Read More
Development of Strategic Market Assessment Tools for Materials R&D

Chemia Discovery is a company that specializes in the research and development of new materials that can enhance the performance and sustainability of various technologies and enable emergent technologies. Chief among the materials explored at Chemia are those with applications for waste heat recovery and carbon capture. Chemia evaluates potential material R&D projects based on […]

Read More
Development of State-Space Models for Predicting Insurance Risk of Accidents in Autonomous Vehicles Based on Telematics Data and Improvements to Existing Modeling Approaches

The development of autonomous vehicles and telematics is transforming the auto insurance sector. Reports highlight Tesla’s insurance ventures predicting a significant revenue share. This shift is underpinned by telematics, which offers detailed insights into driving behaviors and vehicle usage, essential for autonomous vehicle insurance risk assessments and pricing. The research in this domain, especially in […]

Read More
Utilisation de l’apprentissage machine dans les pompes à chaleur à hautes températures pour la prévision et l’optimisation des coûts énergétiques, de la performance et de l’efficacité exergétique

Les pompes à chaleur à haute température (PACHT) peuvent répondre à la demande thermique de diverses applications. Elles peuvent être utilisées pour des applications résidentielles, commerciales et industrielles et fournir à la fois le chauffage et l’eau chaude. Selon le site officiel du gouvernement du Canada, les thermopompes sont une technologie éprouvée et fiable au […]

Read More
Studying weak-to-strong-generalisation using influence functions

A crucial reason that it is possible to train ML systems to outperform human experts in narrow domains such as protein folding or chess, is because for these well-defined problems, it is easy to produce a reliable reward signal. However, current techniques for aligning frontier models with human goals, such as human feedback, are only […]

Read More
Development of the Neural Network-Based Index Insurance : A Focus on Climate Change Risk Management

This project focuses on enhancing agricultural resilience to climate change by incorporating neural network-based optimization into weather index insurance designs. By utilizing advanced machine learning techniques, the initiative aims to improve the accuracy and appeal of insurance products for the agricultural sector, which is highly vulnerable to climate-induced weather unpredictability. The collaboration involves academia and […]

Read More
Predicting Material Properties from Electronic Band Structures: Integrating Machine Learning with Computational Modeling Techniques

The project involves the development of a machine learning model which can predict targeted properties of materials from their band structure. Computational modeling methods, such as ab initio (quantum chemistry) calculations, Density Functional Theory and Molecular Dynamics, enable us to calculate properties of materials from their crystalline structure. The band structure is a representation of […]

Read More