Projets novateurs réalisés

Africentric Learning Design: Socio-culturally Sensitive and AI-driven Virtual Learning Platform to Support African Canadians

The school closures due to COVID-19 accompanied with the change to remote learning had further exacerbated disparities in the already existing achievement gaps of African Nova Scotian learners in Canada. We propose a technology innovation to be co-developed with the African Nova Scotian community and teachers, offers flexibility in delivery, with content and pedagogical approaches linked to local resources, integrated with social and cultural presence consistent with African worldviews. The proposed study employs a co-design approach along with the relatively untapped machine learning (ML) capabilities to develop a smart socio-culturally sensitivity e-learning system that adapts to each learner’s state via dynamic ablation experiments to discover and implement a personalized learning experience and learner’s engagement using various persuasive strategies. The study would engage the Nova Scotia Black community in participatory action research to co-develop the e-learning system consistent with their social and cultural practices. Our project partner Delmore “Buddy” Daye Learning Institute is an Africentric Institution committed to facilitating educational change and genuine opportunities for learners and communities of African ancestry to reach their full potential.

Des phytotechnologies aux jardins de biodiversité

L’objectif du projet présenté ici est d’établir le potentiel d’utilisation de plantes indigènes et de leur combinaison face à la décontamination du triclosan au sein d’infrastructures phytotechnologiques innovatrices ; des marais filtrants intégrés aux paysages québécois. Pour ce faire, des marais en mésocosmes seront mis en place en fonction de la diversité, de la capacité de remédiation et de l’esthétisme. Au cours de ce stage qui s’inscrit dans un projet plus large, l’etudiante de M2 aura pour tâche d’installer les unités expérimentales plantées d’espèces uniques. Le potentiel de survie de ces espèces indigènes en contexte de marais filtrant sera alors évalué ainsi que leur potentiel de décontamination.

Tokamak Dust Studies Collaboration (STOR-M and WEST)

A fusion reactor is a device capable of producing even more power than a fission reactor, with carbon free emissions and no long lived radioactive waste. No fusion reactor exists as of yet, though the tokamak design is a promising candidate. The goal of a modern tokamak is to produce a fourth state of matter, known as a plasma. Subsequently, the plasma must be contained and heated in order to generate excess heat from fusion reactions occurring within the plasma. Understanding how this hot plasma interacts with its container is a critical step in designing a fusion reactor. At the WEST tokamak facility and PIIM laboratory at Aix-Marseille University, the intern will analyze various micro and nanoparticles (dust) produced by plasma interactions with the tokamak wall, in order to better understand their erosion, deposition and structure. In addition, the intern will work on tracking simulations of dust particle dynamics is the WEST tokamak.

Application of Head-Mounted Devices to identify corrosion damage present on sub-sea assets on a 3D digital reconstruction application.

In this project our goal is to facilitate the 3D reconstruction of assets that are found in the ocean bed for the purpose of monitoring the state of the asset, especially to assess whether there is corrosion or cracks in the equipment. Using high-quality subsea imaging, we can obtain images of assets that can be visually inspected for corrosion and cracks. A 3D reconstruction of the asset would be a valuable tool to communicate the location of the detected regions of interest, as the 3D model can be tagged with positional markers that indicate the exact location of the damaged regions. In this project, we will produce a prototype system that combines 3D reconstruction of the environment and the virtual reconstruction using HMD’s, letting a human observer adjust and manipulate the scene using interactive VR widgets. An inspector will be able to more thoroughly and precisely examine the hard-to-reach spots that are not visible at the first glance. The research problem of this project is to examine, from a set of three different implementations, which of the proposed solutions proves useful, robust, practical and overall the most convenient to use, based on the results of user study.

Cholinergic bioactives from cereals

Cholinergic compounds can act as both pharmaceuticals and bioactive compounds in functional foods. Alpha-Glycerylphosphoryl choline (alpha-GPC) is a known cholinergic compound that is used in Korea as a prescription pharmaceutical for treatment of Alzheimer’s disease. However, development as a functional food and related researches in Korea is limited. Recently, the team led by Dr. Martin Reaney has reported that cereal grains can be processed by enzyme treatments and fermentation to produce concentrates that are highly enriched in alpha-GPC. Our proposal is to produce an alcohol free concentrate beverage base that is rich in GPC in Canada. This will be used for testing of its in vitro efficacy in BV2 murine microglial cells using MTT assay. RNA and protein expressions of neuro-inflammatory factors and pathways will be measured by RT-PCR and Western blotting, respectively. In the mouse model, behavioral experiments and acetylcholine content will be tested. Through this collaboration, home university member could learn how to demonstrate the functionality of alpha-GPC in Alzheimer’s disease, and host university members could explore ways to develop it as a functional food in Korea.

Architected materials design using quasi-periodic homogenization

Architected materials are those which have a designed microscopic structure or “microstructure”. They of exhibit material
properties which are not attainable by conventional materials. One important field of application for these materials is bone
biomechanics, in which the search for suitable bone biosubstitutes is of high scientific and clinical importance. For example,
architected materials are well-suited for the manufacture of bone-scaffolds, which are designed to promote bone regeneration
following surgery by providing support for growing bone. In this project, we intend to develop a mathematical model of a specific
microstructure design, test the model through simulation and experiment, and develop techniques to predict the material
properties of similar designs based on more easily understood examples.

Geophysical detection of microplastics in soils

Plastics pollution is a global environmental hazard with a wide range of impacts on wildlife, biodiversity, food webs, ecosystem
services and human wellbeing. Of particular concern are microplastics (including nanoplastics) because their small sizes enhance
their long-range transport, their uptake by biota and the capacity to sorb and leach contaminants. The proposed project will focus
on the fate of microplastics in soils. Agricultural soils treated with biosolids have been shown to contain large amounts of
microplastics, yet how these microplastics move through the soil environment is hardly known. We will apply a novel, and likely
game-changing, approach to the detection and real-time monitoring of microplastics in the soil environment, by applying a noninvasive
geophysical remote sensing technique known as Spectral Induced Polarization (SIP). While SIP has been used to follow
the transport of engineered nanomaterials through soils, it has never been applied to microplastics. In the proposed project we will
acquire and analyze SIP signatures associated with the movement and immobilization of microplastics in soil column experiments.
The results will lay the groundwork for the systematic investigation of the interactions between microplastics and the abiotic and
biotic components of soils.

Visual Anomaly Detection and Applications in Product Quality Assessment

Currently, most small or medium manufacturers inspect products or parts’ visual quality manually. The manual visual quality inspection is error prone, subjective, and labor intensive. In recent years, image-based automated
inspection has seen exciting uptakes in many modern factories. One critical challenge that limits their vast potentials lies in its ability to detect anomalous situations and events that usually involve product defects in
manufacturing processes – the central theme of our proposed project. In particular, we list the following key objectives: 1) learning anomaly detection with positive instances; 2) unsupervised learning anomaly detection;
3) a practical pipeline of visual anomaly detection, with a focus on in metal bottle manufacture. Our research program aims to address these fundamental and practical challenges, as well as to make practical impact in
real-world applications.

Developing a Sensitive and Quantitative Opioid Detector for Use in a Clinical Setting

The opioid epidemic is a serious health crisis in Canada, North America, and globally and has worsened during the COVID pandemic. Opioid treatment strategies are at the forefront of efforts to tackle this crisis. To improve the replacement therapy currently used, an estimate of tolerance is required. This proposal takes an existing proof-of-concept opioid detection device and adapts it for use in the clinical setting to address this challenge. Results from a parallel separately funded pharmacokinetic study to understand the relationship between the opioid level and the patient’s tolerance level. This information will be needed for sensor design and defining performance metrics which will improve the current standard of care.

Data Analytics Models for FreshBooks’ Customers’ Engagement

An organization that can effectively understand its specific customers’ needs will be able to follow the best communication approach and accurately measure engagements. A data-driven framework based on the customer’s digital behavior, historical data, will be developed to identify specific customer segmentation and used to find optimal next best action to enhance customer experience by improved personalized and quantifiable marketing strategies. A deep understanding of user segmentation and corresponding support strategies to enhance customer engagement (based on their providing service/product) is critical for our partner organization. In this project, we
proposed to develop a framework (combined with unsupervised and supervised models) for segmenting customers based on their invoice line-item (i.e., provided product or services). Furthermore, to enhance engagement, we also propose to design an advanced Machine Learning and optimization framework for recommending the next best
action for supporting specific customers on our partner organization’s platform.

Using machine learning to explain the fitness landscape of an enzyme involved in antibiotic resistance

An organism’s genome contains the information necessary for its development. Part of this information is used as “instructions” for
cells to synthesize molecules called proteins, which perform most of the cell’s functions. However, over time, changes to the
genomic information can occur. These changes (mutations) can have all kinds of effects: some might cause diseases, others
confer antibiotic resistance to bacteria. Thus, much work has focused on studying what determines the effects of mutations. We
selected a protein involved in antibiotic resistance and are experimentally testing the effects of all possible mutations on its
sequence to understand the determinants of their effects. We believe these determinants are a combination of several factors:
how much of the protein the cell produces, the type of mutation, etc. Using machine learning and integrating data from several
studies, we aim to identify the underlying patterns and relative importances of each of these factors.

Protic Ionic Liquids as Alternative Electrolytes Enabling Intermediate Temperature Fuel Cell Operation Above 100°C

State-of-the-art polymer electrolyte fuel cells (PEFCs), based on membranes like Nafion© have achieved a mature level of performance and cost reductions. To enable new cell concepts, allowing further steps in cost reduction of the whole fuel cell system in the future, it is vital to maintain a high commitment in research on catalyst and electrolyte materials. An intermediate temperature PEFC would enable a simplified design without water management, more effective cooling, utilization of waste heat and a lower sensitivity against feed gas impurities.

Based on own preliminary studies, protic ionic liquids (PILs) can be identified as promising candidates. At the current stage, we prepare PEFC cells based on PILs on a simple demonstrator cell level which show at first only a very limited performance. For this, the scope of the project is defined as:
-Optimization of the polymer-electrolyte system;
-Improvement of the cell performance;
-Investigation of the membrane degradation.