Projets novateurs réalisés

Stratégie de livraison le jour même dans l’industrie du commerce de détail

The research will focus on understanding how same-day delivery courier companies can collaborate with retailers in order to form a mutually beneficial option for the end consumer. It will focus on choosing retailers that can have such service incorporated into their current operations. The challenges, risks, and considerations of the transition will be analyzed to help all parties involved. Ultimately, the research will validate the market, which will show whether there is a demand for such service.
The research will ensure Novex continues to operate profitably in the future by helping the company understand which retailers they can partner with using Zipments’ online platform, mobile app, and an API in order to help revitalize its growth in the quickly changing courier industry.

Data Amalgamation and Analysis across Agricultural Data Silos

The agriculture industry uses multiple disparate data sources. Examples of these data sources includes different types of sensors like moisture sensors, weather information, intelligent farming equipment like tractors, and grain tracking applications. This project will integrate two data sources into a common hosted platform. Existing software such as Esri, for geospatial data and analytics, PI System for operational data (IoT) to provide situational awareness, and Maximo for asset management and tracking.

While Mera‘s partners in the agricultural industry have outlined numerous specific needs that are often siloed and are difficult to integrate, this project will look specifically at the initial creation of a central system to consolidate data and provide a user interface to view this data. We will be taking two data sources and integrating them into a central storage solution. These data sources are being identified as part of an in progress NSERC Engage grant and they will be selected prior to the interns starting.

Développement du dialogue entre les perspectives scientifiques et autochtones sur la forêt boréale

Les Premières Nations sont de plus en plus impliquées dans les projets de recherche qui touchent leur territoire. Or, le développement de compétences en recherche en sciences naturelles au sein des communautés est nécessaire pour assurer une collaboration équitable et harmonieuse avec les institutions de recherche. La recherche proposée sera menée par la Première Nation Abitibiwinni, en partenariat avec l’Institut national de la recherche scientifique et Ressources naturelles Canada. Elle se décline en trois parties. Un premier volet vise à documenter la biodiversité dans le bassin versant de la Rivière Harricana depuis les perspectives autochtones et scientifiques, à partir de l’ADN environnemental contenu dans des échantillons d’eau. Le second volet porte sur la conciliation des valeurs pour la conservation du caribou forestier en contexte autochtone. Il vise à documenter les critères et valeurs des différentes parties-prenantes de l’aménagement du territoire et à développer des outils pour faciliter la prise en compte des enjeux autochtones. Le troisième volet s’attarde à la mobilisation des savoirs développés par la communauté dans ses différents partenariats de recherche. L’objectif est de développer du matériel pédagogique en sciences naturelles destiné aux élèves des écoles des communautés autochtones du Québec et du Canada.

Atmospheric water harvesting with carbon nanoporous sponges

Water scarcity threatens more and more people in the world. Cape Town (South Africa) imposed strict water restrictions in 2018 in response to shortages. Closer to home, water restrictions were put into place in Quebec in the summer of 2020, and First Nation communities have been confronted with fresh water issues for years. Water scarcity is a worldwide issue amplified by climate change, even in Canada. Alternate water sources, including atmospheric water harvesting, are required to secure a fresh water supply. Nanoporous sponges (NPS) are new carbon-based water harvesting material synthesized via the pyrolysis of low-cost materials, achieving comparable performance to metal organic framework (MOF) based systems, but at significantly lower cost. This material was developed at Polytechnique Montreal, in partnership with McGill University and Awn Nanotech, via a collaboration started in 2017. This research project aims to bridge the gap between lab scale prototyping and commercial uptake. We aim to: (1) Create a roadmap for NPS production at large scale; (2) Identify the key parameters impacting water capture and subsequent release through modelling and experimental validation; and (3) Fabricate and test water capture prototypes based on NPS technology and benchmark them against other adsorbents.

Using Phase Field Modelling and Machine Learning to Develop a Microstructure Design Platform for Hydraulic Turbine Steels

Materials fatigue has a detrimental impact upon the lifetime and cost-effectiveness of turbine equipment in Hydro-Québec’s energy production division. Metal fatigue, in turn, is linked to it internal microstructure, that developed in a metal during its fabrication or repair through welding, as is often done to damaged hydroelectric turbine blades that break during operation. The ability to efficiently and accurately predict the evolution of said microstructure is thus key to optimizing turbine blade performance. This project will develop and ultimately combine two state-of-the art computational approaches to develop a tool that can id Hydro-Québec to predictively design repair strategies of optimal turbine performance. The first will be a multi-physics model, called a phase field (PF) model, that can predict realistic solidification microstructures in steel. The second is a machine learning (ML) algorithm that will be trained from PF data to rapidly predict the evolution of microstructure from partial knowledge of initial conditions and processing environment. The first model will be used to investigate strategies for optimal microstructure design in turbine blade welding of austenitic and ferritic steels. The machine learning algorithm will be used to improve the PF model’s predictive potential over longer intervals of welding time.

Line of Business Explainability

Current planning/business analytics platforms automate time-consuming manual budgeting, forecasting, and reporting processes to help business users (e.g., financial officer, human resources, merchandising, marketing, or sales) make business decisions. Moreover, end users often use the interactive “what-if” analyses to understand the data from different perspectives and gain insights. However, the current way of presenting the analysis results has limitations, which only reactively responds to end users’ requests and requires sufficient knowledge on the part of the business users. In this research project, we would like to design and develop an involuntary analytics system that proactively provides suggestions for end users to look into different perspectives of the data, highlight a subset of the data that might be anomalous and worth further investigation, and generate transparent, accountable, and trustworthy explanations for the results of the analysis using terminology that makes sense to business users. In this research project, we will study how to improve the explainability of business analysis results and make it possible for almost anyone (regardless of skill level) to pinpoint business problems and make informed business decisions. The main outcomes will include the design and development of an involuntary analysis infrastructure that enhances business analytics.

Design of Prefabricated Exterior Wall Panels for Robotic Building Retrofit

Retrofitting aging commercial buildings from the exterior using wall panels can increase their sustainability and energy efficiency. The partner, RoBIM Technologies Inc., is developing an end-to-end automated solution by using robotic technologies and introducing more energy efficiency materials into the panel design. The combination of robotic prefabrication and sustainability of engineered wood products (EWPs) are well matched with the goals of greening Alberta’s construction industry and reducing carbon emissions from buildings. The purpose of this research is to develop a new EWP-based exterior wall panel system for commercial building retrofits from perspectives of structural integrity, thermal efficiency, robotic constructability. The outcome of this research will provide Alberta’s building industry with an example of robot-constructable panel system will facilitate future adoptions of the integration of EWPs and robotic technologies in building retrofits.

Defocus and Aberration Modeling for RGBInfrared Cameras

Conventional camera sensors record three color channels: red, green and blue. In this project we will investigate computational photography algorithms for cameras that record a near-infrared channel (NIR) in addition to RGB. This channel is particularly useful for biometric imaging and holds great potential in consumer imaging applications as well. The key challenge in simultaneously capturing RGB and NIR is that lens behavior depends on wavelenth and thus the NIR channel may be defocused compared to the other three. Our aim will be to study this lens behavior in detail and propose demosaicing/deblurring algorithms for high-quality RGB-NIR photography. To validate our image formation models and algorithms we will use an RGB-NIR prototype camera developed by Qualcomm as our experimental testbed

Impact d’une intervention virtuelle favorisant de saines habitudes d’activité physique et alimentaires chez des femmes ayant été atteintes d’un cancer du sein.

Ce projet vise le développement d’un programme de promotion de saines habitudes d’activité physique et alimentaires chez des femmes ayant été atteintes d’un cancer du sein. L’intervention impliquera deux approches, l’une virtuelle et l’autre en présentiel, qui sollicitera la collaboration entre le médecin de famille, le kinésiologue, le nutritionniste et le patient. Deux groupes de médecine familiale universitaire (GMF-U) de la région de Lanaudière et de Québec seront impliqués et prendront chacun en charge 40 participantes qui seront aléatoirement classées dans l’une ou l’autre des deux interventions. Dans ce projet, la kinésiologue et la nutritionniste sont des professionnelles certifiées qui sont également inscrites à des études graduées à l’Université Laval. Cette implication contribuera à leur formation clinique et scientifique. Pour ce qui est du partenaire externe, soit la Fondation cancer du sein du Québec, cette collaboration représente une opportunité unique de bonifier ses activités de promotion de saines habitudes de vie.

Artificial Intelligence and Unsolved Historical Homicides

We have initiated what we hope is a long-term collaboration between University of Alberta (Randy Goebel, Amii/Computing Science) and Edmonton Police Service (Brian Rector), to investigate and develop the application of AI methods to aid in the solution of long-term unsolved homicides (“cold cases”). The initial idea is focused on AI methods for information extraction from historical cold cases. Cold case files are dossiers of a broad collection of data, including paper documents, photographs, DNA evidence, witness reports, records of temporal events, confirmation of relationships and interactions amongst individuals, even video and voice documents.
The initial idea is to use AI methods to create abstractions of the relationships amongst cold case files. For example, methods from Natural Language Processing (NLP) tools can be used to summarize the relationship between all named individuals and all temporal events in a cold case dossier, with the hope that making these relationships explicit can aid the cold case experts in developing new leads to help solve a case.

Metal-organic framework-based electrodes for CO2 capture and conversion

The world’s stringent need to transition to a low-carbon industrial economy is more pressing than ever. It is imperative to innovate, develop, and implement revolutionary technologies that use low-carbon-intensity energy generation sources and have an intrinsic negative GHG emission factor while being economically profitable. The electrochemical carbon dioxide reduction to fuels and chemicals coupled with renewable electricity sources is one of the most promising technologies that could enable the decarbonization of heavy industries such as cement and steel manufacturing. In this context, Metal-Organic Frameworks (MOF) are promising and cost-effective advanced materials for CO2 capture and conversion due to their exceptionally customizable porous structure using a variety of molecular building blocks. The focus of the proposed project is on developing active and stable bi- and tri-metallic metal-organic framework materials for CO2 capture and conversion employing fundamental electrochemical methods, experimentally validated models and structural characterization techniques. The developed materials can be integrated into Agora’s CO2-based redox flow battery technology, enhancing its charge cycle with the added benefit of using unpurified flue gas in the system.

Design and development of a novel bioink for HeartPrint

Cardiovascular disease is one of the world’s leading causes of mortality. However, due to a scarcity of heart donors, new cardiac regenerative medicine sources are desperately needed. The increasing use of biomaterials in tissue engineering has created a direct and promising platform. However, technical advancements are still needed to properly create a heart structure with complete biological function. 3D bioprinting technique for tissue engineering has demonstrated significant benefits in the creation of micro-scale heart tissues, demonstrating its promise as a novel foundation for cardiovascular regeneration. This project will develop HeartPrint – a novel bioink for generating human cardiac tissue models