Projets novateurs réalisés

Strain Measurement after Martensitic Transformation

This collaborative research project between McMaster University’s Materials Science and Engineering department and Grenoble INP Phelma’s SIMaP laboratory aims to investigate the development of accurate strain measurement techniques using transmission electron microscopy (TEM).

Leveraging AI for Data Characterization and Analysis in a Youth Wellbeing Database in UK

This project aims to characterize and analyze the Community Health Dataset using AI techniques. This dataset, sourced from the Cambridge Community Services Trust, contains electronic health records (EHRs) of 111,317 children and young people aged 0–18 years, covering the period from 2007 to 2021. The significance of this project lies in several key aspects: (1) the large amount of available data, enabling the development of robust models and conclusions; (2) the broad age range of subjects, addressing a gap in research focused on youth mental health beyond student populations or controlled conditions; (3) the substantial number of samples related to diagnosed mental illnesses, such as ADHD and ASD, which remain underrepresented in the literature; and (4) the integration of AI tools to enhance data analysis. This analysis will provide key insights into healthcare system utilization and contribute to a better understanding of youth mental health in the UK, with the potential to apply these findings to similar databases in Canada.

Recommender Systems for Investing

(1) The Desjardins Quantitative Strategies department manages a set of internally developed systematic investment strategies. There are two main products; global equity strategies (developed and emerging countries), as well as alternative strategies using futures on global stock indices, resources, interest rates and currencies. The team owns a proprietary technology platform that has been developed over a period of more than 10 years and is actively used for fund management.
(2) The universe of available financial securities and the amount of financial, economic, social, governance, and environmental data is a big data problem. Identifying relevant factors and data to make optimal investment recommendations under constraints is
computationally intensive. Further, the recommender system should be interpretable or explainable so that it is understood what risk factor contribute to the inclusion or exclusion of a particular investment.
(3) The main benefits, due to its impact on our portfolios and to accelerate the adoption of machine learning approaches internally at Desjardins, would be the construction of a novel stock recommendation system based on fundamental and technical properties of investments, and interactions with the macroeconomic environment or environmental considerations.

Investigating brain blood flow control in pre- and post-menopausal women

This project investigates how menopause influences brain function by comparing blood flow in pre- and post-menopausal women. Estrogen plays a crucial role in protecting the vascular system; however, as women transition through menopause and estrogen levels decline, the risk of diseases such as stroke and vascular dementia increases significantly. I will conduct research at Bangor University, utilizing advanced neuroimaging techniques, including magnetic resonance imaging (MRI), to measure brain blood flow and vascular function in both pre- and post-menopausal women. By combining MRI with established ultrasonography techniques, this study will provide a more comprehensive understanding of how menopause affects brain blood flow control. At Bangor University, I will receive training in gold-standard intracranial imaging methods from Dr. Geoff Coombs, expanding my skill set and enhancing my ability to investigate brain health with greater precision. This work will provide an opportunity to integrate expertise from McMaster University, where I have been studying sex and menstrual cycle phase differences in brain blood flow control using non-invasive ultrasound techniques with Dr. Baraa Al-Khazraji. By combining the strengths of from institutions, this research will foster international collaboration, knowledge exchange, and the development of new interdisciplinary approaches to studying women’s brain health.

Instilling Ecological and Emotional Literacy to Engage Youth in Climate Action

The proposed project aims to develop an illustrated children’s book to educate youth on the importance of climate action, which has become increasingly importance due to the consequences of anthropogenic climate change. This project aims to develop a book that instills ecological and emotional literacy in order to empower youth to take action against climate change by integrating empathy, compassion, and care into their ecological perspectives. This project will include work with youth to help inform how children’s can be best utilized to educate them, as well as the utilization of previous research from The Arctic University of Norway’s ECO_CARE project on how empathy, compassion, and care can be instilled within individuals to be agents of change. This project will benefit both McMaster University and The Arctic University of Norway by exploring how to best educate youth, and therefore aid in developing comprehensive curricula within these institutions. The proposed project would contribute to a generation that takes effective climate action and guides their lives and choices through empathy, and make the institutions global leaders in taking climate action.

Postpartum Mental Health in Japanese Women

By systematically reviewing and analyzing existing literature and data on postpartum mental health in Japanese women, this research project aims to understand the cultural expectations of motherhood and perceptions of mental health on mothers in Japan, and how this may impact the uptake of support and public health interventions in the Japanese context. The research will involve literature review, environmental scan, data examination and analysis, as well as meetings with maternal and mental health experts to guide and inform the study. The goal for this research is to inform specific mental health supporting interventions in Japan, interventions for Japanese immigrants in other countries, or in other countries with similar mental health stigma or cultures. Aside from the immediate research outputs, the aim of this collaboration is to continue to strengthen ties between McMaster University and Niigata University, as well as continuing to foster positive ties between Japan and Canada.

Affordable Housing Analysis

This project is a historical analysis of Federal/Provincial affordable housing agreements signed from 2000 to 2011 and whether the housing stock continued to be rented at affordable rates after the agreements expired. Federal/provincial housing agreements during the 2000-2011 period primarily consisted of capital grants to the private sector (for profit and non-profit) to develop affordable rental housing. Affordable was broadly defined as “median market or below”. Grant recipients signed agreements with the Province which required that rents remained affordable for 20 years. Many of these agreements have now expired.

For this project the priority for West Central Women’s Resource Centre (WCWRC) and Right to Housing (RTH) is to ascertain whether any of the housing units previously funded through Federal/Provincial affordable housing agreements between 2000 and 2011 continue to rent at affordable rates after the agreements expired. This could further make the case for the importance of ongoing investment in social housing. Manitoba Housing and Renewal Corporation (MHRC) has agreed to work with RTH to provide data to determine the status of units funded through these agreements. The housing researcher will collect and analyze data and prepare a report.

L2M-Autonomous Wildfire Aerial Control Solution

We address the limitations and hazards of current wildfire detection and suppression methods, focusing initially on Alberta’s boreal zone. Alberta Wildfire uses aircraft, helicopters, specialized equipment, and trained personnel, but these methods have critical drawbacks. Crewed aerial systems cannot operate 24/7, leaving gaps when fires can go undetected. Additionally, deploying personnel is expensive and not scalable for vast high-risk areas. Refueling aircraft and replenishing fire suppressants are also time-consuming, hindering rapid response. The core issue is the inefficiency of current systems in timely, cost-effective, and comprehensive wildfire detection and suppression. This problem is exacerbated by the increasing frequency and intensity of wildfires due to climate change, which disrupt ecosystems, endanger lives, and incur significant economic costs. Our solution transforms lightweight crewed helicopters into autonomous firefighting UAVs. By integrating commercial autopilot systems and a custom hardware-software interface with water supply equipment, we enable efficient and cost-effective autonomous firefighting operations. Eliminating the need for human pilots enhances safety and allows continuous coverage, even at night and in poor visibility. Our system enables swift early fire control by autonomously responding to wildfires, initiating firefighting measures before other resources arrive. Stationing these autonomous helicopters near potential wildfire areas ensures prompt response, reducing the risk of wildfire spread and enhancing overall wildfire management.

Image Processing Production Monitoring AI Camera

Working with AI, an image processing model will be developed to be utilized on site in sawmills to increase productivity and efficiency of the mill by using a camera connected to an AI model to detect irregularities in the production line. The project will begin with image collection and labelling then move into model creation and training. If time permits, a user interface will also be developed for operators to view and compare results. ** Need to note how this project will benefit Iron Code

MRI-microscopy co-registration and 3D reconstruction of human cortex and amygdala for multi-modal assessment of epileptogenicity in drug-resistant epilepsy

Through combining information from MRI and microscopy, this research aims to propose advanced computational methods for the registration, reconstruction, and analysis of brain images. To improve the accuracy and resolution of the combined brain scans, a key component of this effort is the application of statistical techniques to create correlations between the various imaging modalities. Our approach focuses on developing sophisticated reconstruction procedures to generate high-definition composite images, reliable image registration algorithms to precisely superimpose MRI and microscopy images, and analytical tools that take advantage of these correlations to extract more profound insights from intricate neurological data. By providing researchers and clinicians with better tools to study brain anatomy and function, this improved imaging and analysis capabilities will greatly advance the diagnosis and management of neurological disorders.

Integrating High-Resolution UAV Data and Machine Learning for Monitoring and Analyzing Soil Erosion in an Agricultural Landscapes

This project aims to improve the monitoring and management of soil erosion in agricultural landscapes using advanced technologies like combinations of optical and LiDAR data from remotely piloted aircraft with machine learning. By creating detailed, high-resolution models of soil erosion and deposition, the project will help quantify erosion processes more efficiently than traditional methods. The expected benefits to participating institutions include enhancing their research capabilities through collaboration, providing valuable data for conservation efforts, and helping them develop more effective strategies for soil and water management. This approach will improve the precision of erosion assessments based on remote sensing data, assist in identifying critical areas for intervention, and contribute to more sustainable land management practices

Energy efficient iGrow air circulation system for raspberry cultivation (2)

Despite being the world’s third-largest raspberry importer, Canada faces challenges like high local wholesale prices, erratic climate, pest issues, and labor costs. This project offers a breakthrough solution—an innovative, scalable indoor farm—to address these issues. The goal is to create a cutting-edge platform that overcomes horticultural challenges, empowers future growers, and transforms Canadian indoor farming using advanced technology and sustainable methods.

The primary focus is to optimize the microclimate of the existing iGrow platform by managing airflow and vapor pressure deficit, vital factors impacting crop yield and plant health. To achieve this, a skilled postdoctoral researcher experienced in designing airflow for engineering applications using open-source libraries will be engaged.

The current iGrow system utilizes a closed-loop design to efficiently remove moisture from plants and recover energy from light fixtures. This captured heat serves to warm plant roots and condition incoming air, boosting energy efficiency. The appointed postdoctoral researcher will redesign airflow components—supply plenum, nozzles, and return ducts—to ensure controlled vapor pressure deficit and optimal airflow distribution within the closed-loop system, aiming for maximum benefits.

By merging technology and sustainability, this project aims to revolutionize indoor farming in Canada, leading to improved yields, plant health, and knowledge sharing among future growers.