Projets novateurs réalisés

L2M – Oil spill detection using Empowered Earth Eyes (OEEE): A space-based smart solution

The OEEE is dedicated to combating oil spills in oceans and enhancing marine ecosystem health. Utilizing advanced satellite imagery analysis and AI modeling, this cutting-edge technology enables the monitoring of vast oceanic areas globally. Its capabilities extend to the early detection of oil spills and the identification of high-risk areas prone to oil spill pollution. The core of our mission is to address the pressing problem of delayed oil spill detection, which poses significant environmental and economic risks. With an automated detection system, the OEEE offers an innovative solution to enhance the detection and monitoring of oil spills in a near-real-time manner, ensuring broad accessibility and usability across various sectors.

L2M- Innovative Metal Powder Solution- Transforming metal Waste into Sustainable Additive Manufacturing Materials

NexaPowder Inc. aims to revolutionize metal 3D printing by recycling scraps and waste into affordable, eco-friendly metal powders. This will slash costs by half and reduce carbon emissions by 80%, making metal 3D printing more accessible and sustainable. The Lab2Market Launch program offers NexaPowder tailored support to develop vital business skills and secure funding, helping them bring their innovative solution to market. By partnering with NexaPowder, organizations can access cost-effective, sustainable powders that enhance manufacturing while minimizing environmental impact, paving the way for a greener future in metal additive manufacturing

L2M – Remote Estimation of Ocean Sound Speed

Our technology remotely measures sound speeds in ocean depths using acoustic techniques, eliminating the need for physical sensors to be lowered into and raised from the ocean. As sound speed is a crucial parameter in most ocean acoustics systems, our remote measurement capability revolutionizes ocean acoustics and oceanography by providing real-time sound speed data. Attending the Lab2Market Launch could help us to commercialize our technology.

L2M – BoviSense AI: Intelligent Solutions for Sustainable Dairy Farming

BoviSense AI revolutionizes dairy farm management by harnessing AI-driven biometric facial recognition to ensure personalized care for every cow. Leveraging unique bovine facial features, it offers precise, non-invasive monitoring of health and productivity in real time, steering traditional farming towards a sustainable, data-driven future. Our dedication to ethical AI use and broad compatibility underscores BoviSense AI’s role in leading dairy farming into an era of enhanced efficiency, animal welfare, and environmental stewardship. With BoviSense AI, we’re not merely tracking cows; we’re shaping the future of intelligent agriculture.

Classification des rachis cervicaux dans la population québécoise adulte nécessitant une chirurgie

Lorsque des prothèses et outils sont développés pour la chirurgie de la colonne vertébrale, leur conception exploite des simulations numériques. Cependant, les simulations de colonne qui sont utilisées ne représentent souvent qu’un individu caucasien de sexe masculin, dans la trentaine, et sans maladie. Ceci ne correspond pas aux patient·es susceptibles de recevoir une chirurgie de la colonne au Québec, et le processus de conception en est biaisé. Le but de ce projet est donc d’évaluer la variabilité des formes et des dimensions de la colonne vertébrale de la population québécoise afin de garantir l’excellence locale en conception de prothèses et en soins de santé. Pour cela, une analyse de classification sur les images médicales que des patient·es d’un hôpital du
Québec ont volontairement cédées à la recherche sera réalisée afin d’en ressortir ce que serait, par exemple, une colonne de taille M par rapport à une colonne de taille L.

L2M – Imprinted polymeric microstructures for specific capturing of target analytes

For those who need precise and selective capturing, releasing, and sensing of substances within complex samples and harsh conditions, SensoFluidix offers microparticles and membranes with monodispersed shapes and sizes, serving as tailor-made synthetic recognition elements within disposables microfluidic cartridges and sensors. Unlike natural receptors, our cost-effective synthetic receptors can endure harsh environments, boast a prolonged shelf life, and are user-friendly, easily stored, and animal-free. Our technology can be engineered for a wide range of target analytes, including ions, and whole microbial cells. We aim to address a series of validated problems for well-identified customers in environmental monitoring, mining, battery recycling, and analytical chemistry industries.
The Mitacs BSI program will enable us to grasp the fundamentals of lean startup methodology and take significant strides toward commercializing our ideas. This includes finalizing our business model under the guidance and support of mentors, facilitators, and supervisors, providing us with invaluable expertise and direction.

L2M- Launching BravoZulu Create

Transition and reintegration from service represents a profound psychosociocultural change for individuals who release from military service (i.e. Veteran). Service is impactful to health and wellbeing over the life course. Veterans represent a special population in Canada with heterogenized needs. Acculturation and loss of service identity presents the need for social reintegration and to restore identity through alternative roles (Thompson et al., 2017). There is a need to develop programs and services that reflect the heterogenous needs of Veterans. Community, belonging, autonomy, ability, purpose, and meaning of art and craft suit a myriad of transition and reintegration demands however access and resources to art and craft could represent barriers to participation. There is currently no online community that supports Veteran art/craft endeavours domestically nor internationally. Such a novel technology represents a valuable contribution to Veteran health by supplying a neutral space for Veterans to convene, share art/craft and learn as they choose as well as to co-create in a meaningful way.

Identification de stratégies d’approvisionnement en naissain de moule aux Îles-de-la-Madeleine

Aux Îles-de-la-Madeleine (Qc), les mytiliculteurs s’approvisionnent en jeunes moules (naissain) dans une lagune côtière, le Bassin du Havre-Aubert (BHA), car les stocks récoltés (captage) présentent une résistance particulière au stress, en lien avec une diversité génétique plus importante. Toutefois, face au manque d’espace disponible au BHA et à une variabilité interannuelle du succès de captage, cette industrie aquacole considère comme prioritaire l’évaluation du potentiel d’approvisionnement en naissain de moules performant et ce, à l’échelle de l’archipel. Dans ce contexte, l’objectif de ce projet est d’identifier les stratégies alternatives d’approvisionnement qui reposeraient principalement sur l’exploitation d’autres plans d’eau. Élaborés avec la volonté de limiter la colonisation d’espèces nuisibles au captage, plusieurs scénarios de culture seront testés sur la base d’une évaluation de la performance du naissain (croissance, survie, génétique). Les retombées directes du projet seront l’obtention d’une quantité suffisante de naissain de moule de qualité à l’échelle de l’archipel, permettant ainsi aux entreprises mytilicoles d’atteindre leurs objectifs de production et de rentabilité.

Modélisation spatio-temporelle de pertes dues aux tempêtes de grêle au Canada

Ce projet a pour but d’établir un modèle considérant la dépendance dans l’espace et dans le temps, entre les tempêtes de grêle causant des dommages assurables. Nous utilisons un modèle hiérarchique Bayesien, où la fréquence des pertes assurables sera scindée en partie que nous définirons comme faisant partie du noyau et des extrêmes. Nous utilisons la méthode Monte Carlo Hamiltonienne pour l’estimation des paramètres. Cette modélisation pourra ensuite être utilisée afin de combiner des taux de dommages par rapport à la valeur des effets assurés. L’objectif est de fournir un modèle libre d’accès, qui représente l’évolution des tempêtes de grêle.

Deep Reinforcement Learning in Optimal Market-Making

On June 1, 2021, Futures First Canada and FinML began a pilot collaborative project involving three Canadian universities by-way-of a MITACS Accelerate internship (IT25712) which jumpstarted an initiative to use cutting edge techniques in machine learning, financial mathematics, and AI for making predictions in financial markets. This goal is integral to the business operations of Futures First and is currently a popular topic in academic research. The pilot project created a basis for this current project application which will continue the effort, extending positive academic results and furthering integration into the company’s infrastructure. This next project will extend previous research from project IT35694 which focused on applying SOC (stochastic optimal control) to algorithmic and HFT (High-Frequency Trading) problems. The trading problem Futures First specifically focuses on is market-making, which is one of the most heavily studied trading problems in the futures trading environment. The main subject of this new project will be to utilize the novel topic of deep reinforcement learning to generate optimal market-making solutions. This will be a challenging project where we uncover the obstacles for applying the academic theory around deep reinforcement learning in practice.

Procedural Tree Modeling with Silhouette Constraints

Modeling trees is known to be a difficult problem in computer graphics. At Animal Logic, the typical artist workflow involves using the in-house tool for semi-procedural tree generation. The artists hand model trunk, branch, and leaf geometry, and trees are generated by scattering branches and leaves in a recursive manner.

This approach has several limitations. First, artists often would like to hit a certain silhouette or shape of a tree, represented with closed mesh volumes. While this is possible with the existing approach by culling branches that leave the volumes, this results in an unnatural appearance, as if the tree had been manually trimmed. Second, the approach does not prevent intersections between branches during the recursive addition of branches. Such cases are undesirable and result in an unrealistic appearance of generated trees.

The aim of this project is to develop a method for semi-procedural tree generation that generates a tree defined within mesh volumes using artist modeled trunk, branch, and leaf geometry in a manner consistent with artist expectations. Our approach will significantly reduce the time artists spend manually creating trees that fit a certain shape; as a result, large collections of trees can be constructed with reduced manual intervention.

Development of Cost-Effective Solutions for Energy Management in Smart Buildings

The proposed research aims at developing control strategies under the paradigm of Demand Response (DR) in the context of the Smart Grid in order to improve energy efficiency and to reduce operational cost in commercial buildings and communities. The emphasis will be put on consumer side energy management strategies that able to balance energy demand and supply and to reduce the overall operational cost while providing an enhanced performance. The envisaged solutions lie mainly on autonomous demand response management in smart buildings including peak shaving, consumption scheduling, and load forecasting. The achievements of the present project will allow the industrial partner, Fusion Energy Inc., to enhance their solutions for energy management through optimization of mechanical and electrical equipment, automation, and real-time energy consumption control.