Innovative Projects Realized

Projet stage en logistique et achat chez Orange Traffic été 2024

Nous avons déjà notre stagiaire donc je ne crois pas que nous devons remplir cette section

AI-Driven non-invasive spinal deformity management

Momentum Health is an AI-based digital health platform for remote spine care management. From a 45-second video taken on a smartphone, their technology creates a photo-realistic 3D Model of the patient’s body and using AI predicts the degrees of spinal curvature and assesses the patient’s spinal deformity from the surface topography. They were co-founded by one of the top pediatric spine surgeons, Dr. Jean Ouellet, to address the 40 Million and growing North American population living with spine deformities. In less than 18 months, they have launched clinical studies and pilots at top Hospitals, including UCSF, Texas Scottish Rite and SickKids Hospital; have received FDA 510K Clearance, where they are the first AI Device cleared under the dept. Of Physical Medicine, and they are backed by the largest orthopedic association in the world (https://www.aofoundation.org/). They are starting with spine, but their vision is that by using the phone’s camera combined with AI, they will build a next generation patient-empowered medical imaging platform.

The internship project at Momentum Health is focused on advancing the field of AI-driven spinal deformity management. The intern will work on developing sophisticated machine learning models to predict the progression of spinal deformities and adapt existing AI algorithms for direct 3D mesh data input, aiming to revolutionize spine care diagnostics and patient monitoring.

Unlocking Perpetual Flight through Thermal Prediction

Inspired by how birds fly, Shearwater Aerospace applies AI technology to make drones fly faster and stay in the air much longer. Their autonomous operating system, Smart Flight, enables scalable, adaptive and resilient drone operations by coordinating drones and generating dynamic flight routes that leverage wind energy. This enables drones to fly 25% faster in transit and stay in the air loitering 800% longer.
Shearwater Aerospace is developing an autonomous operating software, Smart Flight, for professional and commercial drones. Smart Flight revolutionizes drone capabilities, enabling them to achieve extended flight durations, higher speeds, and increased operational frequency through the integration of cutting-edge artificial intelligence and wind-powered autonomy. This internship opportunity provides a unique chance to collaborate with an experienced team and world-class researchers specializing in autonomous soaring.
The internship is anticipated to have a transformative impact on Shearwater, elevating our capabilities and positioning us at the forefront of the unmanned aerial vehicule industry. Enhancing our capacity to accurately predict the location of potential energy sources before and during flight operations will enable us to provide a precise estimation of the flight potential to drone operators. This is not only critical for planning successful missions, but it will also significantly improve flight safety, operational efficiency and overall performance, including a substantial increase in flight time. This extended flight duration will not only enhance mission capabilities but also result in a considerable reduction in drone fuel consumption, aligning with our commitment to sustainable and green aviation.

Cultivating Financial Literacy and Mentorship Programs for Indigenous Communities

The Summer Internship for 2024 will focus on having two interns continue to enhance and roll out e-learning platforms that focus on Financial Literacy and Entrepreneurship fundamentals in Indigenous communities. Specifically, two interns will first be trained in project management, event planning, customer service, financial literacy and technology certification programs that will allow them to deploy the training to 38 Indigenous high school students and over 500 Indigenous people on-reserve across the country. This internship will also provide the opportunity for the interns to engage in telehealth and emergency preparedness practices.

Contrast reduction in coronary catheterization procedures through Artificial Intelligence (AI) analysis of coronary angiograms.

This invention is a software that integrates artificial intelligence (AI) to improve the way contrast media is injected into coronary arteries during medical procedures. It focuses on using the first contrast injection to determine the exact amount needed for further injections in either the left or right coronary artery. This means that the software can predict how much contrast media is needed for each patient, which can be given to an automatic injection system for use by passing specific parameters (volume, flow rate). By tailoring the contrast volume to the patient, the software aims to reduce the amount of contrast media used, lowering the risk of side effects.

Contrast media can cause adverse effects, including contrast-induced acute kidney injury (CI-AKI), which affects up to 8% of patients undergoing coronary catheterization. The risk is higher in patients with conditions like diabetes, hypertension, and chronic kidney disease. Developing CI-AKI can lead to serious complications such as increased risk of bleeding, heart attacks, and even death. It also results in longer hospital stays and higher costs, with an average increase of 3.36 days and $9,448 per patient. In severe cases, about 0.3% of patients might need dialysis, significantly increasing both the hospital stay and costs.

As far as the inventors know, this AI-guided system is the first of its kind to provide specific recommendations for contrast injections in the heart’s arteries, with no existing patents found that conflict with this invention.

Analyse du potentiel opérationnel de la technologie RFID – Déploiement d’un procédé de traçabilité de matériels dans les entreprises par la technologie RFID : migration vers l’usine 4.0

Ce projet concerne l’intégration collaborative de la technologie RFID par cinq entreprises leaders, visant à révolutionner leurs processus opérationnels et logistiques. Cette initiative stratégique est centrée sur l’amélioration de la traçabilité, l’efficience et la compétitivité à travers différents secteurs. En capitalisant sur les avantages de la RFID, les entreprises s’engagent vers une transformation digitale, facilitant une gestion optimisée et une visibilité accrue de leurs chaînes d’approvisionnement. Ce partenariat illustre une approche proactive vers l’innovation et l’adoption de solutions de l’Industrie 4.0 pour un avantage concurrentiel durable. Face à ces nombreux avantages, un regroupement de cinq entreprises s’est uni sous l’égide de l’organisme NOVINOR pour incorporer la technologie RFID dans leurs processus de fabrication et opérationnelles

Novaxe: Novel Online System for Guitar Music Score Recognition, Retrieval, Presentation, and Animation

This project is going to digitalize a patented method of presenting the guitar tablature and build an online system to assist guitar teaching. The new method invented by Mr. Mark Vandendool can present the guitar tablature with 8 building clocks. People can easily learn the chores of thousands of songs, which is impossible with the other methods. The system is called Novaxe. Novaxe is going to have a graph screen to display the fretboard with the information about the chord progression, rhythm pattern, tempo, key, `position`, song form, chord form, title, artist, year, and genre of a song. The fretboard contains the map of the scale notes as diamonds, and temporary chord tones as circles underneath. There are several difficulties in this project. First, the search function needs some sophisticated algorithm to search for songs in the library. Detecting of the music patterns is not an easy task and there is no 100% accuracy as there are different interpretations of music patterns. Second, the animation required on the user interface is complicated. And all the animation needs to be implemented by JavaScript. Third, the storage of the songs is unique than the business logic we are used to in database-design

Evaluate the impact of green infrastructure on reducing the risk of contamination during contact recreational activities in dense urban areas using a QMRA model

The project aims to investigate whether implementing Blue-Green Infrastructure (BGI) can provide extra protection to bathing and water recreation areas from Combined Sewer Overflow (CSO) risks. By utilizing the Storm Water Management Model (SWMM) software and Quantitative Microbial Risk Assessment (QMRA), this internship abroad offers a unique chance to assess such risks comprehensively. It also involves studying the impact of BGI on urban water recreation zones, particularly in reducing microbiological contamination, crucial amidst increasing overflows due to climate change. Moreover, the internship enriches my academic and professional journey by providing exposure to international expertise, fostering skill development, and facilitating collaboration across institutions, ultimately advancing research in microbiological risk assessment and urban water management. The participating institutions can expect benefits such as enhanced research insights, expanded networks, and potential contributions to policy development aimed at addressing pressing environmental and public health challenges.

Développement d’outil d’aide décision pour l’automatisation manufacturière dans le contexte des produits récréatifs

L’introduction de nouvelles technologies dans la production des produits récréatifs s’est considérablement accélérée chez BRP, Leader mondial dans la conception et la fabrication de produits récréatifs. La personnalisation des produits et l’augmentation des systèmes embarqués sur les véhicules contribuent à alourdir les tâches de reconfigurations qu’il faut apporter à la ligne d’assemblage. Le département de stratégie manufacturière est présentement à la recherche d’une méthodologie adaptée à la réalité de BRP qui servira comme outil d’aide à la décision pour l’automatisation à déployer sur un nouveau produit.
Dans un contexte manufacturier multisite, multiproduit à haute variété, à cadences très variables entre les différents produits, la sélection des différents niveaux d’automatisation des procédés d’assemblage et de fabrication est basée sur la rentabilité des investissements (ROI) basée sur le coût de la main d’œuvre. Le projet a pour objectifs de : (1) Définir les critères et les barèmes de décision permettant de rationaliser la décision d’automatiser ou non un procédé d’assemblage ou de fabrication selon le type de procédé dans un contexte de coûts totaux; (2) Fournir une méthodologie et les outils basés sur des calculs en fonction du type de procédé et des critères identifiés; (3) De définir les critères et les barèmes de décision permettant de sélectionner les procédés potentiels à robotiser en phase préliminaire de développement de produit.

Global Talent Streamlining: Leveraging AI for Strategic Immigration Solutions in the Canadian Labour Market

Our project addresses the critical challenge in the Canadian labour market: the mismatch between the demand for talent and the availability of skilled individuals to fulfill economic priorities. With Canada facing prolonged labour shortages across various sectors due to demographic shifts, this initiative seeks to bridge the gap by leveraging AI to analyze and match foreign talent with Canadian employment opportunities. By meticulously examining data sets of potential candidates and job vacancies, we aim to identify the most suitable immigration pathways and align skills, experiences, and qualifications with the needs of the Canadian economy. This comprehensive approach not only promises to mitigate the looming national crisis in industries like healthcare, construction, and technology but also sets a precedent for applying innovative solutions to global labour market challenges.

Scaling laws of GPBO algorithms

Déterminer les lois de scalabilité du cadre algorithmique GPBO pour l’appliquer à la résolution de n’importe quelle disponibilité de ressource physique en termes de mémoire et capacité computationnelle, à partir des microcontrôleurs jusqu’au clusters de computation. En particulier, évaluer :
1) le contraintes physiques et mathématiques qui déterminent la fonction multivariée entre la disponibilité de ressources de computation et la dimension du problème maximal faisable,
2) les lois d’implémentation optimale du système d’optimisation à travers plateformes de dimensionnalité variée et la valeur relative des choix impliqués dans les compromis d’implémentation – tel que une réduction du problème ou des limites à la mémoire d’optimisation immagasinée.

Streamlining Medical Administration: Developing an AI Solution for Automating Medical Form Processing in Canada

Physicians in Canada spend significant time on administrative tasks, including completing paperwork that requires filling out various forms in different formats. It is estimated that most physicians spend about 19 hours per week on paperwork. Such demands not only lead to burnout but also detract from patient care. Moreover, this additional workload is also an impediment to caring for physicians’ patients. To reduce the administrative workload of physicians, this project aims to investigate the use of artificial intelligence (AI) to automatically fill medical forms by extracting data from unstructured and unlabelled medical documents. The project will start by conducting structured interviews and surveys with physicians to understand the specific requirements and experiences with administrative tasks. Subsequently, machine learning and natural language processing techniques will be used to develop a prototype solution for analyzing medical records and filling out forms automatically. This project will use publicly available datasets and/or synthetic data for training and validation. Finally, the project aims to explore future directions for developing a complete AI-based solution that has the potential to fill out a variety of forms in different formats.