L’imagerie aérienne offre de nombreuses opportunités en assurances: simplification de la souscription grâce à la complétion automatique de champs, amélioration de l’indemnisation grâce à des images post-catastrophes, raffinement de la tarification grâce à l’obtention de nouvelles données sur les caractéristiques physiques d’un lieu, etc. Cependant, l’utilisation de ce type de donnée pose plusieurs défis techniques. […]

Cardiac specialists spend anywhere from 60-70% of their patient consult working with electronic medical record (EMR) software attempting to extract salient patient data that leads to providing the most accurate diagnosis and care path. Cadea Health Inc. is seeking to reduce the workload cardiologist face by taking advantage of AI to intelligently gather and present […]

The Internet of Things (IoT) connects a plethora of smart devices globally across various applications like smart cities, autonomous vehicles, and health monitoring. IoT systems are predominantly software-defined, making them susceptible to quality issues on a large scale. This research aims to improve IoT trustworthiness through simulation-based testing and automated fault localization. Existing IoT systems […]

The proposed research project aims to develop a machine learning model that can draft preliminary radiology reports for x-rays. The project will use a large language model based on transformer neural networks to analyze x-rays and generate reports that are personalized to the reporting radiologist and based on the patient’s x-ray images. The goal is […]

Brain tumors are the leading cause of cancer-related death in childhood and are generally categorized as low-grade or high-grade. More granularly however, there can be over 100 types of brain tumors which can vary widely in both prognosis and treatment. Machine learning has increasingly been applied to classify brain tumors and other cancer types but […]

Augmented reality (AR) allows us to add virtual artifacts into the physical world. For example, we can place a 3D medieval castle onto the floor of a classroom, allowing students to explore it. AR supports collaborative learning since students can all see the same virtual artifact, and can interact using natural gestures like pointing. In […]

Notre mission est d’outiller et d’accompagner les propriétaires et aspirant·es propriétaires dans la réalisation de leurs ambitions immobilières. Ce projet vise à établir les conditions de réalisations nécessaires permettant la création d’un double numérique de propriété dans le plein respect des règles de protection des renseignements personnels.

Amélioration d’un Avatar bienveillant personnalisé pour aider les personnes âgées à rester autonomes à la maison, tout en favorisant la collaboration des différents intervenants avec la personne âgée.

Cette recherche consiste en l’application de techniques d’intelligence artificielle pour créer des gabarit qui serviront à l’extraction de données de formulaires (en format images ou PDF) dans le domaine de la gestion. Une combinaison de méthodes d’apprentissage automatique (intelligence artificielle) et de méthode d’ingénierie traditionnelles seront utilisés pour ce projet. Il est également fort possible […]

We focus on building the systems that allow for the storage and analysis of big data for preventing cybersecurity attacks. This telemetry data is collected from customers by leveraging endpoint, network, and cloud data sources both inside and outside our customers’ networks. Our team then builds products that allows our customers as well as our […]

Biomedical research, particularly preclinical research, is a complex and challenging field with a high failure rate of 98% in pharmaceutical research investment. Extracting relevant information from preclinical research papers involves synthesizing information from various sources, which is a demanding task that requires domain-specific knowledge. Natural language processing, specifically Large Language Models (LLMs), has demonstrated tremendous […]

The ability to quickly check if robot poses are not in collision with environment geometry is critical for robot applications that rely on forward kinematics, inverse kinematics, and path planning. It has been shown that during path planning 99% of the time is spent performing collision checks between the robot & its environment. Improving collision […]