Innovative Projects Realized

Etude de marché des nouvelles compétitions et des évènements sportifs en milieu urbain pour le Parc Olympique de Montréal

L’objectif de cette étude est de fournir au Parc Olympique des recommandations qui lui permettront d’améliorer son attractivité à travers l’organisation d’évènement sportif porté sur des disciplines émergentes, ayant un fort pouvoir en termes de marketing.
Le projet va utilisé deux méthodes de recherche en marketing, lune étant une étude comparative des nouveaux compétitions et évènements sportifs apparus dans le paysage urbain sur la dernière décennie, l’autre reposant sur un sondage auprès de la population montréalaise et utilisateur du Parc Olympique afin de tenir compte de leur motivation et attentes concernant la participation à des évènements sportifs.

Domely – Projet de stage en IA – Inférence des charactéristique des toitures d’édifices commerciaux à l’aide de la télédétection et de l’intelligence artificielle

Le projet vise l’opérationnalisation d’un modèle d’intelligence artificielle permettant de modéliser la structure des toits au Canada à partir d’imagerie géoréférencée de télédétection par laser (LIDAR). En obtenant ainsi de l’information précise sur chaque bâtiment et la structure des toits et combinant ces informations à de multiples données météorologiques en provenance de sources externes et d’objets connectés, Domely technologies développe une meilleure compréhension de l’impact des risques climatiques sur nos infrastructures canadiennes. Ces modèles numériques permettront à l’entreprise d’améliorer son offre visant principalement les assureurs et les gestionnaires d’immeuble et incluant des solutions analytiques de préventions intelligentes et d’aide à la décision.

Business development strategy for the commercialization of a digital health technology committed to preventing kidney failure

Collogh Cares Inc is a digital health technology and advocacy start up, committed to preventing kidney failure, one family at a time .We are building an end-to-end solution to the problem of kidney disease and the inadequate follow-up of Chronic Kidney Patients. Our solution constitutes of a Chronic Kidney Disease (CKD)
management “ecosystem” comprising of monitoring devices (licensed hardware), digital health coach and predictive AI. With our solution we will be able to slow down and prevent progression to kidney failure by over 3x and improve the health outcomes for marginalized patients at high risk of developing kidney failure.

With the help of the Intern, we will be able to strategize and build our regulatory requirements for our prototype and have it ready for testing. Intern will assist with building and establishing potential client relationships and securing our first health insurer client.

Open Minds Digital Transformation

Digital Transformation of Open Minds NB will allow us to reach clients in a broader spectrum, using virtual technologies to interact and connect clients with therapists. Therapists increasingly work from home, and connect virtually with clients in their homes. At Open Minds NB, we are aware of the challenges and risks of increasing our virtual interactions, including issues of privacy and safety. We seek an intern to help us enhance and strengthen our virtual tools; our website, our Client Management Tool for scheduling, invoicing and tracking client needs, and our social media outreach, including our blog, weekly newsletter and Facebook and Instragram feeds.

Get In the Loop Digital Transformation with UNB Catalyst

Get in the Loop is engaging a UNB intern to assist with development and enhancement of the business to affect Digital Transformations and improvements in business protocols.

We are seeking – and have found- a professional and personable individual to join our dynamic Business Development team to expand our market and develop our brand awareness across Greater Saint John. The intern will be part of a cohesive, energetic team and will benefit from a flexible work schedule, valuable training, and wide-ranging experience in all aspects of our business with the opportunity for future growth.

Inverse graphics network for 3D building reconstruction using a GAN-based approach

The ability to extract 3D models from 2D images, a process called Inverse Graphics, finds applications in the many applications of Virtual Reality. For the development of urban digital twins, we focus our research on Inverse Graphics of buildings, which would greatly simplify the reconstruction of entire city blocks in a virtual environment. We plan to investigate a Generative Adversarial Network (GAN) and Differentiable Renderer based approach. We first plan to train a building image GAN which would allow for the creation of a synthetic self-supervised dataset. This dataset would then be used to train the Differentiable Renderer, which is responsible to 3D reconstruction. We expect the product to generate 3D mesh and texture from 2D images taken from phones or other digital cameras.

Factors that Promote the Effectiveness ofInternships for Internationally QualifiedProfessionals

This project will explore factors that contribute to the benefits of internships for internationally qualified professionals in terms of improving these essential immigrants’ integration into the Canadian labour market. The project involves a partnership between Career Edge (a non-profit organization that arranges paid internships for internationally qualified professionals and Canadian individuals), the University of Western Ontario and York University, and will utilize an online survey and follow-up interviews to achieve its goals. The final products will include a report and presentation to Career Edge describing the research findings and providing recommendations for optimizing the internships that they coordinate. Given the broad relevance of the findings, we will also write the research up for publication in a peer reviewed journal and present the findings at relevant conferences.

Stereo (Multi-view) DepthIQ and its Application in SLAM

Our partner organization has developed a new type of camera, one where depth information is part of a single lens/sensor construction, meaning that there are no occlusions or shadows which plague stereo cameras, there is no requirement to light the scene as well time-of-flight cameras, and the expense is low compared to light-field cameras. Currently these cameras are limited to a near-range depth field of around 2m, this project aims to improve through several methods. We shall work with our partner organization to develop a stereo setup (including a calibration process) that will greatly extend that range, and then incorporate a deep learning method that will be able to use the actual stereo method to infer the stereo back from a single camera. To validate this process we shall develop a Simultaneous Location and Mapping (SLAM) method using both cameras and determine the errors produced.

Design and development of machine learning and signal processing algorithms for a wearable device (Watch HOP) for critical care, surgery, and chronic disease monitoring

Diabetes is a chronic illness characterized by elevated levels of blood glucose, accompanied by disturbed metabolism of fats and proteins. In the present project, a non-invasive wrist-worn device (Watch HOP) will be designed and fabricated to obtain physiological data (digital biomarkers) from participants to enable the creation of an algorithm that will ultimately allow to monitor and predict HbA1c levels and assess the efficacy of the given treatment.
In many applications of the smartwatch, it is desirable to record data for long periods of time. As a result, the recoded data will have a large dimension. Therefore, compression of the signal is an important part of design process. Compression algorithms, represent the original signal with fewer information bits. It is important to preserve all the information in the original signal in the compression method. The candidate will work with the hardware and firmware team to design and implement a lossless compression algorithm to compress the recorded signals.

Développement et implantation de la technologie des fondations stabilisées comme solution de réhabilitation de chaussée environnementale et économique

Le retraitement en place de type 2 est une technique de réhabilitation des chaussées qui s’inscrit dans les principes du développement durable et de l’économie circulaire. Ce projet vise à développer des outils permettant de mieux encadrer cette technique de réhabilitation dans un contexte climatique propre au Canada. Les organismes partenaires pour ce projet représentent les différents types d’intervenants impliqués dans des projets typiques de réhabilitation de chaussée, soit un donneur d’ouvrage, un laboratoire génie-conseil, et un représentant des entrepreneurs.

Thermodynamic investigation into the recovery of rare earth elements

The proposed research aims to contribute to the development of a recycling process for waste magnets. The proposed method is based on slag treatment which is a high temperature process for separation of one element from another based on their difference in oxygen affinity. For example, the affinity of neodymium for oxygen is significantly higher than the affinity of Iron for oxygen. This will facilitate the separation of iron from neodymium in their oxide form.
Cyclic Materials is developing a recycling process for magnets. Considering the complexity of the chemistry of this mixture, it is necessary to perform a fundamental thermodynamic evaluation prior to high temperature experiments. This proposed project will examine the efficiency of slag treatment of magnets via thermodynamic modelling.

Facilitating the recycling process of catalytic converters using computer vision

Catalytic converters used in car exhausts are effective means of reducing pollutant emissions from internal combustion engines under normal operating conditions. They contain precious metals which makes them attractive for recycling due to their metal value and also the sustainability of the demand for these metals. The price of Catalytic converters can be determined based on their models and the amount of metal that exist in them. Currently, the price estimation requires human experts to identify the model of catalytic converters and then query a database to find the amount of precious metals in the catalytic converter and then estimate the recycling price of the catalytic converters based on the daily value of the PGM metals. The objective of this project is to build an application that can automate the price estimation of catalytic converters for recycling. We will train a machine learning classifier model using computer vision and integrate it in a cross-platform mobile application.