Innovative Projects Realized

Application du ML pour la détection de mots-clés dans divers types d’articles d’un site web

L’arrivée chez Tastet de l’intelligence artificielle a permis de proposer un service automatisé de recommandations d’adresses pour les utilisateurs inscrits, et ce service s’ajoute à l’activité première du site : l’analyse et la promotion des bonnes adresses selon des critères humains. Il est important pour Tastet de continuer sa mission en utilisant l’IA convenablement pour bonifier certains processus. Dans ce projet, nous visons à améliorer la catégorisation des contenus sur le site qui viendra supporter la recherche en proposant des mot-clés qui aideront nos visiteurs à trouver le contenu que nous avons à leur proposer. En utilisant l’IA, nous venons soulager notre équipe de rédaction en leur donnant la chance de se concentrer sur des textes de qualité et en retirant les étapes qui semblent redondantes, mais qui sont si importantes afin d’être en mesure de retrouver le contenu.

Understanding the Lifecycle of Software Innovation in Asia: Partnership Opportunities for Canadian Companies and Researchers

This proposal aims to understand the environment and lifecycle of digital technology development in Asia. Through this internship, with the collaboration of the academic supervisor and the Cansbridge Fellowship, the student will aim to write a review paper that examines the environment and lifecycle of digital tech developments in Asia, and will explore avenues to further promote mutual understanding and future collaboration between Asia and Canada in the digital technology sector.

Improving reliability of solid-state nanopore sensors through redundancy and chemical functionalization

Solid-state nanopores—tiny holes in thin glass similar in size to biomolecules like proteins or DNA—are poised to disrupt many essential growth markets, including genomics and proteomics, personalized medicine, point-ofcare diagnostics, and next-generation information storage. While holding great promise as a broadly applicable
disruptive technology, solid-state nanopore sensors are individually failure-prone, requiring use of many in parallel, as well as improvements to individual pore quality, before being able to deliver on this promise. This project seeks to consolidate several key advances, include a novel method of nanopore fabrication that can scale to arrays of pore, and surface modifications recently reported, to deliver redundant arrays of reliable nanopores as the basis for solid-state nanopores to deliver on their promise.

Development of a Prototype and Commercialization Pathway for the Improved Treatment of Periprosthetic Joint Infection (PJI)

Periprosthetic Joint Infections (PJIs) are infections involving an implanted joint prosthesis and surrounding tissue that occur following joint arthroplasties. Management of these infections is challenging and often surgical due to the antibiotic-resistant nature of the biofilm produced by infecting organisms. In 2019-2020, more than 63,000 Total Hip Arthroplasties (THAs) and 75,000 Total Knee Arthroplasties (TKAs) were performed in Canada. Studies have shown that the annual incidence rates of infection for THAs and TKAs to be 1-2%, resulting in significant economic burden to the healthcare system. The goal of this project is to prototype a medical device and workflow for the intraoperative treatment of PJIs during DAIR (debridement, antibiotics, implant retention), single-stage, and two-stage revision operations through the eradication of biofilm. To achieve this, the project will include the development of a business plan to describe a viable pathway from bench to bedside, technical feasibility assessments from a clinical perspective to optimize the integration of a medical device into existing surgical practices, and the construction of a physical preliminary prototype. The results of this project have the potential to improve outcomes for those undergoing PJI treatment, thereby reducing patient morbidity and healthcare costs associated with failed treatment strategies.

Projet PLAZA: Évaluation du projet pilote de navettes autonomes sur la rue St-Hubert

Le projet-pilote de navette autonome (et électrique) sur la rue St-Hubert, piloté par la ville de Montréal, représente ainsi une opportunité intéressante de documenter l’expérience des usagers de la navette et les perceptions des riverains par rapport à l’arrivée de ce véhicule sur le réseau routier. Le deuxième objectif vise à étudier les interactions des usagers de la route en présence de la navette autonome. Ces deux objectifs impliquent des collectes de données le long du parcours de la navette, incluant des observations non-participantes de la navette et des passants à proximité, des questionnaires auprès des usagers (aux arrêts et dans la navette) ou des riverains (sur la rue) et des collectes d’image vidéo à partir de caméras aux intersections. Les résultats permettront de mieux comprendre les effets de la présence d’une navette autonome sur le comportement des autres usagers de la route et d’ainsi proposer des lignes directrices assurant la sécurité et l’acceptabilité des futurs projets.

Improved Tactile Sensors for Biomedical Applications

The Institute of Biomedical Engineering at UNB is at the frontier of myoelectric signal acquisition and interpretation in patients with prosthetic devices. A particular challenge is understanding the effect of surface contact pressure on voltage measurements at the skin-electrode interface. Smart Skin Technologies (SST) is a New Brunswick company developing multi-touch pressure sensors aimed at several markets including smart-phones, sports training and industrial quality assurance. However, the pressure resolution and accuracy need to be improved before the sensors can be used in biomedical applications. The research project will study the device materials used at SST to achieve uniform response and improve pressure sensitivity. The goal of the research project is to improve the sensors to the degree that they can be employed in finesse applications such as prosthetics.

Algorithmic and Software Progress in Symbolic Computation

In recent years, research in computer algebra has expanded beyond its traditional territories, such
as exact linear algebra and formal solutions of partial differential equations, to enter new arenas,
such as symbolic analysis and polyhedral geometry. The proposed research projects will expand the
scope of computer algebra systems (CAS) into these two new areas. They will also strengthen CAS
in one of their well-established territories, namely symbolic integration.
This proposal capitalizes on the research conducted by the academic partners at the University of
Western Ontario in order to strengthen and extend the technology of their industrial partner, MAPLESOFT,
the developers of MAPLE, one of the leading CAS world-wide. In fact, the proposed research
projects extend a series of research projects conducted by the partners over the past two years with
the support of MITACS.

AI-powered SaaS Cybersecurity chatbot

CloudConseils is a startup that offers next-generation cloud security solutions and cloud consulting services. We are focusing on the security, development and migration of cloud applications and SaaS in AWS and Azure.
Identifying and remediating cybersecurity issues of Software-as-a-service (SaaS) and cloud-based applications is an essential and expensive task, specifically, for organizations that do not have an internal and expert security team. This project aims to explore the extent to which a cybersecurity tool could automated the finding and
remediation of vulnerabilities by monitoring a SaaS or Cloud application in real time and using AI and natural language processing technologies. In particular, we will automatically identify a list of vulnerabilities for a given SaaS and then propose remediation actions during an interactive chat session between a developer and an AI
chatbot.

Regulation of ubiquitin specific protease 8 by AMPK-mediated phosphorylation

Parkinson’s disease (PD) is the 2nd most common neurodegenerative disorder, affecting greater than 1% of people over 60. As occurrences are predicted to double in the next 20 years, there is a critical need for the development of prophylactic and/or therapeutic interventions. We have recently identified two enzymes, USP8 and AMPK, that interact and may be involved in mechanisms that lead to the onset and progression of PD. In collaboration with the Parkinson’s Society Southwestern Ontario (PSSO), the interaction of USP8 and AMPK will be explored to determine if they are directly involved in PD or associated cellular mechanisms. The research proposed will add to the growing list of potential therapeutic targets for the fight against this debilitating disease.

COGNI-ACTIF: apprendre en bougeant, un jeu à prendre au sérieux

Ce projet vise à développer la version bêta du jeu sérieux COGNi-ACTif, un outil technopédagogique qui mise sur la synergie entre le mouvement et l’apprentissage. Ce jeu sérieux est développé par des praticiens et des chercheurs issus de domaines variés (arts numériques, éducation, informatique, kinésiologie et neuropsychologie) dans le but 1) d’augmenter le niveau d’activités physique des élèves pour favoriser leur développement global et 2) d’augmenter leur niveau de motivation et d’engagement scolaire.

AI for Extraction of Biomedical Signals from Headphones

In an age of so many new wearable devices, e.g., smartwatches, glasses, rings, clothing, and so on, headphones can be recognized as the first widely adopted wearable device. They have been around for more than a century and have been used mostly as an output device for listening to music, or, in the
recent decades, talking on the phone. Even more recently, Ohmic has developed a technology formed by a suite of hardware and software solutions that enables headphones to go beyond their initial purpose. Ohmic has created a dongle to which any wired headphone can be connected to and that transforms any simple headphone into a smart version of itself, enabling gesture recognition (tapping and sliding), user identification, and biometric monitoring (heartbeat). It does that by using a circuit to cancel the incoming audio signal while amplifying and processing the signals of interest.

While the prototype can already read biometric signals, user activities like walking and running interfere with the desired signal causing a reduction in the signal-to-noise ratio (SNR). These so-called motion artifacts are a very well-known problem1 for wearable devices in general, however it can be mitigated by use of artificial intelligence to extract desired features, e.g., heart rate and heart rate variability. The latter being used to detect human emotions.

In the current context of making any headphone smarter, the intern student will be researching and developing the most appropriate machine learning strategies that can be used to extract biometric features, more specifically to ensure signal integrity, to understand the needs for future development,
and to lay the basis for the path from R&D prototypes to mass market products.

More precisely, the main tasks will be :
? Working on a literature review and comparison table of machine learning techniques for
biometric signals, highlighting their respective advantages and drawbacks.
? Developing AI algorithms for feature extraction of biometric signals, such as heart rate, heart
rate variability, respiration rate, and in-ear canal characterization.
This project is stand-alone and no other projects are planned at this time.

Permeability-based leakage model to describe functional failure in composite storage vessels for alternative fuels

Pressure vessels made entirely from fiber-reinforced polymer can generate substantial cost and performance improvements leading to their greater acceptance as a storage medium for pressurized alternative fuels (e.g. hydrogen). Inherent anisotropy and inhomogeneity of fiberreinforced composites usually induces functional failure (i.e. leakage) that precedes structural failure by bursting. Functional failure is attributed mainly to transverse matrix micro-cracking. The complex material behaviour and diverse failure mechanisms associated with composite pressure vessels cannot appropriately be modeled by existing failure criteria. The goal of the proposed project is to develop permeability-based analytical models to evaluate the performance of composite vessels under monotonic and certain fatigue loading conditions.