Projets novateurs réalisés

Linguistic Cues for Heuristic Determination of Patterns of Speech in Noise

This project aims to investigate the benefits of using linguistic cues for extracting speech-of-interest from competing background noise. Given an algorithm which detects formants of a speaker of interest within an audio signal which includes background noise, and given that the limits of such an approach are reached when formants of the speaker of interest become substantially lost within the noise, are there linguistic cues within some formants, or linguistic relationships between some successive speech sounds, which can be used to infer with confidence which speech sounds from the speaker of interest are present beneath the noise floor of a noisy audio signal. The partner organization will benefit from this internship by extending the range of solutions it can offer to the market. If the proposed solution proves to be useful and novel, the partner organization will apply for patent protection. This could lead to increased sales and the additional employment within the company.

Data, Analytics, Visualization and Streaming

Interaction Concepts for Remote Robot Exploration in Crisis Scenarios using Virtual Reality

Building Information Modeling (BIM) for Energy-Efficient Building Operations

Internship at the University of Münster in a research project on intentional forgetting and trust

Optical characterization of flexible neural implants

Internship “Nutrition and Microbiota”

Using Cryo-EM to Determine Macromolecular Complexes

QDoc – Online Medical Platform

QDOC designs and builds cutting edge medical software. Our premier product connects patients seeking either immediate or appointment-based encounters with Canadian licensed Physicians.
Building on the rideshare model of matching clients with transportation, QDOC implements custom algorithms, along with secure PHIA/HIPAA compliant technology to create a seamless, streamlined experience for both patient and physician.
By allowing QDOC physicians to work anywhere, anytime, leveraging NLP and AI we can create a seamless on demand offering for patient visits. We provide advanced tools to document the patient encounter, follow up on tests, and order prescriptions all from within the application.
Our system can be used by patients who require a physician immediately, as well as providing a central portal to allow for referrals to specialists, and other medical professionals that might be part of a comprehensive patient care approach.

Evaluation of LTD 3.0 Framework Adoption and Implementation

The Long-Term Development (LTD) 3.0 framework and its previous versions have been distributed by Sport Canada to national sport organizations since 2005 to improve participation and physical activity levels across the country, although the LTD’s acceptance and rollout has not been evaluated. Therefore, the purpose of this study will be to speak with national and provincial/territorial sport organization directors and community leaders as well as review relevant documents (e.g., athlete development policies) to understand how each side has put the framework into action and how it has impacted their members, funding, and international medal success. Our partner organization, Sport for Life, will benefit from this study by gaining a greater understanding of where sport organizations from the national to local level stand on the framework and how future versions can be changed to better serve these communities.

Speculative Sensory Interfaces: Opening a dialogue between differently-abled bodies through sensory interventions

This project will use speculative design methodologies to create wearable technologies (wearables mounted with sensors that can be worn), capable of sending, receiving, and sharing sensory information across differently-abled human bodies. As the participants with different body structures, mobility, and agility move in space wearing aforementioned wearable technologies, proprioceptive information (sense of balance and body gestures) from one participant’s body will be strategically mapped using machine learning algorithms to tactile senses (such as pressure on the skin through shape changing interfaces) – acting as a stimulus on another person’s body. Overall, the aim of this project is to question the normative perception of sensory-motor disability (often seen as a impairment in the body) through a confusing and playful bi-directional flow of sensory information across differently-challenged human bodies.

AI model building accelerator

The candidate will be working with Modellicity to participating in the development and bringing-to-market of the company’s proprietary end-to-end AI model building platform that will enable users to quickly build, validate, and deploy AI models.