Innovative Projects Realized

Les techniques des orthophonistes en thérapie vocale : leurs effets sur la motivation du patient et sur l’apprentissage moteur.

Ce projet vise à développer un système d’entraînement vocal virtuel offrant un support à domicile pour les personnes présentant un trouble de la voix. La première étape des efforts de notre équipe de recherche vise à mieux comprendre les éléments thérapeutiques en TV afin de développer une entraîneur vocal virtuel. Lors de ce projet, nous visons également à développer une grille afin de faciliter la documentation des processus thérapeutique en TV.
Question de recherche : Notre objectif de recherche est de documenter les éléments thérapeutiques utilisés par les orthophonistes lors des TV et d’étudier comment ceux-ci participent à soutenir le patient dans l’atteinte de ses objectifs.
Méthode : 10 séances de thérapie avec 5 orthophonistes différentes vont être enregistrées et transcrites afin d’identifier et de documenter les effets de différents techniques utilisées par l’orthophoniste sur l’apprentissage moteur et sur la motivation du patient.

Optimization and Development of Bombardier Data Based Engineering Design Tools

The proposed research will involve optimizing and improving engineering operations within Bombardier based on data collected from flight recorders and aircraft operators. This will involve developing new processes in maintenance tracking (i.e. tracking aftermarket spares sales, scheduled maintenance, accessing direct maintenance costs per component, etc.), and implementation of a stress tools suite for in-service structures evaluations. Currently, many internal processes within Bombardier are based on nonstandardized reporting and data collection methods. With the increasing influence of using data management and analytics in engineering, the challenge of the proposed research is incorporating these fields into the existing engineering simulation and design systems at Bombardier. To solve this issue, design platforms, linking to internal Bombardier databases, will be developed using tools such as MicroStrategy and Visual Basic to guide engineering decisions with respect to maintenance scheduling, structures evaluation, and aircraft efficiency.

Sentiment Analysis in Dialogue Systems

More and more companies are choosing to automate various aspects of their customer service using chatbots. While these chatbots are still in their technological infancy, they currently provide useful customer service to many people around the world. They will continue to become more desired by companies as a single chatbot system can engage millions of customers with minimal scaling costs. In these many interactions, there is a substantial amount of potential information to extract. This project focuses on extracting user sentiment information from a large set of chatbot-customer interactions. The ultimate goal of this project is to develop a module that collects and summarizes customer’s sentiment about the company’s products and services as well as their overall sentiment when engaging with the chatbot. Ideally, if successful, the information generated by our sentiment analysis module can be used by companies to more efficiently identify and handle customer issues.

Autonomous Energy System; Scalable, Flexible, Light and Low Cost

Nowadays the most rewarding aspect of engineering is to create solutions to the needs

of society in a natural and resource efficient manner, therefore we must come up with more

innovative and resource efficient solutions. One such solution can be a novel scalable

autonomous energy system, which integrates Organic (polymer) based photovoltaics (OPVs),

high density Polymer Energy Storage (PES) devices, and their Integrated Circuit (IC) interface

all as a System-in-Package unit. OPV and PES cells are thin, light, and flexible technologies

that have the potential to be used for such energy system at low cost. The IC interface manages

charging of PES cells from the harvesting energy provided by OPV cells and regulates such

power for the target applications. For the scalability of the system, the configuration of the cells

(both OPV and PES) will be optimized using statistical analysis based on experimental results

and characterization of the cells. This project will build on innovations made by our research………………………..TBC

Analyse de la diversité fonctionnelle des arbres de petites municipalités et mise en place d’une approche pour en améliorer la résilience

Les forêts urbaines d’aujourd’hui sont confrontés aux changements globaux, notamment l’augmentation de la fréquence des événements climatiques extrêmes (sécheresses, inondations, etc.) et l’arrivée d’espèces exotiques (maladie de l’orme, agrile du frêne, etc.), et subissent donc de lourdes pertes associées à ces stress. Les conséquences de la réduction de la canopée peuvent être dramatiques d’un point de vue social, environnemental et économique et peuvent par exemple se traduire par une augmentation du nombre de maladies cardio-vasculaires et respiratoires dans la société du fait de l’augmentation du niveau de pollution de l’air.
Ce projet vise à mettre en place une approche de diversification de la forêt urbaine de petites municipalités afin d’en favoriser la pérennité et la résilience face aux plus grand nombre de perturbations possible. TO BE CONT’D

La mesure de l’impact social des congrès d’affaires internationaux

Chaque année, des centaines d’associations professionnelles tiennent leur événement annuel dans une destination différente dans le monde. Ces rencontres servent aux participants pour acquérir des connaissances dans leur domaine d’expertise et faire du réseautage avec leur s collègues des autres pays. Notre projet de recherche pose les questions suivantes :
Comment de tels évènements pourraient laisser une empreinte positive durable dans leur lieu d’accueil?
Comment mesurer ces retombées positives?
Quels sont les facteurs de succès qui permettent de laisser un impact social local positif

Developing Design Strategies for Net-zero Energy High-rise, Mixed-use Buildings

This project explores and develops various strategies for the design of net zero energy high-rise mixed-use buildings. Net zero energy refers to the capacity of a building to generate renewable energy to supply all its yearly energy consumption. A mixed-use building combines residential and commercial building functions (e.g. retail, offices, etc.). Strategies that will be developed focus mainly on high performance building envelope with enhanced capabilities of generating energy, and on advanced building mechanical systems. Modular façade systems will be investigated to optimize the geometry to integrate photovoltaic system, and to increase its energy performance. Various mechanical systems and energy sources will be studied, and their performance will be analysed to allow further reduction of energy consumption, and thus achieving net zero energy status. Extensive advanced simulations will be conducted, employing building simulation tools.

Automated Monitoring and Orchestration of Cloud Native IMS VNFs.

By virtualizing all the various appliances in the network, Virtual Network Functions (VNF) became a key enabler for the coming 5G infrastructure and nowadays a major shift is under way bringing an evolution to cloud-native VNF. In the latter operational model, applications are decomposed into microservices running inside containers to enable automated installation, configuration and scaling with the dynamic network requirements beside self-healing and automated upgrading and updating of the VNFs. For efficient management of VNFs, reliable monitoring and advanced orchestration, powered by machine learning, are needed. This project aims to innovate methods and tools that will enable efficient monitoring and orchestration of Cloud Native IMS VNFs.

Tizen OS Support for SOTI MobiControl Interoperability

In this project, we propose to expand support of SOTI’s MobiControl (MC) to Tizen Operating System. SOTI MobiControl has assisted numerous enterprises to overcome the management issues due to lack of security and improve business performance by monitoring the health and safety of employees, and increasing productivity, with the introduction of wearables and other IoT (Internet of Things) devices. On the other hand, Tizen is a Linux-based mobile operating system developed by Samsung Electronics and offers support to Samsung smart devices, including Samsung Gear Watches, Samsung Smart TVs, Samsung Cameras and many other devices. This project aims to deploy the MobiControl management service to the Tizen devices in order to provide solutions to smart devices management to our customers.

Speaker Diarization

Machine-transcription of speech into text is very helpful in many scenarios. Consider the case of machine-transcription of conversation between a Doctor and a patient. If we are able partition and identify the segments of patient’s speech from those of doctor’s, then the transcribed text is more structured and can be more helpful for further use. The process of partitioni a given input audio stream into homogeneous segments according to speaker identity is called Speaker Diarization. In this project, we want to implement and improve the state-of-art method for speaker-diarization.

Super resolution for MRI scans

Brain MRI scans are a critical component in the diagnosis of neurodegenerative disorders. However, there is a wide diversity in terms of the image quality and resolution obtained from different MRI scanner. In particular, it is common to find coarse resolution MRI scans (e.g. every axial slice is 3-5 mm thick), which limit the type of anatomical analysis that can be performed. The goal of this project is to develop and validate the performance of state-of-the-art super-resolution methods in 3D MRI scans, which generate high resolution MRI scans from low resolution scans.

Low data drug modeling

The project aims to facilitate the research and development of new drugs by exploring Machine Learning methodology useful for both the generation of new molecules and the prediction of molecule properties. Doing so will involve training deep learning models on a large number of small, heterogeneous datasets, with the objective of transferring learned representations quickly when faced with a new drug-discovery or drug optimization objectives. The trained models will be used for the purposes of predicting molecular properties of new drugs and generating novel molecules with high likelihood of satisfying certain properties. The multi-objective nature of designing new molecules satisfying competing objectives will be approached using techniques from Reinforcement Learning.