Projets novateurs réalisés

Explorez des milliers de projets réussis issus de la collaboration entre organisations et talents postsecondaires.

30 508 projets complétés

2882
AB
5105
C.-B.
825
MB
681
NL
860
SK
9051
ON
9491
QC
97
PE
586
NB
1141
NS

Projets par catégorie

Deep Transfer Learning for Diagnostics from Eye Fundus Images

THIS IS A GENERIC TEXT PUT IN PLACE AS THERE WAS NO PROJECT OVERVIEW

Voir la description complète du projet
Superviseur du corps professoral :

Ioannis Mitliagkas

Étudiant :

Partenaire :

Optina Diagnostics

Discipline :

Computer science

Secteur :

Manufacturing

Université :

Université de Montréal

Programme :

Accelerate

Quantifying and Combatting the Sexually Dimorphic Risks and Outcomes of Tobacco Dependency in Downtown Ottawa: A Mixed Methods Community-Based Participatory Action Research Project (SDRTT-Ottawa)

Smoking and all other forms of tobacco exposure are known to cause extremely detrimental health effects. It is the leading cause of preventable morbidity and mortality worldwide, and quitting smoking can increase life expectancy by as much 10 years. Tobacco is associated with poor reproductive health outcomes, cardiovascular disease, lung cancer, diabetes, blindness, and much more. It is lesser commonly known that tobacco affects male and female differently. There are chemicals in cigarettes such as bisphenol-As or phthalate esters that can increase the risk of estrogen dependent diseases such as breast or ovarian cancer.
Furthermore, the population that is most at risk for developing tobacco dependency involve those who are underprivileged and underserviced, and struggle with housing and food security. Within the community, male and female are predisposed to different risks in the context of acquiring tobacco dependency, and the associated health outcomes.
Therefore, this study aims to quantify the sexually dimorphic health risks of tobacco through the analysis of previous data, as well as work with community members to identify and ameliorate sex-specific risk factors for those in downtown Ottawa.

Voir la description complète du projet
Superviseur du corps professoral :

Smita Pakhale

Étudiant :

Partenaire :

Ottawa Hospital Research Institute

Discipline :

Life Sciences

Secteur :

Health and Related Sciences & Technology; Professional, scientific and technical services

Université :

University of Ottawa

Programme :

Accelerate

Multi-regional salary prediction model

The task of predicting salaries for a given job title and seniority in a specific region is challenging due to the complexity of various factors as well as the sensitivity of salary data. It’s hard to get an accurate sense of what people are getting paid in many regions in the world and getting harder as companies are hiring globally.
The objective is to create a machine learning model that considers the relevant features such as cost of living, job demand, education levels, etc., to provide valuable insights for quarterly budget planning or recruitment purposes. The model can help in understanding the regional job market trends and compensation practices, for the customers to make more informed decisions.

Voir la description complète du projet
Superviseur du corps professoral :

Mariano Consens

Étudiant :

Partenaire :

Agentnoon

Discipline :

Computer science

Secteur :

Information and cultural industries

Université :

University of Toronto

Programme :

Accelerate

Identifying Causal Risk Factors for Hazardous Driving and Accident Propensity for Safer Fleets and Smart Cities

Road safety affects everyone. In an effort to reduce accidents, we need to understand both the driving behavioural patterns that are predictive of accidents, and the environmental factors involved. In order to analysis risks, at first, collect a rich set of data: including Latitude/Longitude, engine RPM, accelerometer data in the X, Y, and Z plane, ambient temperature, and much more. Then, several derived datasets were created from aggregate customer information which provide metadata about the surrounding environment and pulled in numerous third-party data sources. The research will be focused on processing this data in such a way that useful features representing driving behaviours can be extracted for training machine learning models.

Voir la description complète du projet
Superviseur du corps professoral :

Andrei Badescu

Étudiant :

Partenaire :

Geotab Inc

Discipline :

Computer science

Secteur :

Information and cultural industries; Professional, scientific and technical services; Transportation and warehousing

Université :

University of Toronto

Programme :

Accelerate

Early detection of Septic shocks using vital signs

SpassMed’s ShockRanger is a primary product that utilizes vital signs from patient monitors to provide healthcare providers with meaningful signals for clinical decision-making. SpassMed is seeking one or more methods that can accurately forecast shocks, particularly Septic shock, among patients in ICUs. In addition, SpassMed aims to develop models for effectively classifying patients into their diagnosed diseases, with a specific focus on Sepsis. Sepsis and septic shock have the highest mortality rates in hospitals, and time-sensitive interventions are crucial in making the difference between life and death. Research conducted by Critical Care indicates that between 24.4% to 38.8% of patients die from Sepsis and Septic shock. Failure to predict shocks in a timely manner can prevent hospitals from assigning resources and taking immediate action, which can lead to life-threatening consequences.

Voir la description complète du projet
Superviseur du corps professoral :

Igor Jurisica;Vardan Papyan;Adam Stinchcombe

Étudiant :

Partenaire :

SpassMed

Discipline :

Computer science

Secteur :

Professional, scientific and technical services

Université :

University of Toronto

Programme :

Accelerate

Research and implementation of dash cam installation and image quality automatic detection based on big data

Geotab‘s dash cams deliver a clear and complete picture of harsh driving events and provide crucial video evidence in the case of collisions and insurance disputes. It is essential to ensure the dashcams work well and capture high quality footage.
The object of this project is to automatically detect dash cam installation faulty and monitor the image quality. We will implement a streaming or batch-basis algorithm to send alerts to fleet managers that a camera needs to be fixed, reinstalled, etc. In addition, we will also quarantine the data coming from the dash cam so that that video data will not be used in subsequent training.
In addition, this project also involves building an ML model deployment and production pipeline steps and associated data pipeline steps to add additional valuable data to the products we provided.

Voir la description complète du projet
Superviseur du corps professoral :

Marsha Chechik

Étudiant :

Partenaire :

Geotab Inc

Discipline :

Computer science

Secteur :

Information and cultural industries; Professional, scientific and technical services; Transportation and warehousing

Université :

University of Toronto

Programme :

Accelerate

Spatial flood risk mapping and forecasting using GIS and remote sensing in Central Vietnam

Floods have been considered the most common and leading cause of natural disasters worldwide. In Vietnam as well as in Canada, more frequent and severe floods have been documented to growing number of negative health outcomes. Alongside concurrent mitigation efforts, developing accurate methods to identify the health impacts of flooding to adapt will be crucial. This postdoctoral project is an extension of the fellow’s PhD research with other aspects of the impacts of floods on two different cultural and different living-way countries/provinces focusing on human health. In this project, the NASA’s MODIS Near Real-Time Global Flood Water (MFW) will be extracted with the support of Geographic Information System (GIS) and Google Earth tools to examine the model showing the relationship between floods and human health, using case studies of Thua-Thien-Hue in Vietnam and New Brunswick in Canada. The approach is implemented using a novel external dataset comprising satellite images, thereby allowing a highly precise and objective geographical measure of flood data. This project will open up a promising research direction that would effectively help address the existing and future challenges of flooding impacts in Canada and Vietnam.

Voir la description complète du projet
Superviseur du corps professoral :

Tri Nguyen-Quang

Étudiant :

Partenaire :

Hoa Sen University ;Hue University of Sciences

Discipline :

Earth science

Secteur :

Sustainability & the Environment; Environmental Science and Technology

Université :

Dalhousie University

Programme :

Globalink Research Award

Leveraging SSL 2 Generate High Quality 3D Face Avatar from Portrait Image

High-fidelity 3D face reconstruction from monocular images aims to obtain a 3D representation of the subject from a single or multiple input image. Recently, self-supervised deep-based methods have demonstrated impressive performance in 3D face reconstruction. These methods are efficient and produce plausible face reconstruction. However, for AAA production (games and movies), they do not yet meet the production-level requirements. For instance, the estimated geometry does not fully recover the likeness of the subject and the estimated texture maps used for rendering typically have low resolution. However, at least 4K texture maps are required in AAA productions. In this work, we aim to push the quality of the reconstruction provided by self-supervised methods to reach production-level needs.

Voir la description complète du projet
Superviseur du corps professoral :

Steve Engels

Étudiant :

Partenaire :

Ubisoft Toronto

Discipline :

Computer science

Secteur :

Information and cultural industries

Université :

University of Toronto

Programme :

Accelerate

Facial Landmark Detection with Synthetic data

Facial landmark detection is a computer vision problem where the goal is to predict the location of specific points on a face, like the eyes, nose, and mouth. This is useful for things like facial recognition and 3D modeling. To train a model to do this, we need a lot of images with those points already marked, which can be expensive and time-consuming. So instead, we can create synthetic images using scans of real people’s faces. Models trained on synthetic data have shown promising outcomes and have been successful. However, these models don’t work well on images taken with helmet-mounted cameras, which are commonly used in film and video games. This research aims to create synthetic data that looks like it was taken with these cameras and train models on it to improve performance.

Voir la description complète du projet
Superviseur du corps professoral :

Steve Engels

Étudiant :

Partenaire :

Ubisoft Toronto

Discipline :

Computer science

Secteur :

Information and cultural industries

Université :

University of Toronto

Programme :

Accelerate

Security enhancement of free-space quantum key distribution system

Satellites have become a crucial part of everyday life. We use satellites for watching television, navigation, weather
predication, national defense, and everything in between. Therefore, the safety and security of our satellites is
very important.
However, there are two problems that put satellites at risk of cyberattack:
1. As computers become more advanced, old cryptographic protocols become obsolete.
2. Encryption keys are lost or compromised.
QEYnet is working to address both issues and secure satellite communications using quantum key distribution
(QKD). QKD uses the properties of quantum mechanics to ensure secure communication, now and into the future.
Satellite QKD requires two main components: a quantum transmitter on the ground, and a quantum receiver on
the satellite. In this research project, we test the complete end-to-end QKD system for security vulnerabilities and
ensure both components are safe from cyberattack.

Voir la description complète du projet
Superviseur du corps professoral :

Li Qian

Étudiant :

Partenaire :

QEYnet Inc.

Discipline :

Computer science

Secteur :

Professional, scientific and technical services

Université :

University of Toronto

Programme :

Accelerate

Pre-contact Indigenous agricultural systems in southwestern Manitoba

We aim to identify the different agricultural crops grown by Indigenous farmers in the Pierson Wildlife Management area in southwestern Manitoba prior to the arrival of European settlers. Agriculture was an important aspect of life for many Indigenous peoples living in southwestern Manitoba. Identifying plant remains associated with different crops will tell us about daily meals people ate. Identifying past farming practices through the same plant remains can inform us of the ways people grew domesticated and non domesticated plants, and how producing food may have organized their lives. Indigenous peoples had sophisticated food-getting and cultivation practices. Identifying these through archaeology helps challenge stereotypes of Indigenous peoples as foragers and decolonizes the history of agriculture in Canada.

Voir la description complète du projet
Superviseur du corps professoral :

Mary Malainey

Étudiant :

Partenaire :

Manitoba Archaeological Society

Discipline :

Sociology

Secteur :

Arts, entertainment and recreation

Université :

Brandon University

Programme :

Accelerate

Design and develop a speech to intent system for numerical data

THIS IS A GENERIC TEXT PUT IN PLACE AS THERE WAS NO PROJECT OVERVIEW

Voir la description complète du projet
Superviseur du corps professoral :

Ioannis Mitliagkas

Étudiant :

Partenaire :

BusPas Inc.

Discipline :

Computer science

Secteur :

Information and cultural industries; Professional, scientific and technical services

Université :

Université de Montréal

Programme :

Accelerate

Précédent
1...9991,0001,0011,0021,0031,0041,005...2,543
Suivant

Joignez-vous à un écosystème d’innovation florissant.

Abonnez-vous à notre infolettre dès maintenant!

S’inscrire

Mitacs — Retour sur innovation

Mitacs est financé par le gouvernement du Canada, le gouvernement de l’Alberta, le gouvernement de la Colombie-Britannique, Research Manitoba, le gouvernement du Nouveau-Brunswick, le gouvernement de la Nouvelle-Écosse, le gouvernement de l’Ontario, Innovation PEI, le gouvernement du Québec, le gouvernement de la Saskatchewan, le gouvernement de Terre-Neuve-et-Labrador et le gouvernement du Yukon.