Projets novateurs réalisés

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

29 670 projets achevés

2811
AB
4990
C.-B.
801
MB
663
NL
825
SK
8841
ON
9197
QC
95
PE
568
NB
1088
NS

Projets par catégorie

Automating Insider Threat monitoring and detection

Advanced persistent threat (APT) groups, as well as those sponsored by a nation-state, often aim to gain undetected access to a network and then remain silently persistent, establish a backdoor, and steal data, as opposed to causing damage. APT groups use different tactics, techniques, and procedures (TTPs) at various stages of cyberattacks. The continuous and ongoing threats and attacks imposed by APT groups create a need for continual and collaborative assessments of defensive measures. So APTs drive the need for purple teaming. Purple teaming is a collaborative approach to cybersecurity that brings together Red and Blue teams to test and improve an organization’s security posture. By emulating adversaries’ tactics, the Red team makes the blue team better at defense. To create an optimized and continuous security workflow, the purple teaming processes must be automated. In the Red team phase, there are several tools that can be used to emulate attacks and its possible to interact with all parts of the tools through the core REST API to make the process automatic.

Voir la description complète du projet
Superviseur du corps professoral :

Ali Dehghantanha

Étudiant :

Partenaire :

GlassHouse Systems

Discipline :

Computer science

Secteur :

Manufacturing; Professional, scientific and technical services

Université :

University of Guelph

Programme :

Accelerate

Développement du biocarbone pour des applications à haute température – QC-655

Le changement climatique représente l’un des plus grands défis auxquels nous devons faire face. Ce phénomène est causé par le réchauffement de la planète en conséquence des concentrations élevés des gaz à effet de serre (GES) dans l’atmosphère liée aux activités humaines telles que l’utilisation des combustibles fossiles dans le secteur industriel.
Les acteurs métalliques sont de plus en plus engagé à réduire leurs émissions de GES. Dans ce contexte, Elkem, un des fournisseurs mondiaux de métaux, souhaite remplacer le charbon fossile par du biocarbone, un produit obtenu par la pyrolyse de la biomasse forestière. Pour introduire le biocarbone dans le marché métallurgique comme alternative fiable et économique au charbon fossile, ses propriétés structurelles et mécaniques doivent être explorées et étudiées en profondeur. En effet, ce projet vise à étudier et optimiser les propriétés physico-chimiques du biocarbone afin d’améliorer sa réactivité dans les fournaises de ferrosilicium.

Voir la description complète du projet
Superviseur du corps professoral :

Richard Martel

Étudiant :

Partenaire :

Elkem Métal Canada

Discipline :

Physics

Secteur :

Manufacturing

Université :

Université de Montréal

Programme :

Accelerate

Robotic-based methodology for synthetic seizure dataset generation for machine learning-driven medical devices.

This research project aims to improve epilepsy treatment by developing a robotic-based method for testing wearable seizure detection devices. The project will create a robotic system that can simulate seizures, providing realistic data to help refine and test machine learning algorithms for detecting seizures more accurately. The goal is to address the limitations of current wearable devices and enhance the effectiveness of seizure detection and neurostimulation. By improving these devices, the project intends to make epilepsy treatment more accessible and enhance the quality of life for millions of people affected by this neurological condition.

Voir la description complète du projet
Superviseur du corps professoral :

Xilin Liu

Étudiant :

Partenaire :

NerveX Neurotechnologies, Inc.

Discipline :

Engineering

Secteur :

Manufacturing; Professional, scientific and technical services

Université :

University of Toronto

Programme :

Accelerate

Modelling of Asset Health and Risk Matrix for Rotating Assets in Sawmill

Weyerhaeuser Drayton Valley Lumber Mill has employed continuous monitoring of vibration for all the critical rotating assets in the mill to detect failures in early stage and prevent failures. Continuous monitoring is achieved through sensors mounted on the equipment and each sensor collects real-time vibration data of the equipment. Real-time vibration data give an understanding of the condition/health of the rotating asset. If the asset’s vibration goes above a certain limit (typically the limits are called as “warning” or “alarm”), then maintenance actions are initiated to prevent the failure. To reduce the overall vibration and prevent failures, Weyerhaeuser wants to better use the asset’s vibration information to represent asset health as very healthy, healthy, approaching warning, warning, and alarm. In this project, interns will work on developing an Asset Health Model to classify the asset condition/health using vibration information and build a risk matrix to prioritize maintenance activities. This will help maintenance team at Weyerhaeuser to take the appropriate actions to prevent failures, run the mill reliably, and achieve planned production.

Voir la description complète du projet
Superviseur du corps professoral :

Zhigang (Will) Tian

Étudiant :

Partenaire :

Weyerhaeuser

Discipline :

Engineering

Secteur :

Agriculture; Manufacturing

Université :

University of Alberta

Programme :

Accelerate

Using multi-modal data and self-supervised approaches for machine learning in healthcare

This research project aims to address the growing interest in predicting clinical outcomes using machine learning
(ML) approaches applied to Electronic Medical Record (EMR) data. The primary objective of this study is to
develop representations of both EMR and text data found in medical notes using current state-of-the-art ML
techniques. In particular, this research proposes to leverage self-supervised learning techniques to learn dynamic
representations. By doing so, the research aims to improve the prediction of clinical outcomes. Upon successful
completion, the machine learning models will effectively assist clinical decisions, which will benefit both the
company and the Canadian healthcare community.

Voir la description complète du projet
Superviseur du corps professoral :

Bo Wang

Étudiant :

Partenaire :

Signal 1 AI

Discipline :

Computer science

Secteur :

Professional, scientific and technical services

Université :

University of Toronto

Programme :

Accelerate

Evaluating self-efficacy and performance outcomes in an elementary school mentoring program

This project will evaluate an elementary school mentoring program, the Learning Buddies Network (LBN), which targets challenged students in reading and math, in terms of its outcomes in respect to the mentee’s self-efficacy beliefs and performance. The intern will consult with senior staff members of the LBN organization to identify improvements and extensions to the existing program evaluation tools and he will develop additional instruments to perform the evaluation. The outcomes of the project will include an assessment of the program outcomes during a three-month period of the mentoring program implementation, evaluation of the pairing procedures between mentors and mentees and suggestions on how these outcomes may be further improved in the future, regarding mentor training, type of mentoring (face to face or remote), and methods / strategies implemented. The resulted conclusions will be the basis for further evaluation of the program in the future, iterating additional expansions, improvements, and updates.

Voir la description complète du projet
Superviseur du corps professoral :

John Nesbit

Étudiant :

Partenaire :

Learning Buddies Network

Discipline :

Sociology

Secteur :

Education

Université :

Simon Fraser University

Programme :

Accelerate

1991 Soviet Coup Attempt – Part 2

The intern will investigate the 1991 Soviet coup attempt, a critical event in history when some powerful Soviet leaders tried to take control from then-President Mikhail Gorbachev. They will study why it happened, who was involved, and what the consequences were for the Soviet Union and the world. By analyzing historical documents, interviews, and other materials, the intern will gain a deeper understanding of the events and motivations behind the coup attempt. The expected outcomes of this research include: understanding the political context, the key players involved, the timeline of events, and the aftermath and consequences of the coup.

Voir la description complète du projet
Superviseur du corps professoral :

Seva Gunitsky

Étudiant :

Partenaire :

Taras Shevchenko National University of Kyiv

Discipline :

Sociology

Secteur :

Public Service, Policy, and Governance; Information and Communications Technology; Other

Université :

University of Toronto

Programme :

Globalink Research Award

1991 Soviet Coup Attempt – Part 1

The proposed research project aims to analyze the causes and consequences of the Soviet Coup attempt, including the political and economic factors that led to the coup, the role of the Soviet military and the KGB, and the impact of the coup on the collapse of the Soviet Union. The expected outcomes of the research project are to provide a comprehensive understanding of the events that led to the coup attempt, the factors that contributed to its failure, and the implications of the coup for the Soviet Union and the world. The research findings can contribute to the scholarly literature on Soviet history and politics and inform policymakers and the general public about the risks and challenges of political transitions and reforms.

Voir la description complète du projet
Superviseur du corps professoral :

Seva Gunitsky

Étudiant :

Partenaire :

Lviv Polytechnic National University

Discipline :

Sociology

Secteur :

Public Service, Policy, and Governance; Information and Communications Technology; Other

Université :

University of Toronto

Programme :

Globalink Research Award

Driver Behaviour Analysis Using Accelerometers on Android Devices

The objective of this project is to develop a software solution that can analyze the accelerometer data on android devices and report certain metrics of a moving vehicle related to road safety and driving conditions. The reports can then be used for immediate call for action in case of detecting an emergency or collecting the statistical data over a longer time period for assessing the general driving behavior. Advanced AI tools can be trained to immediately detect dangerous or harmful situations or patterns by monitoring the data on the device and reporting anomalies or sending alerts to the central control entity. In addition to data science skills, this project requires a good understanding of physics and dynamics of vehicles in driving conditions as well as a strong background in mobile device hardware and software engineering.

Voir la description complète du projet
Superviseur du corps professoral :

Arvind Gupta;Huaxiong Huang

Étudiant :

Partenaire :

SOTI Inc

Discipline :

Computer science

Secteur :

Information and cultural industries; Professional, scientific and technical services

Université :

University of Toronto

Programme :

Accelerate

CIUSSS-MTL : Apprentissage supervisé en radiologie du thorax

L’Intelligence Artificielle est utilisée dans le domaine médical afin d’offrir d’une part une aide à la décision à un personnel médical généralement surchargé et d’autre part une meilleure personnalisation des soins à partir des données relatives à une population.
Il est nécessaire de vérifier a posteriori, la bonne généralisation du modèle avec des ensembles de données dédiées à la validation et distinctes des ensembles de données utilisés pendant l’apprentissage.
Le projet de recherche est une preuve de concept dont les buts sont de valider :
1. L’utilisation des concepts de l’Intelligence Artificielle dans des applications médicales ;
2. L’utilisation d’une architecture de type CNN pour la détection automatique des anomalies dans des images radiologiques du thorax ;
3. La capacité d’augmenter le nombre de classes en utilisant le transfert de connaissances ;
4. Les résultats à partir d’une connaissance a priori des pathologies présentes dans l’ensemble de validation et de test (comparer ces résultats à ceux obtenus par le groupe ML de Stanford)
La validation du concept si elle parvient à être démontrée ouvrira la voie à un projet de développement.

Voir la description complète du projet
Superviseur du corps professoral :

Christian Gagné;Flavie Lavoie-Cardinal

Étudiant :

Partenaire :

Centre intégré universitaire de santé et de services sociaux du Centre-Sud-de-l’Île-de-Montréal

Discipline :

Computer science

Secteur :

Health and Related Sciences & Technology

Université :

Université Laval

Programme :

Accelerate

Data Communication Optimization between Mobile Devices and Servers

The proposed research project aims to improve the way data is transmitted between mobile devices and company servers. This will improve the speed and security of file transfers, data synchronization, application deployment, and distant management of mobile devices. The intern will collaborate with experts from the partner organization who will offer guidance and support in this research to identify new techniques that can be used to reduce the amount of data being transmitted, while also ensuring that the data is secure. The resulting improved communications layer will be integrated into the partner’s products, providing better service to their customers.

Voir la description complète du projet
Superviseur du corps professoral :

Eyal de Lara

Étudiant :

Partenaire :

SOTI Inc

Discipline :

Computer science

Secteur :

Information and cultural industries; Professional, scientific and technical services

Université :

University of Toronto

Programme :

Accelerate

Development of a distributed framework for deep learning models

Layer 6 powers the AI use cases for a variety of banking and financial applications at TD Bank. The goal of the research project is to improve the AI engine by having the training more efficient and distributed among a variety of clusters. The AI engine will allow models to be trained faster and with more optimal performance of the models. An improved AI engine can help deliver better machine learning models to over 25 million customers that rely on TD Bank for their financial decisions. As a whole, millions of Canadians who use TD Bank will benefit from their banking decisions being more accurate and up to date.

Voir la description complète du projet
Superviseur du corps professoral :

Scott Sanner

Étudiant :

Partenaire :

Layer 6 AI

Discipline :

Computer science

Secteur :

Other; Finance and Insurance; Artificial Intelligence

Université :

University of Toronto

Programme :

Accelerate

Précédent
1...925926927928929930931...2,473
Suivant

Joignez-vous à un écosystème d’innovation florissant.

Abonnez-vous à notre infolettre dès maintenant!

S’abonner