Projets novateurs réalisés

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

30156 projets achevés

2861
AB
5059
C.-B.
812
MB
673
NL
842
SK
8957
ON
9368
QC
96
PE
579
NB
1120
NS

Projets par catégorie

DNS tunneling detection method based on ML & DL models

Domain Name System (DNS) tunnels as a covert communication channel between a controlled host and a master
server can be utilized by malicious attackers disguising the master server as an authoritative domain name server.
DNS tunneling can cause significant harm due to its ability to easily evade network security mechanisms by using
DNS traffic, so it is crucial to detect the malicious domain in advance. In this research, the performance of the
machine learning and deep learning models with existing detection methods are compared to determine their
effectiveness in detecting DNS tunneling activity, and optimize the models by tuning hyperparameters, adjusting
the architecture of the models, or combining multiple models to achieve better performance in the real-time
prediction.

Voir la description complète du projet
Superviseur du corps professoral :

Murat Erdogdu

Étudiant :

Partenaire :

BlueCat Networks

Discipline :

Computer science

Secteur :

Professional, scientific and technical services

Université :

University of Toronto

Programme :

Accelerate

Real-time DNS tunneling detection using Machine Learning & Deep Learning techniques

Domain Name System (DNS) tunneling is a malicious technique that enables attackers to bypass network security
measures and steal sensitive information. Traditional detection methods that rely on signature-based approaches
are often ineffective against advanced attacks. In light of this, recent years have seen a growing interest in the
use of deep learning techniques for network intrusion detection. This research aims to explore the feasibility of
using deep learning algorithms for the detection of DNS tunneling in real-time network traffic. The study will involve
the analysis of a large dataset of DNS traffic to develop and evaluate a deep learning-based model. The model’s
performance will be compared against existing detection methods, and the outcomes of this research will
contribute to improving the effectiveness of DNS tunneling detection, enhancing network security overall.

Voir la description complète du projet
Superviseur du corps professoral :

Murat Erdogdu

Étudiant :

Partenaire :

BlueCat Networks

Discipline :

Computer science

Secteur :

Professional, scientific and technical services

Université :

University of Toronto

Programme :

Accelerate

The development of predictive capabilities in terms of pH and solubility for complex mixtures of organic acids and organic acid salts

This project will require a combination of theoretical and empirical modeling based on extensive experimentation to develop a predictable solubility model in organic acids and salts mixture systems. The successful completion of the project will allow the company to predict capability of the complex mixtures during products development. It can be used by formulators & scientists to develop desired new products in food and beverage industry.

Voir la description complète du projet
Superviseur du corps professoral :

Fei Geng

Étudiant :

Partenaire :

Bartek

Discipline :

Engineering

Secteur :

Manufacturing

Université :

McMaster University

Programme :

Accelerate

Cylinder Detection on Point Cloud 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 :

Carlton Davis;Terry Peckham

Étudiant :

Partenaire :

Antea Canada Inc.

Discipline :

Physics

Secteur :

Mining; Professional, scientific and technical services

Université :

Collège Dawson

Programme :

Accelerate

Feature Search using Automatic Machine Learning

This research project focuses on developing an automated system to search and analyze time-series tabular features in the financial institution’s machine learning pipeline. The goal is to identify relevant features and improve efficiency in the decision-making process. The project will begin by prototyping a system to support automated feature search patterns and researching feature search approaches. The system will be tested and deployed in a use case, with appropriate governance for production systems. Successful completion of the project will contribute to the feature search automation of the machine learning pipeline at the financial institution.

Voir la description complète du projet
Superviseur du corps professoral :

Gennady Pekhimenko

Étudiant :

Partenaire :

Layer 6 AI

Discipline :

Computer science

Secteur :

Technology; Finance and Insurance; Artificial Intelligence

Université :

University of Toronto

Programme :

Accelerate

The effects of various dairy products on the gut microbiota

Probiotic bacteria may be the reason why dairy products are good for you. Some dairy foods may change how the gut microbiota
is made up, which can help with weight control and metabolic health. But it’s not clear how dairy products could fix the bad effects
of a high-fat, low-carbohydrate diet on lipid and glucose metabolism by changing the GI microbiota. So, the goal is twofold: 1) to
find out how the different types of dairy affect the gut microbiota in a mouse model of a high-fat, high-sugar diet; and 2) to find out
how gut microbes change the way the body uses energy.

Voir la description complète du projet
Superviseur du corps professoral :

Catherine Chan

Étudiant :

Partenaire :

Helmholtz Centre Munich

Discipline :

Life Sciences

Secteur :

Health and Related Sciences & Technology; Agriculture and Food

Université :

University of Alberta

Programme :

Globalink Research Award

Development of a virtual active learning environment: Making use of digital knowledge objects, data visualizations, and smart assessments to engage students in collaborative deeper learning in online teaching contexts

This project will be focus on developing a digital learning platform that is: grounded in the science of learning research; informed by established pedagogical approaches for supporting collaborative learning; responsive to principles of equity and inclusion; and based on principles of effective assessment to provide high-quality online and hybrid delivery modes of distance learning education for students.

Voir la description complète du projet
Superviseur du corps professoral :

Fanny Chevalier

Étudiant :

Partenaire :

University of Toronto Schools

Discipline :

Computer science

Secteur :

Education

Université :

University of Toronto

Programme :

Accelerate

Automatic Machine Learning for Recommender Systems

This project aims to improve recommendation systems by using advanced computer techniques called Auto
Machine Learning and Meta Machine Learning. This involves automating parts of the machine learning process,
like finding similar data and picking the best settings for the computer model. This project also aims to make it
easier for others to set up these systems by automating significant portions of the work, like deciding which
features to use. Current research methods will be analyzed and evaluated to find the best methods. Overall, the
goal is to create smarter recommender systems that can learn on their own with less human help, while also
making the recommendations more accurate and helpful for customers.

Voir la description complète du projet
Superviseur du corps professoral :

Eldan Cohen

Étudiant :

Partenaire :

Crossing Minds Canada Inc.

Discipline :

Computer science

Secteur :

Professional, scientific and technical services

Université :

University of Toronto

Programme :

Accelerate

Detection of Cloud Network Traffic Abnormalities

This research project aims to develop a technique for detecting and analyzing security incidents in their early stages, reducing the potential impact on an organization’s operations. Conventional methods of deep packet inspection (DPI) and network monitoring solutions only identify frequently occurring traffic patterns, and security threats are often not detected until it’s too late. The project investigates a new approach that takes a “horizontal perspective” to detect outliers by identifying packets with out-of-distribution attributes and a “vertical perspective” to detect unusual patterns formed by common packets during a certain interval. The project will also develop countermeasures for specific attacks and general abnormalities. The expected benefit for the partner organization is early detection of security incidents, reducing the risk of data breaches and damage to the organization’s operations.

Voir la description complète du projet
Superviseur du corps professoral :

Dehan Kong

Étudiant :

Partenaire :

SOTI Inc

Discipline :

Computer science

Secteur :

Information and cultural industries; Professional, scientific and technical services

Université :

University of Toronto

Programme :

Accelerate

Étude de la variation des propriétés physiques et chimiques du bois du pin sylvestre

Le pin sylvestre (Pinus sylvestris) fait partie des espèces les plus dominantes de la forêt méditerranéenne et il est connu pour sa croissance rapide et sa capacité d’adaptation à divers sites écologiques. Dans cette étude, plusieurs méthodes seront utilisées (densitomètre à rayon X et la spectroscopie proche infrarouge (NIRS)) pour déterminer les propriétés physiques (densité) et chimiques (cellulose, hémicellulose, lignine et extractibles) de cette essence. L’objectif général de ce travail est d’étudier les différents caractères de la qualité du bois du pin sylvestre et leurs variations. Plus précisément, nous allons évaluer la croissance, la densité des cernes et les caractéristiques chimiques de cette essence. Les programme d’amélioration génétique des arbres forestiers profitent bien des résultats de cette étude sur les propriétés du bois pour les intégrer comme critères de sélection.

Voir la description complète du projet
Superviseur du corps professoral :

Mebarek Lamara

Étudiant :

Partenaire :

Municipalité régionale de comté d'Abitibi

Discipline :

Life Sciences

Secteur :

Forestry; Natural Resources; Environmental Science and Technology

Université :

Université du Québec en Abitibi-Témiscamingue

Programme :

Accelerate

Navigation and dynamic obstacle avoidance for UAVs in cluttered indoor GPS-denied environments

With the evolution of unmanned aerial vehicles (UAVs) in recent years, more and more researchers are setting their sights on the application research of indoor environment. Indoor applications include industrial facility inspection, warehouse inventory management, health sector, search and rescue, among others. However, the use of UAVs in these applications requires continuous high-accuracy positioning and pose information, and consequently an efficient obstacle avoidance algorithm. The current implementation uses Visual Inertial Odometry (VIO) to compute pose information, rapidly exploring Random Trees (RRTs) for path planning, and the PX4 stack for navigation. The goal of the project is to design an obstacle avoidance system which can avoid both static and dynamic (slow and fast moving) objects while executing optimal path planning strategy.

Voir la description complète du projet
Superviseur du corps professoral :

Igor Gilitschenski

Étudiant :

Partenaire :

SOTI Inc

Discipline :

Computer science

Secteur :

Information and cultural industries; Professional, scientific and technical services

Université :

University of Toronto

Programme :

Accelerate

Wi-Fi SSID Based Positioning System

The use of indoor location-aware applications such as augmented reality, social networking, health care monitoring, asset tracking, and inventory control is on the rise. However, accurately locating Wi-Fi based devices within buildings can be a challenge, particularly in areas where GPS signals are unavailable. This research project focuses on finding ways to locate indoor devices with high precision using Wi-Fi signal patterns and strength, combined with GPS markers gathered from other devices. By analyzing a large dataset of mobile devices, the goal is to identify the most effective techniques for accurately locating Wi-Fi devices in GPS-denied environments

Voir la description complète du projet
Superviseur du corps professoral :

Dehan Kong

Étudiant :

Partenaire :

SOTI Inc

Discipline :

Computer science

Secteur :

Information and cultural industries; Professional, scientific and technical services

Université :

University of Toronto

Programme :

Accelerate

Précédent
1...971972973974975976977...2,513
Suivant

Joignez-vous à un écosystème d’innovation florissant.

Abonnez-vous à notre infolettre dès maintenant!

S’inscrire