Mitacs Project Delivery Completed Projects

Multi-Domain Recommendation for Restaurants Using GNN Models

The student will develop a recommendation system for restaurants, proposing food selections to customers. This system will be based on GNN models to predict a customer’s need based on both user and order data. The data include previous purchases, data of dishes and similarity of users collected from online food orders. In the first phase the model will be trained on a specific domain (pizza, sushi, etc.) with good and sufficient data. Then the student will apply recent deep learning innovations to cross-domain restaurants with limited data. Through better recommendations for users, the system is expected to increase the value of orders and revenues of restaurant.

View Full Project Description

Faculty Supervisor:

Ioannis Mitliagkas

Student:

Partner:

UEAT Technologies Inc

Discipline:

Computer science

Sector:

Information and cultural industries; Professional, scientific and technical services

University:

Université de Montréal

Program:

Accelerate

Weather and Climate Information for Snow Recreation

Individuals and organizations use weather information to help inform day-to-day decisions. This project focuses on the use of weather information by winter recreationists in the Province of Ontario. Based on survey data, the project will identify the main sources of weather forecast information, the importance placed on this information, and the influence of specific aspects of such information in decision making. Analysis of climate weather-station data will also be completed to understand the influence of micro-climatic factors on observed weather at one Ontario ski resort. Both the Ontario Snow Resort Association and the Ontario Federation of Snowmobile Clubs serve their members by being a provider of key information for strategic and operational planning. The proposed research will address some of the knowledge gaps related to weather information utilization by winter recreationists, including skiers, snowboarders and snowmobilers

View Full Project Description

Faculty Supervisor:

Jean Andrey

Student:

Partner:

Ontario Snow Resorts Association;Ontario Federation of Snowmobile clubs

Discipline:

Earth science

Sector:

Accommodation and food services; Arts, entertainment and recreation

University:

University of Waterloo

Program:

Accelerate

2021 Massawippi Watershed Hydrologic Flux Report of Water and Soil Quality Components

This project aims to study and assess nutrient conditions in Lake Massawippi and its surroundings. Previous studies suggest that fertilizer contaminants from various agricultural plots flow to nearby waters, especially the adjacent Tomifobia river. Our team will assess soil, and water components for net transfer of nutrient and other particle contamination. These measurements will be assessed with statistics to determine the source(s) of these flow conditions. This corresponding report will assess the following hypotheses: (1) that nutrient flows from the southeast are connected to Lake Massawippi within and underneath the Tomifobia river, and (2) that cattle farming and general agricultural fertilizers, not residential waste, nor recreational fertilizer applications, are the main sources of these nutrient and particle flows into the lake. Understanding these sources is necessary to maintain ideal water quality conditions in the lake and nearby residential communities.

View Full Project Description

Faculty Supervisor:

Jan Franklin Adamowski

Student:

Partner:

Blue Massawippi

Discipline:

Earth science

Sector:

Other services (except public administration)

University:

McGill University

Program:

Accelerate

Identifying forests with old growth potential in the Credit River Watershed

Old growth forests provide important ecological services including carbon storage and habitats for a diverse array of species, yet they are often rare across the landscape. These forests are often challenging to identify due to the lack of concrete definitions of what constitutes old growth, as well as the lack of understanding of the typical features of old growth forests. This work aims to identify sites with old growth potential by using field and remote sensing methods to evaluate common old growth characteristics, while also developing a suite of indicator values to assist in the future identification of potential old growth sites. This project will help the partner organization address an objective of their recently developed Sustainable Forest Management Plan, contributing to the overall health and resilience of forests in the Credit River Watershed.

View Full Project Description

Faculty Supervisor:

Jay Malcolm

Student:

Partner:

Credit Valley Conservation Authority

Discipline:

Life Sciences

Sector:

Professional, scientific and technical services; Public administration

University:

University of Toronto

Program:

Accelerate

Automated AI-Based Phishing Solution

Phishing emails are a common form of a cyber attack. Attackers use leading content to fraud victims, such as fake banking information, forged Google Alert messages, and so on. Phishing attacks have been around for years, causing countless serious consequences, such as financial losses and confidential documents leaks. As of now, there is still no admitted effective way to detect phishing emails. This project will aim at phishing emails and provide solutions to automatic detection and identification by artificial intelligence. We will also collect data from the phishing content and analyze cyber threat intelligence from various open-source information sharing platforms.

View Full Project Description

Faculty Supervisor:

Xiaodong Lin

Student:

Partner:

KPMG LLP (Toronto, ON)

Discipline:

Computer science

Sector:

Professional, scientific and technical services

University:

University of Guelph

Program:

Accelerate

Cyber Threat Intelligence Integration with MISP Threat Sharing

In the recent technological age, new threats and attacks emerge nearly every day. It might be against everyone on the internet or targeted towards specific organizations and individuals. Attackers have begun to use highly sophisticated techniques and technologies to attain their objectives. It’s a high time, the defenders scale up to defending their infrastructure against every type of intruder. This project emphasizes on building one of the core dependencies of a security infrastructure, the Malware Information Sharing Platform, to detect and thwart these attacks. A machine learning based approach is executed for correlating the threat data to identify the threat types, vulnerabilities and gain an understanding of threats that could target the organization. This platform will be of immense benefit to the partner organization, Bruce Power, to protect its software infrastructure and employee, customers’ data from exfiltration.

View Full Project Description

Faculty Supervisor:

Ali Dehghantanha

Student:

Partner:

Bruce Power

Discipline:

Computer science

Sector:

Utilities

University:

University of Guelph

Program:

Accelerate

Anomalous DNS Query Detection Using Machine Learning Approaches

For organizations that use the Internet, their employees will visit thousands of websites every day. However, there is a chance that the destination website is not safe to visit. Such websites may be fraudulent, phishing, or even data-stealing related. On the other hand, determining if the target website link is suspicious or not could help to prevent potential harm. Using a filtered list is the most straightforward way. The problem is, as the database for malicious websites is growing, hackers’ minds are also developing, which requiring a more profound way to deal with such a problem. This project aims to find any anomalous website visit attempt by using machine learning algorithms to solve the problem. As eSentire is a cybersecurity company dedicated to bringing solutions to companies who are having cybersecurity concerns, this project will serve as a reference for eSentire to solve related problems with more options.

View Full Project Description

Faculty Supervisor:

Hassan Khan

Student:

Partner:

eSentire

Discipline:

Computer science

Sector:

Information and Communications Technology; Artificial Intelligence; Technology

University:

University of Guelph

Program:

Accelerate

Land-use change analysis for the Annapolis Valley Sand Barrens, a globally rare ecosystem at risk

This project will support the development and implementation of a collaborative conservation strategy for the Annapolis Valley Sand Barrens, a globally rare and endangered ecosystem found in Nova Scotia. It has been estimated that only 3% of the Annapolis Valley Sand Barrens remains today, lost primarily due to competing land-uses such as urban development, agriculture and quarrying. More specifically, the project will help to identify and prioritize areas for various land protection and stewardship activities, quantify the extent of impacts from various competing land-uses, and to evaluate baseline conditions for long-term effectiveness monitoring indicators. This work will contribute to provincial and federal biodiversity conservation commitments made through the Accord for the Protection of Species at Risk and re-affirmed through the Pan-Canadian Approach to the Transformation of Species at Risk Conservation in Canada.

View Full Project Description

Faculty Supervisor:

David Colville;Ian Spooner

Student:

Partner:

Clean Annapolis River Project

Discipline:

Life Sciences

Sector:

Professional, scientific and technical services

University:

Acadia University; Nova Scotia Community College

Program:

Accelerate

Automation & Orchestration for Improved Security Communication

Speed is incredibly important when addressing issues with computer security. The longer the time between the attack’s start and resolution, the more assets that attackers can steal from a company. There are various security platforms that can alert a company to a cyber-attack. This research project aims to combine knowledge from all these platforms together at faster speeds than a human would be able to do. The cooperation between security platforms will allow ISA Cybersecurity Inc. to detect and respond to cyber-attacks faster than previously possible. This will benefit them in protecting business, and by proxy Canadian citizens, data from cyber criminals.

View Full Project Description

Faculty Supervisor:

Charlie Obimbo

Student:

Partner:

ISA Cybersecurity

Discipline:

Computer science

Sector:

Professional, scientific and technical services

University:

University of Guelph

Program:

Accelerate

Optimization of key-to-key collision repair process system

The intent of this project is to reduce the cycle time in the vehicle repair process across the Carstar network. The project also includes developing process models that will help in guiding Carstar to reduce cycle time in major process steps for all stores of varying size and disparate locations. During the process of investigation and analyzing the data, the waste (inventory limitations, conflicts, redundant process steps and blockage) will be identified and eliminated. Also, the cost analysis will be documented for each part of the repair process to help show the value of improving the process and the impact on severity, touch time etc. Establishing new process models with improved cycle time will benefit company to remain competitive in repairing vehicles with best quality, at lowest price and at the same time helping the Carstar be profitable.

View Full Project Description

Faculty Supervisor:

Robert Fleisig

Student:

Partner:

Carstar Automotive Canada

Discipline:

Engineering

Sector:

Other services (except public administration)

University:

McMaster University

Program:

Accelerate

Building and Evaluating a Consolidated SIEM (Security Information and Event Management) Threat Identification

Businesses are collecting more and more data, but they do not have the manpower to properly analyse it. This project will implement a proof of concept for a system that uses machine learning to improve the detection of cyber threats. The machine learning algorithm will receive information from many different data sources, detect where there is suspicious activity, and alert a cyber analyst. By adding a machine learning algorithm to the arsenal of cyber analysts, the analysts will be able to cut down on the time it takes to react to the threats. The project will produce reports and documents analyzing the effectiveness of the machine learning algorithm.

View Full Project Description

Faculty Supervisor:

Rozita Dara

Student:

Partner:

Farm Credit Canada

Discipline:

Computer science

Sector:

Finance and Insurance

University:

University of Guelph

Program:

Accelerate

Creating a comparison and alert methodology for managing the CCTX feed

Most collaborations and government departments share their threat data feed in Data Exchange. Inescapably, nowadays with increasing threat data, it is a challenge to extract a large amount of threat data and unify the format more quickly. And as more and more companies join in sharing, the redundancy of this duplicate data will increase dramatically. This project proposes machine learning algorithms for automatic format conversion to extract threat information from the traffic data, and convert them into STIX format and detect whether these structured feeds already exist in CCTX. And a dashboard is developed for security analysts to compare the frequency in feeds.

View Full Project Description

Faculty Supervisor:

Ali Dehghantanha

Student:

Partner:

Canadian Cyber Threat Exchange

Discipline:

Computer science

Sector:

Other services (except public administration)

University:

University of Guelph

Program:

Accelerate

Innovative Projects Realized

31620 Completed Projects

Projects by Category

Multi-Domain Recommendation for Restaurants Using GNN Models

Multi-Domain Recommendation for Restaurants Using GNN Models

Weather and Climate Information for Snow Recreation

Weather and Climate Information for Snow Recreation

2021 Massawippi Watershed Hydrologic Flux Report of Water and Soil Quality Components

2021 Massawippi Watershed Hydrologic Flux Report of Water and Soil Quality Components

Identifying forests with old growth potential in the Credit River Watershed

Identifying forests with old growth potential in the Credit River Watershed

Automated AI-Based Phishing Solution

Automated AI-Based Phishing Solution

Cyber Threat Intelligence Integration with MISP Threat Sharing

Cyber Threat Intelligence Integration with MISP Threat Sharing

Anomalous DNS Query Detection Using Machine Learning Approaches

Anomalous DNS Query Detection Using Machine Learning Approaches

Land-use change analysis for the Annapolis Valley Sand Barrens, a globally rare ecosystem at risk

Land-use change analysis for the Annapolis Valley Sand Barrens, a globally rare ecosystem at risk

Automation & Orchestration for Improved Security Communication

Automation & Orchestration for Improved Security Communication

Optimization of key-to-key collision repair process system

Optimization of key-to-key collision repair process system

Building and Evaluating a Consolidated SIEM (Security Information and Event Management) Threat Identification

Building and Evaluating a Consolidated SIEM (Security Information and Event Management) Threat Identification

Creating a comparison and alert methodology for managing the CCTX feed

Creating a comparison and alert methodology for managing the CCTX feed

Join a thriving innovation ecosystem.

Subscribe to our newsletter now!

Innovative Projects Realized

31620 Completed Projects

Projects by Category

Filter By

Multi-Domain Recommendation for Restaurants Using GNN Models

Multi-Domain Recommendation for Restaurants Using GNN Models

Weather and Climate Information for Snow Recreation

Weather and Climate Information for Snow Recreation

2021 Massawippi Watershed Hydrologic Flux Report of Water and Soil Quality Components

2021 Massawippi Watershed Hydrologic Flux Report of Water and Soil Quality Components

Identifying forests with old growth potential in the Credit River Watershed

Identifying forests with old growth potential in the Credit River Watershed

Automated AI-Based Phishing Solution

Automated AI-Based Phishing Solution

Cyber Threat Intelligence Integration with MISP Threat Sharing

Cyber Threat Intelligence Integration with MISP Threat Sharing

Anomalous DNS Query Detection Using Machine Learning Approaches

Anomalous DNS Query Detection Using Machine Learning Approaches

Land-use change analysis for the Annapolis Valley Sand Barrens, a globally rare ecosystem at risk

Land-use change analysis for the Annapolis Valley Sand Barrens, a globally rare ecosystem at risk

Automation & Orchestration for Improved Security Communication

Automation & Orchestration for Improved Security Communication

Optimization of key-to-key collision repair process system

Optimization of key-to-key collision repair process system

Building and Evaluating a Consolidated SIEM (Security Information and Event Management) Threat Identification

Building and Evaluating a Consolidated SIEM (Security Information and Event Management) Threat Identification

Creating a comparison and alert methodology for managing the CCTX feed

Creating a comparison and alert methodology for managing the CCTX feed

Join a thriving innovation ecosystem.

Subscribe to our newsletter now!