Innovative Projects Realized

Creative Artificial Intelligence in Interactive Mobile Systems

The large amount of information available today on the web brings many challenges to the information retrieval and artificial Intelligence communities. Moreover, personalization is a key component in today’s successful mobile websites and interactive applications. In order to be effective, these websites are required to provide visitors with the information they need without the complexity in finding it. Developing intelligent and interactive systems with visual user interfaces is therefore essential for any mobile device. In this regard, our goal is to develop a new interactive mobile tool that elicit and lean users’ requirements and preferences, in order to provide them with what they actually need. This will be achieved by taking advantage of the advancement of artificial intelligence as well as the new 5G technologies.

IoT device fingerprinting and anomaly detection using ML

The number of Internet of Things (IoT) devices is expected to reach 50 billion devices by 2020 and the devices are increasingly diverse. They are disrupting traditional security measures. Mobile Network Operators (MNOs) have limited control over customers’ IoT devices, as they are deployed on the customer premises. MNOs need to deploy effective security controls at their end to protect their assets. Huge amounts of data are generated by IoT devices, which can be exploited to understand device behaviours. The proposed research program aims at finding novel solutions to the problem of detecting abnormal behaviour in IoT environments. When abnormal network traffic is detected, two solutions can be adopted: blocking the traffic, or sending it for deeper analysis. The first solution may disconnect legitimate IoT devices, as certain behavior deviations are quite normal, e.g., bandwidth fluctuation. The second solution attempts to learn more about IoT devices and refine the learned behaviour model. This is a real-time and continuous learning process that adapts the model to a changing environment, e.g., new device types. Therefore, sophisticated IoT fingerprinting exploiting machine learning algorithms is the ultimate objective to achieve.

New Method for Delivering Protectants into Honey Bee Hives

Pollination services provided by honey bees is imperative to crop production in Canada. Unfortunately, honey bee health is compromised by pests and diseases leading to the decline and/or death of hives and decreased pollination. In this project we will implement the usage of a special inspenser to bring in materials that will protect the honey bees from pests and diseases. These inexpensive inspensers will decrease the workload of already busy beekeepers, while also improving the overall health of the hives. Our partner organization, George Weston Limited, is the largest grocery retailer in Canada, providing food to over 34% of Canadians. Healthy beehives provide better pollination resulting in more food to be delivered to Canadian grocery stores at a lower cost to farmers, beekeepers, and grocery store retailers.

Advancing Strong-Scaling CFD Simulations on Manycore HPC Hardware

Science and engineering companies rely on powerful computers to simulate, in virtual space, the performance of new processes and products. The computer architectures of these systems are evolving to provide even faster virtual solutions with less energy requirements. This hardware evolution impacts software design and implementation of simulation tools such as Computational Fluid Dynamics (CFD). The intern’s project involves software design and implementation related to novel CPU/GPU parallel computers and the CFD software used by the partner organization. The CFD software is essential to product development activities requiring efficient use of powerful supercomputers.

Management practices to improve sustainability and profitability of cow-calf operations across Canada

The purpose of this project if to develop a Canadian Cow-Calf Cost of Production (COP) Network including of 26 different focus group sessions across Canada, located in different eco-regions, to gather production and economic data following agribenchmark global agriculture network methodology.

This data will also be used to assess greenhouse gas emissions associated with the farm scenarios/typologies identified above. It will offer a unique opportunity to identify important practices associated with both increased profitability and sustainability that are specific to individual eco-regions and production systems.

Development of a salmon diet using alternative protein and lipids suitable for land-based recirculation farming systems

Aquaculture feed has historically relied on fish-based protein sources to satisfy nutritional requirements for optimal growth. While plant-based proteins are increasing throughout the aquaculture industry, the need for fish protein is still present to ensure the “natural fish” taste that consumers want. Black Soldier Fly Larvae (BSFL) have been proposed as a solution to this problem as they contain the same compounds responsible for the desired taste. This project looks to determine the effectiveness of protein from BSFL and a proprietary lab-grown marine agent within Atlantic salmon feed. This will be performed over three feed trials, the first of which will be 14-weeks and undertaken during this Mitacs internship. This project will also be testing the ability of the BSFL and marine agent components in providing more solidified fecal matter for improved water quality in land-based aquaculture facilities which recirculate their water.

Surveillance of potential wildlife and domestic animal reservoirs for SARS-CoV-2

Canada’s northern communities are particularly vulnerable to infectious disease because of social determinants of health plus their widespread harvesting of wildlife. The current COVID-19 pandemic is of particular concern to northern peoples and governments since their food security and livelihood needs are often directly dependent on the human-animal interface, at which COVID-19 can transmit in both directions. Although response planning and preparations are well underway by those governments, the challenges they face will be severe and compounded by all the normal challenges of providing services in the north. In collaboration with academic researchers, territorial governments, and private companies in multiple sectors we aim to address critical gaps in our understanding of the COVID-19 pandemic by generating genome sequences of all human and potential zoonotic coronaviruses, especially in the prairies and Northern Canada. This will provide critical information to fill current gaps in the north’s evolving strategy to address the spread of COVID-19, including development of appropriate risk communication, contact tracing, and rapid, locally based diagnostics.

Graphene-based Corrosion Protective Coatings

Globally, all small and large industrial operations pay high and increasing costs to compensate for the damage and losses caused by corrosion. Based on the statistics, in Canada, various industries spend more than $80 billion per year collectively to cover the direct and indirect costs of corrosion. Annually, hundreds of people are injured or killed due to accidents caused by corrosion damage to industrial equipment. The central theme of this research proposal is to design a new generation of graphene-based corrosion protective coatings for metallic surfaces with complex shapes. This research program specifically targets the conversion of Albany Pure Graphite powder to advanced graphene-based nanostructures such as graphene, graphene oxide (GO), and reduced graphene oxide (rGO) via a novel chemical/electrochemical technique. The graphene synthesis technology will allow ZEN to convert its Albany Pure Graphite to value-added graphene at a large scale. The success of this project will lead to new protective coating technologies, Which has the potential to save billions of dollars for Canadian industries by reducing corrosion-induced material damage. The development of graphene-based coatings with corrosion inhibition properties will also result in positive environmental impacts, as durable protective coatings will prevent the leakage of hazardous chemicals into the environment.

Estimating Apple Crop Yield using Images

As a high-value crop, apples are intensively managed with much of this management being associated with yield estimates. Currently, estimates are done manually by experience farmers and by Scotian Gold experts. Unfortunately, this results in costly estimates that vary in their quality from farm to farm and between apple varieties. A system that can provide consistent and accurate estimates using low cost digital photography and cloud-based artificial intelligence can provide an opportunity to improve production and marketing for the industry. The objectives of this project are: (1) to develop a method of capturing images of an apple variety on the tree in the mid-August time frame; (2) to develop a computational vision and machine learning prototype for estimating the size and number of apples on a tree using the images captured; and (3) to use these estimates to predict the harvest yield (bushels per acres) adjusting for forecasted weather.

Technology for Assessing Neurocognitive Functioning; Validation of Mobile Cognitive Assessment Technology using fMRI

There is growing concern that COVID-19 has neuroinflammatory effects which can have acute or sustained impacts on cognition. Tablet-based games can be used to monitor cognition in medical settings but have not been validated as measures of brain function. The current project will administer a suite of tablet-based measures of cognition as images of the functioning brain are acquired using an MRI scanner. The results will help to identify brain networks that play a critical role in higher-order cognition and that are activated in association with performance of game-based assessments of cognition.

Modeling Ekona’s H2 production and carbon capture process

Ekona Power Inc is developing a technology to convert natural gas into H2, electricity and a pure CO2 stream. The CO2 stream will them be removed using underground carbon sequestration. Their approach uses two processes. The first uses pyrolysis to convert natural gas to hydrogen and solid carbon. The second uses a fuel cell to convert the solid carbon to a pure CO2 stream. This proposal concerns the first process.
Ekona is currently finalizing the design of pyrolysis unit and preparing for the pilot scale testing. However Ekona doesn’t have expertise in the detailed chemical kinetic modeling the pyrolysis of natural gas which includes the formation of solid carbon particles. The Thomson Lab at the University of Toronto has over a decade of experience in developing and validating models of hydrocarbon pyrolysis and carbon particle formation. The proposed modeling approach will allow Ekona to better understand its pyrolysis design and anticipate the performance of the prototype unit.

Enhancement of Virtual Synchronous Machine Algorithms with Energy Storage

Modern electric power systems are rapidly adopting renewable energy resources. This positive movement, however, does bring with it major challenges to the way we operate power systems. In particular we may face drastic frequency changes and far-reaching transient phenomena. One way to remedy these is to deploy energy storage systems, such a s batteries, to assist the power system in maintaining its frequency and in releasing and absorbing bursts of power that are required to do so. This internship will look into developing methods for using energy storage in conjunction with power-electronic converters so that local sources/sinks of power available to the converters that assist in maintaining the system’s frequency.