Innovative Projects Realized

AI based multi-phase flow meter

The persistent challenge faced by oil producers in measuring multi-phase flows, characterized by a complex mixture of oil, gas, and water from wells, has prompted the development of an AI-based multi-phase flow meter by MLCan. Current approaches to real-time precision are hindered by the inherent complexity of these flows, leading to costly and less accurate measurements. Additionally, conventional techniques involve phase separation, posing environmental risks and generating increased waste. MLCan’s innovative meter, equipped with pressure and temperature sensors, bypasses the need for phase separation, capturing flow data for individual components. Processed through an AI algorithm, this data enables the meter to provide real-time and online estimations. The research aims to comprehensively study oil wells in Alberta, creating a dataset for various oil resources and implementing machine learning algorithms for evaluation.

Identifying the impact of social determinants of health on the incidence and outcomes associated with acute kidney injury using a machine learning approach

Acute kidney injury (AKI) is a syndrome which involves a sudden decrease in kidney function because of functional or structural impairment. It is a global issue and affects more than 7% of hospitalization in Canada. Unfortunately, although there has been improvement in the recognition and management of AKI, it continues to be a disease associated with poor outcomes. Furthermore, we know that the social determinants of health have a significant impact on outcomes; however, there is very limited information available in AKI. This project will utilize machine learning to identify high risk populations with AKI and determine the intersection with the social determinants of health. The partner organization will have the opportunity to generate important information to help guide future health policy decisions for patients with AKI.

Distributed Energy Resources Management for Grid Modernization and Grid Transformation Applications

Ambitious 100% net-zero emissions targets, the growing proliferation of distributed energy resources including wind, solar photovoltaic and battery energy storage, and a rise in modern loads such as high capacity electric vehicle charging stations are ushering Canadian utility companies through a major transformation in how electrical distribution grids are managed and operated. Consequently, the traditional passive and mostly static distribution networks are rapidly evolving into more complex, active, and dynamically changing systems. This poses several challenges to distribution system utilities in how they operate, manage and optimize the use of distributed energy resources within their system. This research project will help address these challenges within the context of grid modernization and grid transformation applications.

Probabilistic safety evaluation of the effective area methods for the assessment of crack and corrosion defects in pipelines

Pipeline integrity management involves effectively managing various threats, including cracking and corrosion. Crack and corrosion threat management has evolved keeping pace with advancements in the Inline Inspection (ILI) technologies which are primary tools for detection and sizing of crack and corrosion features on a pipeline. With the high-resolution inspection data obtained through ILI tools, the ILI vendors can report features’ profiles with varying depths along the length of crack and corrosion features. Compared to the past, when features were reported with a single maximum depth value that was assumed for the full length, the pipeline operators conservatively assumed the maximum feature’s depth in their assessment analysis. The goal from this research project is to develop an approach to utilize features’ profiles in the reliability analysis of crack and corrosion threats.

Examining the Effects of Cannabis-based Edibles on Cognitive Health and Simulated Driving Performance in Young Drivers

There is increasing evidence showing an increase in motor vehicle crashes associated with young drivers who consume cannabis. While studies show that smoking or vaping cannabis is associated with impaired driving performance, there have been no studies examining the influence of edibles on driving performance. Additionally, prior studies have not defined the type of cannabis tested in research studies and there is a strong likelihood that different cannabis strains produce different impairments related to driving performance. Using a driving simulator, the objectives of the present study are to 1) to discern the effects of cannabis types (sativa and indica) on driving performance; 2) to determine at what time driving is most impaired; 3) to examine how long driving ability is impaired after edible consumption; and 4) to examine the association between driver perceptions, cognitive health, and driving performance.

Robotic gantry for Wire Arc Additive Manufacturing

Wire Arc Additive Manufacturing (WAAM) is a method of 3D printing using arc welding to build up shapes out of weld metal. The project aims to build an in-expensive gantry for mounting welding equipment to carry out WAAM and a control system with AI integration for the robot to which can learn about the complex interplay between welding variables and the final dimensional & materials properties of the printed parts.

Refining and Launching a Digital Commons for the Canadian Humanities and Social Sciences to Facilitate Community-based Open Scholarship

The proposed project focuses on the research, analysis, and engagement of the Canadian Humanities and Social Sciences (HSS) Commons: an open, digital platform for research collaboration and sharing. This collaboration builds on Iter Canada’s investment in related work since 2008, extends previous Mitacs-funded work, and is undertaken by a multi-career level team. When complete, the Canadian HSS Commons will serve communities such as those represented by Iter Canada and groups beyond, as it empowers individual researchers to develop, exchange, and share open access publications, drafts, preprints, datasets, and teaching materials through a national-scale, bilingual (French and English) platform, which combines many features of institutional repositories and social networking sites.

Improving Medication Safety and Prescribing for Individuals with Chronic Kidney Disease (CKD) through the Development, Validation, Implementation and Evaluation of an Electronic Drug Dosing and Decision Support Kidney (eDose CKD) Tool for Nova Scotia Primary Care Pharmacists

Chronic kidney disease (CKD) occurs in 1 out of 10 Canadians. The kidneys are responsible for the removal of many drugs. These drugs may require adjustment to avoid buildup. Individuals with CKD tend to be older and take many medications due to chronic conditions. Considering these factors, the risk of unwanted drug effects or harm are high. A primary care review revealed nearly 20% of high-risk medications should have been dose-adjusted. Community pharmacists are in an ideal position to mitigate harm. Recent interviews of pharmacists identified the need to develop an electronic drug dosing and decision support kidney (eDoseCKD) tool for community pharmacy practice for commonly prescribed high-risk medications to reduce the risk of adverse drug events. This research will encompass tool development, validation, implementation, and evaluation in community pharmacy sites. This work may be scalable to other NSH sites or clinics affiliated with the partner to optimize medication safety.

Web3D Ecosystems: Advancing ICT with a Decentralized Metaverse Platform

The research aims to create a new development platform for building apps that connect easily on decentralized networks with security agreements for digital transactions. This will help protect users’ privacy, handle more users at once, and make it easier for developers to create decentralized apps. Additionally, the project will develop a system that uses artificial intelligence to create virtual worlds and characters, which will help Canadian businesses create innovative and immersive digital experiences. This research could lead to better privacy, increased capacity, and simpler development processes for Canadian businesses looking to explore digital worlds, ultimately making these spaces more secure and user-friendly.

Nanostructured metal oxide hydrogen sensors for enhanced performance

With the rapid growth in green hydrogen production and utilization, there is a need for cost-effective, high-performance hydrogen sensors. For example, green hydrogen is being produced at the gigawatt scale for a range of applications and industries. In particular, use of hydrogen in transportation (fuel cells) and for blending in natural gas for heating has prompted the need for higher performance sensors to guarantee safety. The US DOE has published aggressive metrics in terms of detection limits and response speed that have yet to be attained. This project will develop new nanotechnology enabled sensors to that will achieve these metrics to be met with low-cost production and widespread deployment.

Validation of a novel ionizable lipid library

Tiny particles made of fat are an established system for delivering genetic materials into cells to perform gene therapy. The project is focused on optimizing the fat structure and composition to improve genetic material delivery and target to different parts of the body. We will engineer a library of fat particles made with different combinations of fats. We will study their gene delivery efficiency in small animals. Results from this research will help us develop a better delivery system for genetic materials for improved gene therapy for many diseases.

Artificial-Intelligence-Supported In-Hospital Cardiac Arrest Prediction, Prevention, and Management

In-hospital cardiac arrest is one of the most challenging and overlooked health issues worldwide. Even with care teams dedicated to rapid response when an arrest occurs, only about 1 in 5 patients survive. Since a person’s chance of survival goes down with every minute they are not treated after the arrest, we need to find ways to act before this downward spiral. As many of these cardiac arrests are preventable, if we could figure out which ones we should be able to prevent and how, we could improve patient survival much more than by treating them only after arrests occur.

We will use artificial intelligence to create models that predict and inform which patients are at the most risk of cardiac arrest, whether the arrest might be preventable, and what actions have the best chance of preventing the arrest.

With these models, we’ll be able to identify the unique risks and needs of each patient and respond with the evidence-based actions most likely to prevent a cardiac arrest. In addition, the models will help patients and their healthcare providers have better conversations about the goals of their care, and the kinds of choices they want to make.